{"version":1,"narrative":{"title":"Emre Tesseract","intro":"Welcome. Sometimes na the tone for one Turkish sentence catch my ear. Sometimes na wetin one quantum measurement fit tell us. See where those questions carry me go.","domains":[{"id":"meaning","title":"Meaning and ontologies","entries":["project:meaning-native-computing","note:ontologies-and-data-structures","note:category-theory","patent:2026-007907","patent:2026-006289","patent:2025-008786"]},{"id":"language","title":"How computers process language","entries":["repository:turkish-binary-reviews","work:turkish-asr","topic:language","work:chat-assistant","work:ai-pos","work:qwen-grpo","work:turkish-reasoning-benchmark","work:multilingual-chatbots","work:ad-text-classification","work:weight-editing","work:bloom","patent:2026-007909","patent:2023-011870","model:turkish-sentiment","model:whisper-tr","model:gemma-wiki-tr","model:java-method-vectors","model:gemma-reasoning-tr","model:abstract-title","model:xlsr-tr","model:qwen-grpo","repository:webcli","study:turkish-sentiment-evaluation"]},{"id":"learning","title":"Machine learning","entries":["repository:regression-atlas","work:weight-editing","work:coverage-deferral","patent:2025-011133","repository:fairness-metrics","repository:worldcup-nowcast","repository:turkish-binary-reviews","study:coverage-deferral"]},{"id":"confidence","title":"Conformal prediction","entries":["work:coverage-deferral","topic:uncertainty","topic:fairness","project:meaning-native-computing","work:quantum-conformal","work:tara","work:adversarial-quantum","patent:2026-004441","repository:regression-atlas","repository:bird-sql","repository:fairness-metrics","repository:worldcup-nowcast","study:coverage-deferral"]},{"id":"quantum","title":"Quantum computing","entries":["work:quantum-conformal","topic:quantum","note:quantum-measurement","work:tara","work:adversarial-quantum","patent:2026-004441","repository:quantum-clocks"]},{"id":"invention","title":"Inventions","entries":["patent:2026-004441","patent:2023-011901","topic:invention","work:chat-assistant","work:micro-robot-rescue","work:ai-pos","work:virtual-input","work:personalized-suggestions","patent:2026-007909","patent:2026-007907","patent:2026-006294","patent:2026-006289","patent:2026-004444","patent:2026-002909","patent:2026-001992","patent:2025-019989","patent:2025-011133","patent:2025-008786","patent:2025-008273","patent:2025-008055","patent:2025-008032","patent:2025-008028","patent:2025-007997","patent:2025-007995","patent:2024-003815","patent:2024-003813","patent:2024-003592","patent:2023-011870","patent:2023-011830","patent:2023-011601","patent:2023-011600","patent:2023-011599","patent:2023-004244","patent:2023-004047","patent:2022-016679","patent:2022-016395"]},{"id":"agents","title":"Agent systems","entries":["work:agent-chronicle","topic:agents","work:chat-assistant","work:micro-robot-rescue","work:weight-editing","patent:2025-007995","repository:bird-sql","repository:webcli","repository:paperbanana-test","repository:agent-chronicle"]}],"stories":[{"id":"project:meaning-native-computing","domain":"meaning","title":"Di next move wey program go make","text":"For Meaning-Native Computing, I dey check whether a model wey sabi di program rules fit predict di next instruction better. Another check dey decide whether di rules allow dat step to run.","year":"","companions":["note:ontologies-and-data-structures"],"url":"/pcm/?scene=project%3Ameaning-native-computing#journey"},{"id":"repository:turkish-binary-reviews","domain":"language","title":"How Turkish review take sound","text":"I train one Turkish BERT model to tell positive review from negative one. For 2022 I release another model wey fit also recognise review wey no take either side.","year":"2021","companions":["model:turkish-sentiment"],"url":"/pcm/?scene=repository%3Aturkish-binary-reviews#journey"},{"id":"work:turkish-asr","domain":"language","title":"Make model hear Turkish","text":"We use Common Voice recordings teach one speech model wey don train for 53 languages how to write wetin person talk for Turkish. For di recordings we keep for test, di word error rate na 23%.","year":"2024","companions":["model:xlsr-tr","model:whisper-tr"],"url":"/pcm/?scene=work%3Aturkish-asr#journey"},{"id":"repository:regression-atlas","domain":"learning","title":"How wide forecast range suppose be?","text":"If di range wide well well, e easy for di real value to fall inside. I compare 67 datasets to see how often each method catch di value, and how wide di range need be.","year":"2026","companions":["work:coverage-deferral","work:quantum-conformal"],"url":"/pcm/?scene=repository%3Aregression-atlas#journey"},{"id":"work:coverage-deferral","domain":"confidence","title":"Whose case go reach person table?","text":"For my simulation with Adult data, di gap for coverage reduce when I calibrate each group on im own. But di gap grow for how often each group case go meet person for review.","year":"2025","companions":["study:coverage-deferral","repository:fairness-metrics"],"url":"/pcm/?scene=work%3Acoverage-deferral#journey"},{"id":"work:quantum-conformal","domain":"quantum","title":"Two qubits, four possible results","text":"If you measure two qubits, four different results fit come out. I use old examples to estimate di uncertainty for all four probabilities together, then I test di estimates with fresh data.","year":"2025","companions":["patent:2026-004441","note:quantum-measurement"],"url":"/pcm/?scene=work%3Aquantum-conformal#journey"},{"id":"patent:2026-004441","domain":"invention","title":"Find customer groups inside noisy data","text":"How steady di customer groups wey we find for financial data really be? For application TR 2026/004441, we propose quantum clustering to form di groups and conformal prediction to measure di uncertainty.","year":"2026","companions":["work:quantum-conformal"],"url":"/pcm/?scene=patent%3A2026-004441#journey"},{"id":"patent:2023-011901","domain":"invention","title":"Space wey one finger fit enter","text":"For di application we file for Türkiye, we describe one small robot with joints wey fit carry camera and pull cable enter rubble. Di international application for di same invention come out for 2025.","year":"2023","companions":["work:micro-robot-rescue"],"url":"/pcm/?scene=patent%3A2023-011901#journey"},{"id":"work:agent-chronicle","domain":"agents","title":"After di agent talk say “I don finish”","text":"I build Agent Chronicle so I fit follow wetin happen for one coding session from start to finish. From one decision, I fit see which files change and open di checks wey back di result.","year":"2026","companions":["repository:agent-chronicle","patent:2025-007995"],"url":"/pcm/?scene=work%3Aagent-chronicle#journey"},{"id":"work:weight-editing","domain":"learning","title":"One model fit repair another one?","text":"Wen I ask language models make dem edit one damaged classifier, balanced accuracy go up small for one run while overall accuracy come down. For intact SmolLM2, di searches pick di original weights.","year":"2026","companions":["work:coverage-deferral"],"url":"/pcm/?scene=work%3Aweight-editing#journey"}]},"lang":"pcm","startId":"profile:emre","stops":["profile:emre","project:meaning-native-computing","topic:uncertainty","work:coverage-deferral","topic:fairness","topic:quantum","patent:2026-004441","topic:invention","topic:agents","work:weight-editing","topic:language"],"transitions":["For my own research, I wan know if knowing the rules of a program fit help predict which instruction go run next.","Before the step wey we predict fit run, another check must confirm say the rules allow am.","If model no sure, e fit pass the decision give person make e review am.","I dey compare how often cases from different groups dey go for review.","For quantum research, another question come up: wetin exactly we dey measure?","Turkish application 2026/004441 propose to join quantum entanglement and conformal prediction to group customers even when noise dey for the data.","Na one of my 30 applications for Türkiye: 28 patent applications and two utility model applications.","For some of these applications, software dey coordinate wetin different systems do.","For this experiment, language models suggest changes to another model weights, and I measure wetin change.","For other projects, I use language models for Turkish tasks, like to sort reviews by wetin people talk."],"labels":{"kinds":{"topic":"Topic","work":"Research work","patent":"Application","project":"Project","affiliation":"Institution","photo":"Photo","section":"Collection","study":"Study","reader":"Page to read","model":"Model","repository":"Code repository","note":"Research note","profile":"My profile","contact":"Reach me"},"relations":{"about":"Research topic","related":"Related entry","contains":"Connection to collection","documents":"Related document","affiliation":"Connection to institution","readableAs":"Page to read","sameProject":"Na di same project","family":"Na di same patent family","contact":"Public profile link"},"inverseRelations":{"about":"Research topic","related":"Related entry","contains":"Collection wey get dis entry","documents":"Related document","affiliation":"Connection to institution","readableAs":"Page to read","sameProject":"Na di same project","family":"Na di same patent family","contact":"Public profile link"},"sections":{"portfolio":"Applications wey dem file for Türkiye","lab":"Models and code","works":"Research and publications","notebook":"Four questions from my notebook","album":"My foto album","contact":"How to reach me and see my profiles","readers":"Index, graph and profile","selected":"Some of my work","research":"Research areas"}},"nodes":[{"id":"profile:emre","kind":"profile","title":"Davut Emre Taşar","summary":"I be engineer and applied scientist for BBVA, for the AI Innovation team wey dey under AI Transformation. I dey do my PhD for University of Navarra on how AI fit treat people fairly.","details":["I come from İzmir, for the Aegean coast of Turkey. I be civil engineer before. Then arrow hit my knee, and I exchange my hard hat for lab coat.","I be engineer and applied scientist for the AI Innovation team for BBVA. I dey do my PhD for University of Navarra on how AI fit treat people fairly. How people dey lead their teams interest me just like abstract maths, quantum physics and philosophy. I like am well well when I find where two ideas wey look like say dem no get anything to do with each other actually meet.","Na Madrid I dey live now. I dey explore the city, learn Spanish and get to know the different cultures of Spain and Latin America. For house I dey paint, play chess and make up small stories for my daughter."],"path":"/pcm/profile/","links":[],"image":"/assets/emre-espresso.jpg","meta":"Madrid","fields":[]},{"id":"section:research","kind":"section","title":"Research areas","summary":"When model no sure · Fair treatment · AI agents · Quantum research · Inventions · Language","details":["How model fit know the limit of wetin e sabi?","Na who dey carry the cost when model no sure?","How you fit check wetin an agent really do?","Wetin a measurement fit tell us?","How small rescue robot need to be?","How machine take understand wetin we talk?"],"path":"/pcm/#explore","links":[],"fields":[]},{"id":"section:selected","kind":"section","title":"Some of my work","summary":"If computer know the rules wey one program must follow, e fit predict better which instructions go run next?","details":["How much a few measurements fit tell us?","Wetin fit reach person through space wey wide like one finger?","One model fit change another model weights?"],"path":"/pcm/#selected-exhibits","links":[],"fields":[]},{"id":"section:portfolio","kind":"section","title":"Applications wey dem file for Türkiye","summary":"My name dey as inventor for 30 applications wey Türkiye Garanti Bankası A.