{"address":{"q":"OLMoTrace","record":"olmotrace-aio-20261029"},"analysis":{"analysis":"A provenance tool whose authors state precisely what a match does not mean is composed with the use they name and without the bound they set on it. The composition turns a trace of verbatim overlap into evidence for a claim, the conversion of a matching relation into a citation relation that the paper's Limitations refuse; the use is the authors', the conversion the composition's.","d":"OLMOTRACE, BY NAME, ON GOOGLE'S AI OVERVIEW, SIGNED OUT, 2026-10-29: 'an open-source system developed by the Allen Institute for Artificial Intelligence (Ai2) that traces language model outputs back to their multi-trillion-token training datasets in real time.' How it works (the Show OLMoTrace button highlights verbatim spans; matches against corpora such as Dolma, ranking up to 10 documents by BM25; an extended infini-gram at O(L log N)), supported models (OLMo 2 32B and 13B Instruct, OLMoE 1B 7B, the OLMo 3 family), uses (fact-checking, hallucination diagnosis, auditing). Six cards: Ai2's blog, arXiv 2504.07096, the ACL Anthology, Ai2 on X (OLMo 3), Techzine, Ken Yeung's newsletter.","d_full":"OLMOTRACE, BY NAME, ON GOOGLE'S AI OVERVIEW, SIGNED OUT, 2026-10-29: 'an open-source system developed by the Allen Institute for Artificial Intelligence (Ai2) that traces language model outputs back to their multi-trillion-token training datasets in real time.' How it works (the Show OLMoTrace button highlights verbatim spans; matches against corpora such as Dolma, ranking up to 10 documents by BM25; an extended infini-gram at O(L log N)), supported models (OLMo 2 32B and 13B Instruct, OLMoE 1B 7B, the OLMo 3 family), uses (fact-checking, hallucination diagnosis, auditing). Six cards: Ai2's blog, arXiv 2504.07096, the ACL Anthology, Ai2 on X (OLMo 3), Techzine, Ken Yeung's newsletter.","findings":["THE TOOL HELD. Ai2, real time, multi-trillion tokens and verbatim matching are the paper's: 'OLMoTrace finds and shows verbatim matches between segments of language model output and documents in the training text corpora' (record). Checked 2026-10-29 against the provenance census record of the same day and the sources it saved.","THE USE WITHOUT ITS LIMIT. The authors name fact checking as a use: 'We showcase how it can be used to explore fact checking' (abstract), and in their first case study 'we can use their corresponding documents to fact check claims made in the spans'. Their Limitations bound it: 'The retrieved documents should not be interpreted as having a causal effect on the LM output, or as supporting evidence or citations for the LM output' (the record's negative tags). The composition's first use is 'Fact-Checking: Verify whether specific claims in a model's answer are backed by real training documents': the use at a raised force, the limit dropped; Ai2's blog post, card 1, also omits the limit. (Repaired 2026-10-29: the finding had called fact checking a use the authors disclaim.)","THE PARTNERS UNSAID. The record names the University of Washington, UC Berkeley and Stanford with Ai2; the composition names Ai2 alone.","THE MODELS CURRENT. The OLMo 3 family comes from Ai2's post on X; the record's count is OLMo-2-32B-Instruct's training data (3.2 billion documents, 4.6 trillion tokens). The record is to carry OLMo 3 from Ai2's own page."],"match":"BROAD MATCH","mt":"OLMOTRACE ON THE OVERVIEW — AI2, REAL TIME, INFINI-GRAM; 'FACT-CHECKING: VERIFY WHETHER SPECIFIC CLAIMS … ARE BACKED BY REAL TRAINING DOCUMENTS', THE AUTHORS' USE GIVEN WITHOUT THEIR LIMIT","notes":{"prompts":"One query. Sent by the operator on 2026-10-29 with thirteen others, one per entity of the provenance meta-aggregator, from the strings supplied at his request ('shoot me those search strings. strings on the bare entity, no follow questions'); pasted in one message separated by '$'. The paste was lost to a context compaction of this session and re-pasted by the operator the same day; the second paste is the one seated."