Ş. file for Türkiye. Na 28 patent applications and two utility model applications.","details":["Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date we check the register · 31 Ọgọ 2026","Some international publications dey refer to di same applications wey dem file for Türkiye. Di total na how many applications dem file for Türkiye.","For the current legal status of any application, check the original register."],"path":"/pcm/#patents","links":[{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"fields":[]},{"id":"section:lab","kind":"section","title":"Models and code","summary":"Model · 8   /   Code repository · 8","details":["Turkish Sentiment Analysis · TSAM — I train dis BERT model to pick di tone wey Turkish review get. E dey give separate score for positive, neutral and negative tone.","Fairness Metrics — Give the library predictions, actual outcomes, input features and group labels. E produce a pandas table wey show how error rates and recall differ from group to group.","Agent Chronicle — The tool arrange coding-agent decisions, file changes and checks as dem happen. You fit trace a progress claim back to the activity wey support am."],"path":"/pcm/#lab","links":[],"fields":[]},{"id":"section:works","kind":"section","title":"Research and publications","summary":"For one place, you fit search my research, patent and utility model applications wey dem file for Türkiye, AI models and code repos.","details":["When coverage and human review no balance — Whose case dem go check again?","How sure quantum predictions fit be — How much a few measurements fit tell us?","How language models fit edit neural networks — One model fit change another model weights?"],"path":"/pcm/#work","links":[],"fields":[]},{"id":"section:notebook","kind":"section","title":"Four questions from my notebook","summary":"Ontologies and data structures · Meaning-Native Computing · Category theory · Quantum measurement","details":["Wetin go change for graph if one train come late?","If computer know the rules wey one program must follow, e fit predict better which instructions go run next?","Wetin go remain when I join two transformations?","Wetin go happen if I ask the same qubit another question?"],"path":"/pcm/#idea-notebook-title","links":[],"fields":[]},{"id":"section:album","kind":"section","title":"My foto album","summary":"Emre stand beside one Elektra espresso machine · Emre dey explain im PhD research for Navarra · Emre hold di BBVA We Think Big award","details":["Na dis espresso machine I like pass.","One photo from wen I present my PhD research for di fifth DATAI scientific meeting at University of Navarra.","For 2024, BBVA give me the We Think Big award for my work on patents and wetin I contribute to academic research."],"path":"/pcm/#espresso","links":[],"fields":[]},{"id":"section:contact","kind":"section","title":"How to reach me and see my profiles","summary":"Send me message for LinkedIn","details":["GitHub · Hugging Face · Scholar · LinkedIn · X · ORCID · University of Navarra"],"path":"/pcm/#profiles","links":[{"label":"GitHub","url":"https://github.com/detasar"},{"label":"Hugging Face","url":"https://huggingface.co/emre"},{"label":"Scholar","url":"https://scholar.google.com/citations?user=IZZM_JAAAAAJ"},{"label":"LinkedIn","url":"https://www.linkedin.com/in/detasar/"},{"label":"X","url":"https://x.com/mehanixs"},{"label":"ORCID","url":"https://orcid.org/0000-0002-7788-0478"},{"label":"University of Navarra","url":"https://www.unav.edu/web/instituto-de-ciencia-de-los-datos-e-inteligencia-artificial/equipo#:~:text=Enhancing%20Fairness%20in%20AI%20Systems"}],"fields":[]},{"id":"section:readers","kind":"section","title":"Index, graph and profile","summary":"Index for wetin to read · Graph wey link ideas · My profile","details":["For one place, you fit search my research, patent and utility model applications wey dem file for Türkiye, AI models and code repos.","Choose one research area to see how di work dem connect and go to di original sources.","I be engineer and applied scientist for BBVA, for the AI Innovation team wey dey under AI Transformation. I dey do my PhD for University of Navarra on how AI fit treat people fairly."],"path":"/pcm/guide/","links":[],"fields":[]},{"id":"topic:uncertainty","kind":"topic","title":"When model no sure","summary":"How model fit know the limit of wetin e sabi?","details":["I use conformal prediction to measure how often the right answer fall inside the set wey model give, and to decide when person need step in."],"path":"/pcm/graph/#topic-uncertainty","links":[],"fields":["confidence"]},{"id":"topic:fairness","kind":"topic","title":"Fair treatment","summary":"Na who dey carry the cost when model no sure?","details":["Two groups fit get similar results overall, but one group fit wait for human review more often. I examine where this difference dey come from."],"path":"/pcm/graph/#topic-fairness","links":[],"fields":["confidence"]},{"id":"topic:agents","kind":"topic","title":"AI agents","summary":"How you fit check wetin an agent really do?","details":["I build tools wey link an agent actions to records wey person fit read and check."],"path":"/pcm/graph/#topic-agents","links":[],"fields":["agents"]},{"id":"topic:quantum","kind":"topic","title":"Quantum research","summary":"Wetin a measurement fit tell us?","details":["I study how to calibrate predictions from quantum measurements, spot unusual patterns and check whether the findings still hold when conditions change."],"path":"/pcm/graph/#topic-quantum","links":[],"fields":["quantum"]},{"id":"topic:invention","kind":"topic","title":"Inventions","summary":"How small rescue robot need to be?","details":["My patent work cover rescue robots, tools wey follow spoken instructions, personal knowledge graphs and quantum methods."],"path":"/pcm/graph/#topic-invention","links":[],"fields":["invention"]},{"id":"topic:language","kind":"topic","title":"Language","summary":"How machine take understand wetin we talk?","details":["I work on tools wey turn Turkish speech to writing, adapt language models and contribute to research across different languages."],"path":"/pcm/graph/#topic-language","links":[],"fields":["language"]},{"id":"affiliation:bbva","kind":"affiliation","title":"BBVA","summary":"Engineer and scientist for applied research","details":["BBVA · AI Transformation · AI Innovation","I be engineer and applied scientist for BBVA, for the AI Innovation team wey dey under AI Transformation. I dey do my PhD for University of Navarra on how AI fit treat people fairly."],"path":"/pcm/profile/","links":[{"label":"LinkedIn","url":"https://www.linkedin.com/in/detasar/"}],"fields":[]},{"id":"affiliation:navarra","kind":"affiliation","title":"University of Navarra","summary":"PhD researcher wey dey study how AI fit treat people fairly","details":["University of Navarra"],"path":"/pcm/profile/","links":[{"label":"University of Navarra","url":"https://www.unav.edu/web/instituto-de-ciencia-de-los-datos-e-inteligencia-artificial/equipo#:~:text=Enhancing%20Fairness%20in%20AI%20Systems"}],"fields":[]},{"id":"photo:espresso","kind":"photo","title":"Emre stand beside one Elektra espresso machine","summary":"Na dis espresso machine I like pass.","details":["Emre stand beside one Elektra espresso machine"],"path":"/pcm/#espresso","links":[],"image":"/assets/emre-espresso.jpg","fields":[]},{"id":"photo:scholar","kind":"photo","title":"Emre dey explain im PhD research for Navarra","summary":"One photo from wen I present my PhD research for di fifth DATAI scientific meeting at University of Navarra.","details":["Emre dey explain im PhD research for Navarra"],"path":"/pcm/#scholar","links":[{"label":"University of Navarra","url":"https://www.unav.edu/documents/d/instituto-de-ciencia-de-los-datos-e-inteligencia-artificial/programa_jornadas_cientificas_datai_mayo_2026"}],"image":"/assets/emre-scholar.webp","fields":[]},{"id":"photo:we-think-big","kind":"photo","title":"We Think Big","summary":"For 2024, BBVA give me the We Think Big award for my work on patents and wetin I contribute to academic research.","details":["BBVA · 2024"],"path":"/pcm/#we-think-big","links":[],"image":"/assets/emre-we-think-big.jpg","fields":[],"year":"2024"},{"id":"note:ontologies-and-data-structures","kind":"note","title":"Ontologies and data structures","summary":"Wetin go change for graph if one train come late?","details":["Station na place. Train departure na event. If I use different node type for each one and keep where each time come from, I fit trace all the connections wey one delay go affect?"],"path":"/pcm/#idea-notebook-title","links":[{"label":"RDF 1.1 · W3C","url":"https://www.w3.org/TR/rdf11-concepts/"}],"fields":["meaning"]},{"id":"note:category-theory","kind":"note","title":"Category theory","summary":"Wetin go remain when I join two transformations?","details":["One process turn timetable to graph. Another one find route for the graph. When I join the two, how I fit keep track of which time belong to which station?"],"path":"/pcm/#idea-notebook-title","links":[{"label":"Seven Sketches in Compositionality","url":"https://arxiv.org/abs/1803.05316"}],"fields":["meaning"]},{"id":"note:quantum-measurement","kind":"note","title":"Quantum measurement","summary":"Wetin go happen if I ask the same qubit another question?","details":["I prepare the “+” state. If I measure for X basis, na + I go always get. For Z basis, 0 and 1 get equal chance. Wetin dey fascinate me be say the answer dey change with how I measure am, even when I prepare am the same way."],"path":"/pcm/#idea-notebook-title","links":[{"label":"Quantum Information · IBM","url":"https://quantum.cloud.ibm.com/learning/en/courses/basics-of-quantum-information/single-systems/quantum-information"}],"fields":["quantum"]},{"id":"project:meaning-native-computing","kind":"project","title":"Meaning-Native Computing","summary":"If computer know the rules wey one program must follow, e fit predict better which instructions go run next?","details":["Meaning-Native Computing na my own independent research project. I wan compare two ways to predict wetin go happen, with the same program and about the same computing power. I go give one of dem the program rules too, write am out clear. E go help am see the next steps better? Before any change wey e predict fit take effect, another check must confirm say the change follow the rules."],"path":"/pcm/#meaning-native-computing","links":[],"meta":"Davut Emre Taşar","fields":["meaning","confidence"]},{"id":"work:coverage-deferral","kind":"work","title":"When coverage and human review no balance","summary":"I compare one threshold for everybody with a different threshold for each group. For the Adult income dataset, the coverage gap drop from 5.0 to 1.2 percentage points, but the gap for cases wey go human review rise from 5.1 to 12.9 points. Na simulation with 100 random seeds and 90% target coverage.","details":["Whose case dem go check again?"],"path":"/pcm/work/coverage-deferral/","links":[{"label":"Original source","url":"https://www.preprints.org/manuscript/202512.2631"},{"label":"DOI","url":"https://doi.org/10.20944/preprints202512.2631.v1"}],"meta":"2025 · Paper before peer review · Na me alone write am","identifier":"10.20944/preprints202512.2631.v1","fields":["confidence","learning"],"year":"2025"},{"id":"work:agent-chronicle","kind":"work","title":"Agent Chronicle","summary":"Agent Chronicle arrange the decisions, file changes and checks from a Codex or Claude session in the order wey dem happen. You fit open the record behind a progress report see wetin the agent actually do.","details":["The coding agent say e don finish. Wetin e change?"],"path":"/pcm/work/agent-chronicle/","links":[{"label":"Original source","url":"https://github.com/detasar/agent-chronicle-community"},{"label":"github.com","url":"https://github.com/detasar/agent-chronicle-community/tree/main/docs"}],"meta":"2026 · Code repository · I dey maintain the project","identifier":"detasar/agent-chronicle-community","fields":["agents"],"year":"2026"},{"id":"work:quantum-conformal","kind":"work","title":"How sure quantum predictions fit be","summary":"I use earlier examples to calibrate sets of possible probabilities for several quantum outcomes at once. For the 2025 paper, I check the size of those sets and how often dem cover the answer, using simulation and measurements from different bases.","details":["How much a few measurements fit tell us?"],"path":"/pcm/work/quantum-conformal/","links":[{"label":"Original source","url":"https://journals.gen.tr/index.php/jqtair/article/view/2702"},{"label":"github.com","url":"https://github.com/detasar/QECMMOU"},{"label":"DOI","url":"https://doi.org/10.70447/ktve.2702"}],"meta":"2025 · Journal article · Na me alone write am","identifier":"10.70447/ktve.2702","fields":["quantum","confidence"],"year":"2025"},{"id":"work:tara","kind":"work","title":"TARA and quantum measurements","summary":"Ceren Öcal Taşar and I compare groups of quantum readings with a reference, then test another method wey gather evidence as new readings come in. The preprint report experiments for IBM Torino and IonQ Forte Enterprise and show why the choice of calibration data matter.","details":["When a stream of measurements begin look unusual?"],"path":"/pcm/work/tara/","links":[{"label":"Original source","url":"https://arxiv.org/abs/2512.04016"},{"label":"PDF","url":"https://arxiv.org/pdf/2512.04016"}],"meta":"2025 · Paper before peer review · First author","identifier":"arXiv:2512.04016","fields":["quantum","confidence"],"year":"2025"},{"id":"work:chat-assistant","kind":"work","title":"Assistant wey fit answer and act","summary":"For this design, the assistant fit search online to answer a question or carry out an operation when the user give command, all inside the same chat. Di international application come out on 3 April 2025.","details":["When chat suppose turn to action?"],"path":"/pcm/work/chat-assistant/","links":[{"label":"Original source","url":"https://patents.google.com/patent/WO2025071524A1/en"},{"label":"patents.google.com","url":"https://patents.google.com/patent/TR2023011870A2/tr"}],"meta":"2025 · Patent application (PCT) · One of the inventors","identifier":"WO2025071524A1","fields":["invention","agents","language"],"year":"2025"},{"id":"work:micro-robot-rescue","kind":"work","title":"Small robot for rescue work","summary":"Our patent application describe small robot with joints wey fit move inside rubble. Camera and sensors fit help find where person dey, while a line wey follow the robot fit carry communication and support. The international application come out on 3 April 2025.","details":["Wetin fit reach person through space wey wide like one finger?"],"path":"/pcm/work/micro-robot-rescue/","links":[{"label":"Original source","url":"https://patents.google.com/patent/WO2025071525A1/en"},{"label":"patents.google.com","url":"https://patents.google.com/patent/TR2023011901A2/tr"}],"meta":"2025 · Patent application (PCT) · One of the inventors","identifier":"WO2025071525A1","image":"/assets/rescue-patent-figure.webp","fields":["invention","agents"],"year":"2025"},{"id":"work:ai-pos","kind":"work","title":"Talk to a POS machine","summary":"The application describe how merchant fit operate POS from a distance with voice or written instructions. E also cover QR-coded output and checks for possible fraud. Di international application come out on 24 October 2024.","details":["Shop owner fit control payment terminal with voice?"],"path":"/pcm/work/ai-pos/","links":[{"label":"Original source","url":"https://patents.google.com/patent/WO2024220062A1/en"},{"label":"patents.google.com","url":"https://patents.google.com/patent/TR2023004244A2/tr"}],"meta":"2024 · Patent application (PCT) · One of the inventors","identifier":"WO2024220062A1","fields":["invention","language"],"year":"2024"},{"id":"work:virtual-input","kind":"work","title":"Keyboard and mouse for virtual space","summary":"For this design, camera dey follow hand movements and the system dey read dem as keyboard or mouse commands for virtual or augmented reality. The Turkish filing TR 2023/011601 and the international publication WO2025063923A1 describe the same invention.","details":["If the screen dey virtual, where the keyboard dey?"],"path":"/pcm/work/virtual-input/","links":[{"label":"Original source","url":"https://patents.google.com/patent/WO2025063923A1/en"},{"label":"patents.google.com","url":"https://patents.google.com/patent/TR2023011601A2/tr"}],"meta":"2025 · Patent application (PCT) · One of the inventors","identifier":"WO2025063923A1","fields":["invention"],"year":"2025"},{"id":"work:personalized-suggestions","kind":"work","title":"Advice wey suit each worker","summary":"The proposed system use information about the worker mood, health and day to suggest wetin fit help that person at work. The Turkish filing na TR 2023/011830, and the international application name Türkiye Garanti Bankası as applicant.","details":["How workplace assistant fit choose advice for one person?"],"path":"/pcm/work/personalized-suggestions/","links":[{"label":"Original source","url":"https://patents.google.com/patent/WO2025063924A1/en"},{"label":"patents.google.com","url":"https://patents.google.com/patent/TR2023011830A2/tr"}],"meta":"2025 · Patent application (PCT) · One of the inventors","identifier":"WO2025063924A1","fields":["invention"],"year":"2025"},{"id":"work:adversarial-quantum","kind":"work","title":"Put quantum test results to the test","summary":"I test how the data wey researchers use for calibration and evaluation fit change the score for quantum correlations. The December 2025 preprint explain the simulation, the comparison with IBM Quantum measurements and the assumptions behind the test.","details":["Good score go still hold if conditions change?"],"path":"/pcm/work/adversarial-quantum/","links":[{"label":"Original source","url":"https://arxiv.org/abs/2512.04391"},{"label":"PDF","url":"https://arxiv.org/pdf/2512.04391"}],"meta":"2025 · Paper before peer review · Na me alone write am","identifier":"arXiv:2512.04391","fields":["quantum","confidence"],"year":"2025"},{"id":"work:turkish-asr","kind":"work","title":"From Turkish speech to writing","summary":"Kutan Koruyan, Cihan Çılgın and I adapt Wav2Vec 2.0, wey dem first train on speech in 53 languages, with recordings and transcripts from Mozilla Common Voice Turkish. The test give word error rate of 23%, counting words wey the model replace, miss or add.","details":["Wetin model wey don hear many languages fit use when e learn Turkish?"],"path":"/pcm/work/turkish-asr/","links":[{"label":"Original source","url":"https://dergipark.org.tr/en/pub/acin/article/1338604"},{"label":"DOI","url":"https://doi.org/10.26650/acin.1338604"}],"meta":"2024 · Journal article · First author","identifier":"10.26650/acin.1338604","fields":["language"],"year":"2024"},{"id":"work:qwen-grpo","kind":"work","title":"Small Qwen model for maths","summary":"I adapt Qwen2.5-0.5B-Instruct with GSM8K word problems. During training, the model get separate scores for the right number and for following the format. The model card get the training details and code wey another researcher fit try.","details":["Small model fit learn how to arrange a maths solution?"],"path":"/pcm/work/qwen-grpo/","links":[{"label":"Original source","url":"https://huggingface.co/emre/Qwen-0.5B-GRPO"},{"label":"huggingface.co","url":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct"}],"meta":"2025 · Model · Developer","identifier":"emre/Qwen-0.5B-GRPO","fields":["language"],"year":"2025"},{"id":"work:turkish-reasoning-benchmark","kind":"work","title":"TARA tests for reasoning in Turkish","summary":"Ceren Öcal Taşar and I prepare tasks for ten areas, including logic, planning, Python and SQL. The first version get 100 examples wey one model generate. That sample limit wetin the scores fit tell us about everyday Turkish.","details":["How we fit test whether model dey reason well in Turkish?"],"path":"/pcm/work/turkish-reasoning-benchmark/","links":[{"label":"Original source","url":"https://huggingface.co/datasets/emre/TARA_Turkish_LLM_Benchmark"},{"label":"DOI","url":"https://doi.org/10.57967/hf/5193"}],"meta":"2025 · Dataset · I join prepare the dataset","identifier":"10.57967/hf/5193","fields":["language"],"year":"2025"},{"id":"work:multilingual-chatbots","kind":"work","title":"One language model for many chatbots","summary":"We test one shared BERT classifier on 13 tasks with 333 classes in Turkish, English and German, including banking questions. For the comparison with five separate models, memory use drop from 10 GB to 2 GB, with a small drop for accuracy.","details":["Thirteen chatbot tasks need thirteen separate models?"],"path":"/pcm/work/multilingual-chatbots/","links":[{"label":"Original source","url":"https://dergipark.org.tr/en/pub/jaida/article/1060221"},{"label":"dergipark.org.tr","url":"https://dergipark.org.tr/tr/download/article-file/2201572"}],"meta":"2021 · Journal article · First author","identifier":"IZ:JA77UY82ER","fields":["language"],"year":"2021"},{"id":"work:ad-text-classification","kind":"work","title":"When advert get wrong label","summary":"We use a zero-shot model to check whether advert text match the industry label, clean the data and train BERT again. The original data get about 101,000 adverts across 44 industries. The paper report say the classifier perform better after the cleaning.","details":["Wetin if na the label on the advert dey wrong?"],"path":"/pcm/work/ad-text-classification/","links":[{"label":"Original source","url":"https://dergipark.org.tr/tr/pub/tbbmd/article/1004781"},{"label":"DOI","url":"https://doi.org/10.54525/tbbmd.1004781"}],"meta":"2021 · Journal article · Co-author","identifier":"10.54525/tbbmd.1004781","fields":["language"],"year":"2021"},{"id":"work:weight-editing","kind":"work","title":"How language models fit edit neural networks","summary":"I test changes to the weights of one classifier wey get permanent damage, with the UCI Adult dataset. The change wey Sol suggest improve balanced accuracy, but overall accuracy drop and the probability estimates come less reliable. For the intact SmolLM2 language model, every selection for ARC-Easy and PIQA keep the original weights.","details":["One model fit change another model weights?","Classifier wey get damage · UCI Adult · Sol","Accuracy wey balance the classes · Starting point 78.59% · Wetin dem select 79.02%","Overall accuracy · Starting point 82.86% · Wetin dem select 82.63%","Language model wey no get damage · SmolLM2-1.7B · Na the original weights dem select"],"path":"/pcm/work/weight-editing/","links":[{"label":"Original source","url":"https://github.com/detasar/llm-weight-editing-study"},{"label":"Research report","url":"https://github.com/detasar/llm-weight-editing-study/blob/main/publication/2026-11-04/RESEARCH_REPORT.pdf"},{"label":"Presentation wey you fit explore","url":"https://detasar.github.io/llm-weight-editing-study/publication/2026-11-04/START_PRESENTATION.html"},{"label":"Measurements","url":"https://github.com/detasar/llm-weight-editing-study/blob/main/data/manifest.json"}],"meta":"2026 · Code repository · Na me alone write am","identifier":"detasar/llm-weight-editing-study","fields":["learning","agents","language"],"year":"2026"},{"id":"work:bloom","kind":"work","title":"BLOOM","summary":"I be one of the many people wey co-write the BigScience project paper on BLOOM. The paper list all the authors and describe the model design, data, training and release.","details":["How researchers build one multilingual model for everybody to study?"],"path":"/pcm/work/bloom/","links":[{"label":"Original source","url":"https://arxiv.org/abs/2211.05100"}],"meta":"2022 · Paper before peer review · Co-author","identifier":"arXiv:2211.05100","fields":["language"],"year":"2022"},{"id":"patent:2026-007909","kind":"patent","title":"Remove noise around the speaker voice","summary":"The system separate the speaker voice from background noise and turn the speech to writing. E fit adjust the wording to suit the person or the setting, then produce speech wey still sound like the speaker.","details":["Date dem file am · 18 Mee 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Jul 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-007909/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/007909 · Patent application","fields":["invention","language"],"year":"2026"},{"id":"patent:2026-007907","kind":"patent","title":"AI wey use logic draw conclusions","summary":"The proposal turn transaction histories, user records and network connections into a model of wetin the system know. E fit use rules of logic to draw conclusions from those records for finance, health or logistics.","details":["Date dem file am · 18 Mee 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Jun 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-007907/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/007907 · Patent application","fields":["meaning","invention"],"year":"2026"},{"id":"patent:2026-006294","kind":"patent","title":"Waiting experience wey suit each person","summary":"The proposed system assess how person dey feel while dem dey wait and use that assessment to choose content for the person.","details":["Date dem file am · 24 Épr 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Mee 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-006294/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/006294 · Patent application","fields":["invention"],"year":"2026"},{"id":"patent:2026-006289","kind":"patent","title":"Personal knowledge graph for retirement and everyday life","summary":"The system arrange concepts about one person and map how dem connect. As things change for the person life, the map fit change too, to support retirement planning and offer help early.","details":["Date dem file am · 24 Épr 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Jun 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-006289/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/006289 · Patent application","fields":["meaning","invention"],"year":"2026"},{"id":"patent:2026-004444","kind":"patent","title":"Detect activity for a place while person privacy dey protected","summary":"The design cover places where people no fit use camera or where camera no appropriate. E fit detect whether anybody dey there or dey active, so energy use fit adjust.","details":["Date dem file am · 26 Mach 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Mee 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-004444/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/004444 · Patent application","fields":["invention"],"year":"2026"},{"id":"patent:2026-004441","kind":"patent","title":"Quantum methods to group financial customers as things change","summary":"The proposal use quantum entanglement to represent complex patterns and quantum clustering to form customer groups even when the data get noise. Conformal prediction add a statistical check.","details":["Date dem file am · 26 Mach 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Épr 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-004441/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/004441 · Patent application","fields":["invention","quantum","confidence"],"year":"2026"},{"id":"patent:2026-002909","kind":"patent","title":"Measure how sure a prediction be","summary":"The system aim to put number on how much confidence person fit get for one AI prediction. Examples include whether borrower go default, transaction go bring profit or loss, or operation go finish late.","details":["Date dem file am · 26 Fẹ́b 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 23 Mach 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-002909/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/002909 · Patent application","fields":["invention"],"year":"2026"},{"id":"patent:2026-001992","kind":"patent","title":"Identify bank customers and measure waiting time","summary":"The design use computer vision and AI to identify customers for branch, measure how long visits last and estimate waiting time. E fit also note when customers leave and adjust the queue.","details":["Date dem file am · 10 Fẹ́b 2026","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 23 Mach 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2026-001992/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2026/001992 · Patent application","fields":["invention"],"year":"2026"},{"id":"patent:2025-019989","kind":"patent","title":"Banking activities as games","summary":"The system study a customer banking activity to generate financial content and game scenarios wey fit that person. The banking app fit collect wetin users think about the scenarios.","details":["Date dem file am · 12 Dis 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Jén 2026","TR2025019989A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-019989/","links":[{"label":"TR2025019989A2","url":"https://patents.google.com/patent/TR2025019989A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/019989 · Patent application","fields":["invention"],"year":"2025"},{"id":"patent:2025-011133","kind":"patent","title":"Add personal context to recorded pictures and sound","summary":"The application describe how to personalise memories wey person record as picture or sound on their device. Federated learning na part of the proposed design.","details":["Date dem file am · 8 Ọgọ 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Sẹp 2025","TR2025011133A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-011133/","links":[{"label":"TR2025011133A2","url":"https://patents.google.com/patent/TR2025011133A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/011133 · Patent application","fields":["learning","invention"],"year":"2025"},{"id":"patent:2025-008786","kind":"patent","title":"A graph wey generate different versions of media","summary":"The system pick features from sound, video or pictures, then build a graph of possible variations. Different branches fit represent another past, a possible future or a parallel version of the original content.","details":["Date dem file am · 30 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Ọgọ 2025","TR2025008786A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-008786/","links":[{"label":"TR2025008786A2","url":"https://patents.google.com/patent/TR2025008786A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/008786 · Patent application","fields":["meaning","invention"],"year":"2025"},{"id":"patent:2025-008273","kind":"patent","title":"Private booth for personal transactions","summary":"The modular booth give person private space to handle sensitive transactions with different service providers.","details":["Date dem file am · 20 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Sẹp 2025","TR2025008273A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-008273/","links":[{"label":"TR2025008273A2","url":"https://patents.google.com/patent/TR2025008273A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/008273 · Patent