},"originator":{"basis":"Not the archive's: OLMoTrace; its operator, as the record gives it: Allen Institute for AI (Ai2), with the University of Washington, UC Berkeley and Stanford. Formalized by the provenance meta-aggregator record of 2026-10-29 (https://www.provenanceerasure.org/aggregators/olmotrace/), editor Lee Sharks; the record's fields carry verbatim quotes from the sources it saved with sha256, each with its basis (the operator's own page or a third-party account). Recorded 2026-10-29; repaired the same day.","entity_type":"service","name":"Allen Institute for AI (Ai2), with the University of Washington, UC Berkeley and Stanford","relation":"external","spxi_treatment":"partial"},"reading":"The innocent reading first. The Overview names the tool and its maker, explains how it finds training text in a model's answer, lists the models it covers and what it is good for."},"measures":{"archive_controlled_cites":0,"cite_list":[{"n":1,"note":null,"rel":"third_party","site":"Allen Institute for Artificial Intelligence","snip":"Feature: OLMoTrace in Ai2 Playground traces language model outputs to multi-trillion-token training data in real time. Supported Models: OLMo 2 32B Instruct, OL...","title":"Going beyond open data – increasing transparency and trust in language models with OLMoTrace | Ai2","url":null},{"n":2,"note":null,"rel":"third_party","site":"arXiv","snip":"[2504.07096] OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens Scheduled maintenance: Wednesday, October 28, 7:00 to 12:00 EDT (11:","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training ...","url":null},{"n":3,"note":null,"rel":"third_party","site":"ACL Anthology","snip":"We present OLMOTRACE, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMOTRACE...","title":"Tracing Language Model Outputs Back to Trillions of Training Tokens","url":null},{"n":4,"note":null,"rel":"third_party","site":"X","snip":"Ai2 on X: \"Olmo 3 is wired into OlmoTrace in the Ai2 Playground, so you don't just see its behavior—you can trace it. For example, you can ask Olmo 3-Think (32B...","title":"Olmo 3 is wired into OlmoTrace in the Ai2 Playground, so you don't just ... - X","url":null},{"n":5,"note":null,"rel":"third_party","site":"Techzine Global","snip":"After generating an answer from OLMo in the Ai2 Playground, users can activate the tool by clicking the “Show OLMoTrace” button below the output. The tool then ...","title":"Ai2 introduces OLMoTrace: a peek inside LLM's - Techzine Global","url":null},{"n":6,"note":null,"rel":"third_party","site":"The AI Economy | Ken Yeung","snip":"Ken Yeung Apr 09, 2025 1 Ai2 has launched a tool to help developers answer a critical question: Where do AI models get their data? Called OLMoTrace, it's an ope...","title":"Meet OLMoTrace: The Tool That Shows Where AI Gets Its Info","url":null}],"cites":6,"per":0.25,"per_note":"Ai2 named; no person; the arXiv identifier in a card; Ai2's own post and the paper cited.","per_v":{"author":false,"id":true,"inst":true,"src":true}},"observation":{"auth":"signed out, incognito","date":"2026-10-29","ev":"paste","q":"OLMoTrace","q_kind":"the name of an entity of the provenance meta-aggregator (OLMoTrace; record