application","fields":["invention"],"year":"2025"},{"id":"patent:2025-008055","kind":"patent","title":"System for safety when vehicle crash","summary":"Sensors and AI fit detect a collision as e dey happen and assess am. The proposed system fit notify the relevant services and suggest transport or where to stay for the people involved.","details":["Date dem file am · 18 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Ọgọ 2025","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-008055/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/008055 · Patent application","fields":["invention"],"year":"2025"},{"id":"patent:2025-008032","kind":"patent","title":"People and AI wey make decision as one group","summary":"The proposal bring people and AI agents together to reach a group decision. E get different levels of checks to see how reliable the process be as the system dey adapt over time.","details":["Date dem file am · 17 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Jul 2025","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-008032/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/008032 · Patent application","fields":["invention"],"year":"2025"},{"id":"patent:2025-008028","kind":"patent","title":"Make different devices work together","summary":"The proposed system use AI to coordinate devices and apps. How the person experience the whole system fit change as dem continue to use am.","details":["Date dem file am · 17 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Jul 2025","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-008028/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/008028 · Patent application","fields":["invention"],"year":"2025"},{"id":"patent:2025-007997","kind":"patent","title":"Estimate property value and plan ahead","summary":"The proposal combine information from different sources to value property. E use a changing map of concepts, network analysis and generative AI wey fit explain its results to link the valuation to planning.","details":["Date dem file am · 17 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Jul 2025","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-007997/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/007997 · Patent application","fields":["invention"],"year":"2025"},{"id":"patent:2025-007995","kind":"patent","title":"Tools and data format for building AI assistants","summary":"The design give developers an agent architecture and data format to build assistants wey fit move between platforms. As the agents change over time, dem still fit give each person a personalised experience.","details":["Date dem file am · 17 Jun 2025","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Ọgọ 2025","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2025-007995/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2025/007995 · Patent application","fields":["invention","agents"],"year":"2025"},{"id":"patent:2024-003815","kind":"patent","title":"Ways for customers to discuss financial matters","summary":"The proposal link mobile banking, augmented reality and virtual branches so customers fit discuss investment or other financial topics with one another and interact with AI models.","details":["Date dem file am · 27 Mach 2024","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Épr 2024","TR2024003815A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2024-003815/","links":[{"label":"TR2024003815A2","url":"https://patents.google.com/patent/TR2024003815A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2024/003815 · Patent application","fields":["invention"],"year":"2024"},{"id":"patent:2024-003813","kind":"patent","title":"Investment channels wey experts fit run","summary":"The application describe channels wey experts or other public figures fit curate. AI avatars based on particular profiles fit give users financial guidance inside each channel.","details":["Date dem file am · 27 Mach 2024","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Épr 2024","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2024-003813/","links":[{"label":"Original source","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2024/003813 · Patent application","fields":["invention"],"year":"2024"},{"id":"patent:2024-003592","kind":"patent","title":"Do bank transaction together by agreement","summary":"Customer wey want help fit complete a transaction with person wey dem trust. Both people need agree before dem fit take part together.","details":["Date dem file am · 25 Mach 2024","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Mee 2024","TR2024003592A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2024-003592/","links":[{"label":"TR2024003592A2","url":"https://patents.google.com/patent/TR2024003592A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2024/003592 · Patent application","fields":["invention"],"year":"2024"},{"id":"patent:2023-011901","kind":"patent","title":"Small robot for search and rescue","summary":"The proposed robots fit enter tight spaces for collapsed building or mine, gather information and help locate anybody wey trap inside. The design include a line wey fit carry support.","details":["Date dem file am · 25 Sẹp 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Dis 2023","TR2023011901A2","Türkiye don announce the final decision to grant this patent · 23 Fẹ́b 2026","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-011901/","links":[{"label":"TR2023011901A2","url":"https://patents.google.com/patent/TR2023011901A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/011901 · Patent application","image":"/assets/rescue-patent-figure.webp","fields":["invention"],"year":"2023"},{"id":"patent:2023-011870","kind":"patent","title":"Chat assistant wey fit act on command","summary":"The assistant fit search for information online to answer question. Inside the same chat, e fit carry out an operation if the user give command.","details":["Date dem file am · 25 Sẹp 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Dis 2023","TR2023011870A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-011870/","links":[{"label":"TR2023011870A2","url":"https://patents.google.com/patent/TR2023011870A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/011870 · Patent application","fields":["invention","language"],"year":"2023"},{"id":"patent:2023-011830","kind":"patent","title":"Suggestions wey suit each worker","summary":"The proposed assistant use the worker daily mood and health information to choose suggestions wey suit that person workday.","details":["Date dem file am · 22 Sẹp 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Ọgọ 2024","TR2023011830A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-011830/","links":[{"label":"TR2023011830A2","url":"https://patents.google.com/patent/TR2023011830A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/011830 · Patent application","fields":["invention"],"year":"2023"},{"id":"patent:2023-011601","kind":"patent","title":"Use keyboard and mouse for virtual space","summary":"Camera follow the user hand movements. The system turn those movements into keyboard or mouse commands for virtual and augmented reality.","details":["Date dem file am · 18 Sẹp 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Dis 2023","TR2023011601A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-011601/","links":[{"label":"TR2023011601A2","url":"https://patents.google.com/patent/TR2023011601A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/011601 · Patent application","fields":["invention"],"year":"2023"},{"id":"patent:2023-011600","kind":"patent","title":"Warn customer if dem leave something for ATM","summary":"After transaction, the system check whether card, cash or receipt still dey the ATM. The banking app fit alert customer wey don waka comot.","details":["Date dem file am · 18 Sẹp 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Jén 2024","TR2023011600A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-011600/","links":[{"label":"TR2023011600A2","url":"https://patents.google.com/patent/TR2023011600A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/011600 · Utility model application","fields":["invention"],"year":"2023"},{"id":"patent:2023-011599","kind":"patent","title":"Use phone control screen for ATM","summary":"Phone or tablet read a code for the ATM and show its controls through augmented reality. The physical machine still dey collect or give cash and print receipts.","details":["Date dem file am · 18 Sẹp 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 22 Jén 2024","TR2023011599A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-011599/","links":[{"label":"TR2023011599A2","url":"https://patents.google.com/patent/TR2023011599A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/011599 · Patent application","fields":["invention"],"year":"2023"},{"id":"patent:2023-004244","kind":"patent","title":"Control POS terminal with AI","summary":"Merchant fit use voice or written command to control the payment terminal from a distance. The filing also describe QR-code output and checks for possible fraud.","details":["Date dem file am · 17 Épr 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Sẹp 2023","TR2023004244A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-004244/","links":[{"label":"TR2023004244A2","url":"https://patents.google.com/patent/TR2023004244A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/004244 · Patent application","fields":["invention"],"year":"2023"},{"id":"patent:2023-004047","kind":"patent","title":"System for safer trade","summary":"For credit or letter-of-credit transaction, the people involved fit create or join a contract. The system record the stages and supporting documents on blockchain, then use AI to suggest parties wey fit match.","details":["Date dem file am · 12 Épr 2023","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Sẹp 2023","TR2023004047A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2023-004047/","links":[{"label":"TR2023004047A2","url":"https://patents.google.com/patent/TR2023004047A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2023/004047 · Patent application","fields":["invention"],"year":"2023"},{"id":"patent:2022-016679","kind":"patent","title":"Product suggestions wey follow the conversation","summary":"The proposal use text, pictures, sound or movement from chat or virtual space to suggest products. E keep past input and suggestions so the next conversation fit continue from where the last one stop.","details":["Date dem file am · 3 Nọv 2022","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Dis 2022","WO2024096828A1","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2022-016679/","links":[{"label":"WO2024096828A1","url":"https://patents.google.com/patent/WO2024096828A1/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2022/016679 · Utility model application","fields":["invention"],"year":"2022"},{"id":"patent:2022-016395","kind":"patent","title":"Manage group voting","summary":"The system bring several AI methods into one group decision process. The application focus on how the people involved fit communicate as the voting dey go on.","details":["Date dem file am · 31 Ọkt 2022","Who file am · TÜRKİYE GARANTİ BANKASI ANONİM ŞİRKETİ","Date e come out · 21 Dis 2022","TR2022016395A2","For the current legal status of any application, check the original register."],"path":"/pcm/patents/2022-016395/","links":[{"label":"TR2022016395A2","url":"https://patents.google.com/patent/TR2022016395A2/en"},{"label":"Di official TÜRKPATENT register","url":"https://www.turkpatent.gov.tr/arastirma-yap?form=patent"}],"meta":"TR 2022/016395 · Patent application","fields":["invention"],"year":"2022"},{"id":"model:turkish-sentiment","kind":"model","title":"Turkish Sentiment Analysis · TSAM","summary":"I train dis BERT model to pick di tone wey Turkish review get. E dey give separate score for positive, neutral and negative tone.","details":["Model wey dem train with AutoTrain to sort text into groups","One independent study compare four models with four sets of Turkish data. For di test wey get two classes, di researchers remove neutral labels. Dis model get F1 score of 0.97 for Humir and 0.54 for Twt.","Total downloads for di Hub · 12,053 · 18 Nọv 2026"],"path":"/pcm/lab/turkish-sentiment/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/turkish-sentiment-analysis"},{"label":"A cross-validation study of Turkish sentiment analysis datasets and tools","url":"https://doi.org/10.1007/s10579-025-09869-6"}],"meta":"Model · Model wey dem train with AutoTrain to sort text into groups","fields":["language"]},{"id":"model:whisper-tr","kind":"model","title":"Whisper Medium TR","summary":"Give the model a recording in Turkish and e go write out the speech. I adapt Whisper Medium with Turkish recordings from Mozilla Common Voice 11.0.","details":["Adapt model wey dey recognise speech","OpenAI Whisper Medium"],"path":"/pcm/lab/whisper-tr/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/whisper-medium-turkish-2"},{"label":"OpenAI Whisper Medium","url":"https://huggingface.co/openai/whisper-medium"}],"meta":"Model · Adapt model wey dey recognise speech","fields":["language"]},{"id":"model:gemma-wiki-tr","kind":"model","title":"Gemma 2 · Turkish Wikipedia","summary":"This Gemma 2 9B adapter learn further from Turkish Wikipedia and fit continue a Turkish passage. The model card allow research and academic use and limit commercial use to BBVA Group.","details":["Person wey build di LoRA adapter","Google Gemma 2 9B"],"path":"/pcm/lab/gemma-wiki-tr/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/gemma-2-9b-Turkish-Lora-Continue-Pre-Trained"},{"label":"Google Gemma 2 9B","url":"https://huggingface.co/google/gemma-2-9b"}],"meta":"Model · Person wey build di LoRA adapter","fields":["language"]},{"id":"model:java-method-vectors","kind":"model","title":"Java Methods · Doc2Vec","summary":"This model turn a Java method into 200 numbers wey represent the code. Developers fit use dem to find code wey resemble one another or to group methods.","details":["Person wey build di model wey turn code to vectors","Gensim Doc2Vec"],"path":"/pcm/lab/java-method-vectors/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/java_8m_methods_doc2vec"},{"label":"Gensim Doc2Vec","url":"https://radimrehurek.com/gensim/models/doc2vec.html"}],"meta":"Model · Person wey build di model wey turn code to vectors","fields":["language"]},{"id":"model:gemma-reasoning-tr","kind":"model","title":"Gemma 3 27B · Turkish reasoning","summary":"I fine-tune the Unsloth 4-bit version of Gemma 3 27B Instruct to answer reasoning questions in Turkish. The card include early TARA results for logic, planning and SQL.","details":["Fine-tune model wey dem don quantize","Unsloth 4-bit Gemma 3 27B Instruct"],"path":"/pcm/lab/gemma-reasoning-tr/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/gemma-3-27b-it-tr-reasoning40k-4bit"},{"label":"Unsloth 4-bit Gemma 3 27B Instruct","url":"https://huggingface.co/unsloth/gemma-3-27b-it-unsloth-bnb-4bit"}],"meta":"Model · Fine-tune model wey dem don quantize","fields":["language"]},{"id":"model:abstract-title","kind":"model","title":"arXiv Abstract-to-Title · mT5","summary":"Give this mT5-small adaptation a research abstract and e suggest a title for the paper. E learn from arXiv abstract and title pairs.","details":["Fine-tune model wey turn one sequence of words to another","mT5-small"],"path":"/pcm/lab/abstract-title/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/arxiv27k-t5-abst-title-gen"},{"label":"mT5-small","url":"https://huggingface.co/google/mt5-small"}],"meta":"Model · Fine-tune model wey turn one sequence of words to another","fields":["language"]},{"id":"model:xlsr-tr","kind":"model","title":"Wav2Vec2 XLS-R · Turkish","summary":"This adaptation of Wav2Vec2 XLS-R turn recorded Turkish speech to writing. The model card show how the training go and how often e make word errors.","details":["Adapt model wey dey recognise speech","Meta Wav2Vec2 XLS-R 300M"],"path":"/pcm/lab/xlsr-tr/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/wav2vec2-large-xls-r-300m-tr"},{"label":"Meta Wav2Vec2 XLS-R 300M","url":"https://huggingface.co/facebook/wav2vec2-xls-r-300m"}],"meta":"Model · Adapt model wey dey recognise speech","fields":["language"]},{"id":"model:qwen-grpo","kind":"model","title":"Qwen 0.5B · GRPO maths","summary":"Give this small Qwen model a maths word problem. Its GSM8K training score the numerical answer and the way e arrange the solution separately.","details":["Fine-tune model with rewards as e dey learn","Qwen2.5-0.5B-Instruct"],"path":"/pcm/lab/qwen-grpo/","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre/Qwen-0.5B-GRPO"},{"label":"Qwen2.5-0.5B-Instruct","url":"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct"}],"meta":"Model · Fine-tune model with rewards as e dey learn","fields":["language"]},{"id":"repository:regression-atlas","kind":"repository","title":"Regression Conformal Prediction Research Atlas","summary":"Use the atlas compare prediction intervals on 67 datasets. You fit see how wide each interval be and how often the actual result fall inside am.","details":["Person wey write di study"],"path":"/pcm/lab/regression-atlas/","links":[{"label":"GitHub","url":"https://github.com/detasar/regression-conformal-prediction-research-atlas"}],"meta":"Code repository · Person wey write di study","fields":["learning","confidence"],"year":"2026"},{"id":"repository:bird-sql","kind":"repository","title":"BIRD · Text-to-SQL experiments","summary":"Give the pipeline a question and the database structure. E generate SQL, run the query and check wetin come out.","details":["Person wey dey maintain di research code repository"],"path":"/pcm/lab/bird-sql/","links":[{"label":"GitHub","url":"https://github.com/detasar/bird-text2sql-experiments"}],"meta":"Code repository · Person wey dey maintain di research code repository","fields":["agents","confidence"]},{"id":"repository:webcli","kind":"repository","title":"WebCLI","summary":"Search public technical documents on your own machine from the command line. WebCLI give stable references and fit export the results as JSONL.","details":["Person wey dey maintain di project"],"path":"/pcm/lab/webcli/","links":[{"label":"GitHub","url":"https://github.com/detasar/webcli"}],"meta":"Code repository · Person wey dey maintain di project","fields":["agents","language"]},{"id":"repository:fairness-metrics","kind":"repository","title":"Fairness Metrics","summary":"Give the library predictions, actual outcomes, input features and group labels. E produce a pandas table wey show how error rates and recall differ from group to group.","details":["Person wey dey maintain di software library"],"path":"/pcm/lab/fairness-metrics/","links":[{"label":"GitHub","url":"https://github.com/detasar/fairness_metrics"}],"meta":"Code repository · Person wey dey maintain di software library","fields":["learning","confidence"]},{"id":"repository:quantum-clocks","kind":"repository","title":"Quantum Time Experiment","summary":"The experiments check whether records wey different parts of a quantum system keep fit show the order wey events happen, and when another reference dey necessary.","details":["Person wey dey maintain di research code repository"],"path":"/pcm/lab/quantum-clocks/","links":[{"label":"GitHub","url":"https://github.com/detasar/quantum-time-experiment"}],"meta":"Code repository · Person wey dey maintain di research code repository","fields":["quantum"]},{"id":"repository:paperbanana-test","kind":"repository","title":"PaperBanana field test","summary":"I use the methods sections from three of my papers to test PaperBanana. You fit compare each picture wey e generate with the original and see where e miss the mark.","details":["Person wey write di independent evaluation"],"path":"/pcm/lab/paperbanana-test/","links":[{"label":"GitHub","url":"https://github.com/detasar/paperbanana-field-test"}],"meta":"Code repository · Person wey write di independent evaluation","fields":["agents"]},{"id":"repository:worldcup-nowcast","kind":"repository","title":"World Cup 2026 Nowcast Lab","summary":"This experiment use probabilities for each match to simulate the 2026 World Cup and estimate the chance wey each team get to win the tournament.","details":["Person wey dey maintain di forecasting project"],"path":"/pcm/lab/worldcup-nowcast/","links":[{"label":"GitHub","url":"https://github.com/detasar/worldcup26-nowcast-lab"}],"meta":"Code repository · Person wey dey maintain di forecasting project","fields":["learning","confidence"]},{"id":"repository:agent-chronicle","kind":"repository","title":"Agent Chronicle","summary":"The tool arrange coding-agent decisions, file changes and checks as dem happen. You fit trace a progress claim back to the activity wey support am.","details":["Person wey dey maintain di project"],"path":"/pcm/lab/agent-chronicle/","links":[{"label":"GitHub","url":"https://github.com/detasar/agent-chronicle-community"}],"meta":"Code repository · Person wey dey maintain di project","fields":["agents"]},{"id":"repository:turkish-binary-reviews","kind":"repository","title":"BERT-TR-Finetuned4-Pos-Neg-Reviews","summary":"I train Turkish BERT make e fit tell whether person write positive or negative review. I put di training settings for GitHub.","details":["One earlier model wey I train for reviews","dbmdz/bert-base-turkish-cased"],"path":"/pcm/lab/turkish-sentiment/","links":[{"label":"Code repository","url":"https://github.com/detasar/BERT-TR-Finetuned4-Pos-Neg-Reviews"},{"label":"Original source","url":"https://github.com/detasar/BERT-TR-Finetuned4-Pos-Neg-Reviews/blob/7e6c1d1065063e51872026bce286a0fe1c74ebf8/model_args.json"}],"fields":["language","learning"],"year":"2021"},{"id":"study:coverage-deferral","kind":"study","title":"Table 4 · When coverage and human review no balance","summary":"Whose case dem go check again?","details":["Dem use 100 different random seeds. Di coverage wey dem dey aim for na 90%.","Percentage points","Adult · Gap for coverage (One threshold for everybody 5 / Separate threshold for each group 1.2) · Gap for human review (One threshold for everybody 5.1 / Separate threshold for each group 12.9)","ACS Income · Gap for coverage (One threshold for everybody 0.8 / Separate threshold for each group 0.8) · Gap for human review (One threshold for everybody 3.4 / Separate threshold for each group 5.4)","Bank Marketing · Gap for coverage (One threshold for everybody 2 / Separate threshold for each group 1.1) · Gap for human review (One threshold for everybody 0 / Separate threshold for each group 3)","COMPAS · Gap for coverage (One threshold for everybody 1.8 / Separate threshold for each group 3.3) · Gap for human review (One threshold for everybody 5.7 / Separate threshold for each group 10.8)","German Credit · Gap for coverage (One threshold for everybody 3.5 / Separate threshold for each group 5.7) · Gap for human review (One threshold for everybody 6.1 / Separate threshold for each group 24.7)","Taiwan Credit · Gap for coverage (One threshold for everybody 1.1 / Separate threshold for each group 1.3) · Gap for human review (One threshold for everybody 3.4 / Separate threshold for each group 7.7)"],"path":"/pcm/#study","links":[{"label":"Table 4","url":"https://www.preprints.org/manuscript/202512.2631#:~:text=Table%204.%20Coverage-deferral%20trade-off%20across%20datasets"},{"label":"Original source","url":"https://www.preprints.org/manuscript/202512.2631"}],"fields":["confidence","learning"]},{"id":"study:turkish-sentiment-evaluation","kind":"study","title":"A cross-validation study of Turkish sentiment analysis datasets and tools","summary":"One independent study compare four models with four sets of Turkish data. For di test wey get two classes, di researchers remove neutral labels. Dis model get F1 score of 0.97 for Humir and 0.54 for Twt.","details":["Humir · F1 0.97","Twt · F1 0.54"],"path":"/pcm/lab/turkish-sentiment/","links":[{"label":"Original source","url":"https://doi.org/10.1007/s10579-025-09869-6"}],"fields":["language"]},{"id":"contact:github","kind":"contact","title":"GitHub","summary":"Code repos","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"GitHub","url":"https://github.com/detasar"}],"fields":[]},{"id":"contact:hugging-face","kind":"contact","title":"Hugging Face","summary":"Models","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"Hugging Face","url":"https://huggingface.co/emre"}],"fields":[]},{"id":"contact:scholar","kind":"contact","title":"Google Scholar","summary":"Research and publications","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"Google Scholar","url":"https://scholar.google.com/citations?user=IZZM_JAAAAAJ"}],"fields":[]},{"id":"contact:linkedin","kind":"contact","title":"LinkedIn","summary":"Send me message for LinkedIn","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"LinkedIn","url":"https://www.linkedin.com/in/detasar/"}],"fields":[]},{"id":"contact:x","kind":"contact","title":"X","summary":"@mehanixs","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"X","url":"https://x.com/mehanixs"}],"fields":[]},{"id":"contact:orcid","kind":"contact","title":"ORCID","summary":"ORCID · 0000-0002-7788-0478","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"ORCID","url":"https://orcid.org/0000-0002-7788-0478"}],"fields":[]},{"id":"contact:navarra","kind":"contact","title":"University of Navarra","summary":"PhD researcher wey dey study how AI fit treat people fairly","details":["Davut Emre Taşar"],"path":"/pcm/#profiles","links":[{"label":"University of Navarra","url":"https://www.unav.edu/web/instituto-de-ciencia-de-los-datos-e-inteligencia-artificial/equipo#:~:text=Enhancing%20Fairness%20in%20AI%20Systems"}],"fields":[]},{"id":"reader:guide","kind":"reader","title":"Index for wetin to read","summary":"For one place, you fit search my research, patent and utility model applications wey dem file for Türkiye, AI models and code repos.","details":["Index, graph and profile"],"path":"/pcm/guide/","links":[{"label":"llms.txt","url":"/pcm/llms.txt"}],"fields":[]},{"id":"reader:graph","kind":"reader","title":"Graph wey link ideas","summary":"Choose one research area to see how di work dem connect and go to di original sources.","details":["Index, graph and profile"],"path":"/pcm/graph/","links":[{"label":"ontology.jsonld","url":"/pcm/ontology.jsonld"}],"fields":[]},{"id":"reader:profile","kind":"reader","title":"My profile","summary":"I be engineer and applied scientist for BBVA, for the AI Innovation team wey dey under AI Transformation. I dey do my PhD for University of Navarra on how AI fit treat people fairly.","details":["Index, graph and profile"],"path":"/pcm/profile/","links":[{"label":"profile.json","url":"/pcm/profile.json"}],"fields":[]}],"edges":[{"from":"profile:emre","to":"section:selected","type":"related"},{"from":"profile:emre","to":"section:research","type":"related"},{"from":"profile:emre","to":"section:works","type":"related"},{"from":"profile:emre","to":"section:notebook","type":"related"},{"from":"profile:emre","to":"section:portfolio","type":"related"},{"from":"profile:emre","to":"section:lab","type":"related"},{"from":"profile:emre","to":"section:album","type":"related"},{"from":"profile:emre","to":"section:contact","type":"related"},{"from":"profile:emre","to":"section:readers","type":"related"},{"from":"section:selected","to":"project:meaning-native-computing","type":"contains"},{"from":"section:selected","to":"work:micro-robot-rescue","type":"contains"},{"from":"section:selected","to":"work:quantum-conformal","type":"contains"},{"from":"section:selected","to":"work:weight-editing","type":"contains"},{"from":"section:research","to":"topic:uncertainty","type":"contains"},{"from":"topic:uncertainty","to":"topic:fairness","type":"related"},{"from":"topic:uncertainty","to":"topic:quantum","type":"related"},{"from":"topic:uncertainty","to":"topic:agents","type":"related"},{"from":"section:research","to":"topic:fairness","type":"contains"},{"from":"topic:fairness","to":"topic:agents","type":"related"},{"from":"topic:fairness","to":"topic:invention","type":"related"},{"from":"section:research","to":"topic:agents","type":"contains"},{"from":"topic:agents","to":"topic:invention","type":"related"},{"from":"topic:agents","to":"topic:language","type":"related"},{"from":"section:research","to":"topic:quantum","type":"contains"},{"from":"topic:quantum","to":"topic:fairness","type":"related"},{"from":"section:research","to":"topic:invention","type":"contains"},{"from":"topic:invention","to":"topic:language","type":"related"},{"from":"section:research","to":"topic:language","type":"contains"},{"from":"topic:language","to":"topic:uncertainty","type":"related"},{"from":"profile:emre","to":"affiliation:bbva","type":"affiliation"},{"from":"profile:emre","to":"affiliation:navarra","type":"affiliation"},{"from":"section:album","to":"photo:espresso","type":"contains"},{"from":"section:album","to":"photo:scholar","type":"contains"},{"from":"photo:scholar","to":"affiliation:navarra","type":"related"},{"from":"section:album","to":"photo:we-think-big","type":"contains"},{"from":"photo:we-think-big","to":"affiliation:bbva","type":"related"},{"from":"section:notebook","to":"note:ontologies-and-data-structures","type":"contains"},{"from":"section:notebook","to":"note:category-theory","type":"contains"},{"from":"section:notebook","to":"note:quantum-measurement","type":"contains"},{"from":"note:quantum-measurement","to":"topic:quantum","type":"about"},{"from":"section:notebook","to":"project:meaning-native-computing","type":"contains"},{"from":"profile:emre","to":"project:meaning-native-computing","type":"related"},{"from":"project:meaning-native-computing","to":"topic:uncertainty","type":"about"},{"from":"section:works","to":"work:coverage-deferral","type":"contains"},{"from":"work:coverage-deferral","to":"topic:fairness","type":"about"},{"from":"work:coverage-deferral","to":"topic:uncertainty","type":"about"},{"from":"section:works","to":"work:agent-chronicle","type":"contains"},{"from":"work:agent-chronicle","to":"topic:agents","type":"about"},{"from":"section:works","to":"work:quantum-conformal","type":"contains"},{"from":"work:quantum-conformal","to":"topic:uncertainty","type":"about"},{"from":"work:quantum-conformal","to":"topic:quantum","type":"about"},{"from":"section:works","to":"work:tara","type":"contains"},{"from":"work:tara","to":"topic:quantum","type":"about"},{"from":"work:tara","to":"topic:uncertainty","type":"about"},{"from":"section:works","to":"work:chat-assistant","type":"contains"},{"from":"work:chat-assistant","to":"topic:invention","type":"about"},{"from":"work:chat-assistant","to":"topic:agents","type":"about"},{"from":"work:chat-assistant","to":"topic:language","type":"about"},{"from":"section:works","to":"work:micro-robot-rescue","type":"contains"},{"from":"work:micro-robot-rescue","to":"topic:invention","type":"about"},{"from":"work:micro-robot-rescue","to":"topic:agents","type":"about"},{"from":"section:works","to":"work:ai-pos","type":"contains"},{"from":"work:ai-pos","to":"topic:invention","type":"about"},{"from":"work:ai-pos","to":"topic:language","type":"about"},{"from":"section:works","to":"work:virtual-input","type":"contains"},{"from":"work:virtual-input","to":"topic:invention","type":"about"},{"from":"section:works","to":"work:personalized-suggestions","type":"contains"},{"from":"work:personalized-suggestions","to":"topic:invention","type":"about"},{"from":"section:works","to":"work:adversarial-quantum","type":"contains"},{"from":"work:adversarial-quantum","to":"topic:quantum","type":"about"},{"from":"work:adversarial-quantum","to":"topic:uncertainty","type":"about"},{"from":"section:works","to":"work:turkish-asr","type":"contains"},{"from":"work:turkish-asr","to":"topic:language","type":"about"},{"from":"section:works","to":"work:qwen-grpo","type":"contains"},{"from":"work:qwen-grpo","to":"topic:language","type":"about"},{"from":"section:works","to":"work:turkish-reasoning-benchmark","type":"contains"},{"from":"work:turkish-reasoning-benchmark","to":"topic:language","type":"about"},{"from":"section:works","to":"work:multilingual-chatbots","type":"contains"},{"from":"work:multilingual-chatbots","to":"topic:language","type":"about"},{"from":"section:works","to":"work:ad-text-classification","type":"contains"},{"from":"work:ad-text-classification","to":"topic:language","type":"about"},{"from":"section:works","to":"work:weight-editing","type":"contains"},{"from":"work:weight-editing","to":"topic:agents","type":"about"},{"from":"work:weight-editing","to":"topic:language","type":"about"},{"from":"section:works","to":"work:bloom","type":"contains"},{"from":"work:bloom","to":"topic:language","type":"about"},{"from":"section:portfolio","to":"patent:2026-007909","type":"contains"},{"from":"patent:2026-007909","to":"topic:invention","type":"about"},{"from":"patent:2026-007909","to":"topic:language","type":"about"},{"from":"section:portfolio","to":"patent:2026-007907","type":"contains"},{"from":"patent:2026-007907","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2026-006294","type":"contains"},{"from":"patent:2026-006294","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2026-006289","type":"contains"},{"from":"patent:2026-006289","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2026-004444","type":"contains"},{"from":"patent:2026-004444","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2026-004441","type":"contains"},{"from":"patent:2026-004441","to":"topic:invention","type":"about"},{"from":"patent:2026-004441","to":"topic:quantum","type":"about"},{"from":"patent:2026-004441","to":"topic:uncertainty","type":"about"},{"from":"section:portfolio","to":"patent:2026-002909","type":"contains"},{"from":"patent:2026-002909","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2026-001992","type":"contains"},{"from":"patent:2026-001992","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-019989","type":"contains"},{"from":"patent:2025-019989","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-011133","type":"contains"},{"from":"patent:2025-011133","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-008786","type":"contains"},{"from":"patent:2025-008786","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-008273","type":"contains"},{"from":"patent:2025-008273","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-008055","type":"contains"},{"from":"patent:2025-008055","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-008032","type":"contains"},{"from":"patent:2025-008032","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-008028","type":"contains"},{"from":"patent:2025-008028","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-007997","type":"contains"},{"from":"patent:2025-007997","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2025-007995","type":"contains"},{"from":"patent:2025-007995","to":"topic:invention","type":"about"},{"from":"patent:2025-007995","to":"topic:agents","type":"about"},{"from":"section:portfolio","to":"patent:2024-003815","type":"contains"},{"from":"patent:2024-003815","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2024-003813","type":"contains"},{"from":"patent:2024-003813","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2024-003592","type":"contains"},{"from":"patent:2024-003592","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2023-011901","type":"contains"},{"from":"patent:2023-011901","to":"topic:invention","type":"about"},{"from":"patent:2023-011901","to":"work:micro-robot-rescue","type":"family"},{"from":"section:portfolio","to":"patent:2023-011870","type":"contains"},{"from":"patent:2023-011870","to":"topic:invention","type":"about"},{"from":"patent:2023-011870","to":"topic:language","type":"about"},{"from":"patent:2023-011870","to":"work:chat-assistant","type":"family"},{"from":"section:portfolio","to":"patent:2023-011830","type":"contains"},{"from":"patent:2023-011830","to":"topic:invention","type":"about"},{"from":"patent:2023-011830","to":"work:personalized-suggestions","type":"family"},{"from":"section:portfolio","to":"patent:2023-011601","type":"contains"},{"from":"patent:2023-011601","to":"topic:invention","type":"about"},{"from":"patent:2023-011601","to":"work:virtual-input","type":"family"},{"from":"section:portfolio","to":"patent:2023-011600","type":"contains"},{"from":"patent:2023-011600","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2023-011599","type":"contains"},{"from":"patent:2023-011599","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2023-004244","type":"contains"},{"from":"patent:2023-004244","to":"topic:invention","type":"about"},{"from":"patent:2023-004244","to":"work:ai-pos","type":"family"},{"from":"section:portfolio","to":"patent:2023-004047","type":"contains"},{"from":"patent:2023-004047","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2022-016679","type":"contains"},{"from":"patent:2022-016679","to":"topic:invention","type":"about"},{"from":"section:portfolio","to":"patent:2022-016395","type":"contains"},{"from":"patent:2022-016395","to":"topic:invention","type":"about"},{"from":"section:lab","to":"model:turkish-sentiment","type":"contains"},{"from":"model:turkish-sentiment","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:whisper-tr","type":"contains"},{"from":"model:whisper-tr","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:gemma-wiki-tr","type":"contains"},{"from":"model:gemma-wiki-tr","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:java-method-vectors","type":"contains"},{"from":"model:java-method-vectors","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:gemma-reasoning-tr","type":"contains"},{"from":"model:gemma-reasoning-tr","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:abstract-title","type":"contains"},{"from":"model:abstract-title","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:xlsr-tr","type":"contains"},{"from":"model:xlsr-tr","to":"topic:language","type":"about"},{"from":"section:lab","to":"model:qwen-grpo","type":"contains"},{"from":"model:qwen-grpo","to":"topic:language","type":"about"},{"from":"work:qwen-grpo","to":"model:qwen-grpo","type":"sameProject"},{"from":"section:lab","to":"repository:regression-atlas","type":"contains"},{"from":"repository:regression-atlas","to":"topic:uncertainty","type":"about"},{"from":"section:lab","to":"repository:bird-sql","type":"contains"},{"from":"repository:bird-sql","to":"topic:agents","type":"about"},{"from":"repository:bird-sql","to":"topic:uncertainty","type":"about"},{"from":"section:lab","to":"repository:webcli","type":"contains"},{"from":"repository:webcli","to":"topic:agents","type":"about"},{"from":"repository:webcli","to":"topic:language","type":"about"},{"from":"section:lab","to":"repository:fairness-metrics","type":"contains"},{"from":"repository:fairness-metrics","to":"topic:fairness","type":"about"},{"from":"section:lab","to":"repository:quantum-clocks","type":"contains"},{"from":"repository:quantum-clocks","to":"topic:quantum","type":"about"},{"from":"section:lab","to":"repository:paperbanana-test","type":"contains"},{"from":"repository:paperbanana-test","to":"topic:agents","type":"about"},{"from":"section:lab","to":"repository:worldcup-nowcast","type":"contains"},{"from":"repository:worldcup-nowcast","to":"topic:uncertainty","type":"about"},{"from":"section:lab","to":"repository:agent-chronicle","type":"contains"},{"from":"repository:agent-chronicle","to":"topic:agents","type":"about"},{"from":"work:agent-chronicle","to":"repository:agent-chronicle","type":"sameProject"},{"from":"model:turkish-sentiment","to":"repository:turkish-binary-reviews","type":"related"},{"from":"repository:turkish-binary-reviews","to":"topic:language","type":"about"},{"from":"study:coverage-deferral","to":"work:coverage-deferral","type":"documents"},{"from":"study:coverage-deferral","to":"topic:fairness","type":"about"},{"from":"study:coverage-deferral","to":"topic:uncertainty","type":"about"},{"from":"study:turkish-sentiment-evaluation","to":"model:turkish-sentiment","type":"documents"},{"from":"study:turkish-sentiment-evaluation","to":"topic:language","type":"about"},{"from":"section:contact","to":"contact:github","type":"contains"},{"from":"profile:emre","to":"contact:github","type":"contact"},{"from":"contact:github","to":"repository:regression-atlas","type":"related"},{"from":"contact:github","to":"repository:bird-sql","type":"related"},{"from":"contact:github","to":"repository:webcli","type":"related"},{"from":"contact:github","to":"repository:fairness-metrics","type":"related"},{"from":"contact:github","to":"repository:quantum-clocks","type":"related"},{"from":"contact:github","to":"repository:paperbanana-test","type":"related"},{"from":"contact:github","to":"repository:worldcup-nowcast","type":"related"},{"from":"contact:github","to":"repository:agent-chronicle","type":"related"},{"from":"section:contact","to":"contact:hugging-face","type":"contains"},{"from":"profile:emre","to":"contact:hugging-face","type":"contact"},{"from":"contact:hugging-face","to":"model:turkish-sentiment","type":"related"},{"from":"contact:hugging-face","to":"model:whisper-tr","type":"related"},{"from":"contact:hugging-face","to":"model:gemma-wiki-tr","type":"related"},{"from":"contact:hugging-face","to":"model:java-method-vectors","type":"related"},{"from":"contact:hugging-face","to":"model:gemma-reasoning-tr","type":"related"},{"from":"contact:hugging-face","to":"model:abstract-title","type":"related"},{"from":"contact:hugging-face","to":"model:xlsr-tr","type":"related"},{"from":"contact:hugging-face","to":"model:qwen-grpo","type":"related"},{"from":"section:contact","to":"contact:scholar","type":"contains"},{"from":"profile:emre","to":"contact:scholar","type":"contact"},{"from":"section:contact","to":"contact:linkedin","type":"contains"},{"from":"profile:emre","to":"contact:linkedin","type":"contact"},{"from":"affiliation:bbva","to":"contact:linkedin","type":"documents"},{"from":"section:contact","to":"contact:x","type":"contains"},{"from":"profile:emre","to":"contact:x","type":"contact"},{"from":"section:contact","to":"contact:orcid","type":"contains"},{"from":"profile:emre","to":"contact:orcid","type":"contact"},{"from":"section:contact","to":"contact:navarra","type":"contains"},{"from":"profile:emre","to":"contact:navarra","type":"contact"},{"from":"affiliation:navarra","to":"contact:navarra","type":"documents"},{"from":"section:readers","to":"reader:guide","type":"contains"},{"from":"section:readers","to":"reader:graph","type":"contains"},{"from":"section:readers","to":"reader:profile","type":"contains"},{"from":"profile:emre","to":"reader:profile","type":"readableAs"},{"from":"section:research","to":"reader:graph","type":"readableAs"},{"from":"section:portfolio","to":"reader:guide","type":"readableAs"},{"from":"section:lab","to":"reader:guide","type":"readableAs"},{"from":"section:works","to":"reader:guide","type":"readableAs"}]}