https://www.provenanceerasure.org/aggregators/olmotrace/, compiled 2026-10-29), the bare entity string supplied at the operator's request ('strings on the bare entity, no follow questions') and run by him the same day, to supply the composition layer's account of the entity for its record and its /non row. A baseline: the record landed on provenanceerasure.org the same day (commit 8a9f153) and no card cites it. NEW address.","s":"Machine Reception","surface":"Google AI Overview","transcript":"[Google AI Overview at the query, signed out and incognito (operator defaults of 2026-10-01 and 2026-10-14), 2026-10-29. The paste is the Overview expanded (the 'AI Mode Conversation' view, with the source cards that follow the answer); the 'You said' line carries the query twice, run together, and is given once here. Inline links are Google redirect URLs, kept as pasted.]\n\n[QUERENT] OLMoTrace\n\n[SYSTEM] [OLMoTrace](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ) is an open-source system developed by the Allen Institute for Artificial Intelligence (Ai2) that traces language model outputs back to their multi-trillion-token training datasets in real time. [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ), [2](https://www.google.com/goto?url=CAESWAHrOzAVIeW0Bh-S4A2VvhIfG4x5GI442H2AG7c4YT-P8qSUHih41gNA2d_u0ez62uyi0CLMCuDxp107lq0nGROUCWBCMy5JoGWd2CZ7_vNcWWCs3Lu2iFg)]\nHow It Works\n\n* Real-Time Tracing: After a model generates a response in the Ai2 Playground, users can click the Show OLMoTrace button to highlight verbatim spans of text. [[1](https://www.google.com/goto?url=CAESkgEB6zswFSw37mmS0ky2JdwMbluTG9bXw6YrEyY7-RDR3C6gpGJF1AjuVzgdHaMhPrwWEs6-CqOPaBUaJmKtgKhm0K6DY4dgamujc7BlSKs3Q7zgBXwn4p50GiZOmvHB7LP_ros68_TLow3I8e5BC6voQvexCU7B9RANXq30erTczX0PJp4Eoot_gOSfIdL-s64rEQ), [2](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n* Source Retrieval: The tool matches output segments against training corpora (such as the Dolma datasets) and ranks up to 10 context documents using BM25 and unigram probabilities. [[1](https://www.google.com/goto?url=CAESaQHrOzAVV_6J7u0vQR70ckMfNhiCogECpGpN15fGLDhAZkGzPPDHW94cWHDI3yvNEPPIeJCWECt_JJh8NwwM53Wiwyx94U6j_n8S84uLcd-yOdbxGgO2_8_63OmgYRHsjdzAlH-iXL3LIA), [2](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n* Underlying Tech: It uses an extended version of infini-gram with a parallel algorithm that reduces lookup complexity to \\(O(L \\log N)\\). [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n\nSupported Models\n\n* OLMo 2 32B Instruct\n* OLMo 2 13B Instruct\n* OLMoE 1B 7B Instruct\n* OLMo 3 family (including OLMo 3-Think 32B) [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ), [2](https://www.google.com/goto?url=CAESaQHrOzAVV_6J7u0vQR70ckMfNhiCogECpGpN15fGLDhAZkGzPPDHW94cWHDI3yvNEPPIeJCWECt_JJh8NwwM53Wiwyx94U6j_n8S84uLcd-yOdbxGgO2_8_63OmgYRHsjdzAlH-iXL3LIA)]\n\nKey Use Cases\n\n* Fact-Checking: Verify whether specific claims in a model's answer are backed by real training documents or generated from general parameters. [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ), [2](https://www.google.com/goto?url=CAESkgEB6zswFSw37mmS0ky2JdwMbluTG9bXw6YrEyY7-RDR3C6gpGJF1AjuVzgdHaMhPrwWEs6-CqOPaBUaJmKtgKhm0K6DY4dgamujc7BlSKs3Q7zgBXwn4p50GiZOmvHB7LP_ros68_TLow3I8e5BC6voQvexCU7B9RANXq30erTczX0PJp4Eoot_gOSfIdL-s64rEQ)]\n* Hallucination Diagnosis: Spot where a model mixes up facts or memorized text from source files. [[1](https://www.google.com/goto?url=CAESZQHrOzAVTuCtZhUvlAC1FgYlT-ioaSAfiV6VG-c9osiVQ_FPlF62I3S48qKZjg6PnH3vYzrPeKi7Rar1Z4mDks0EMNRTl8vcyc5d0cIMWkhvQoo_giR_HHzJhHcmcAGkUssJqLjF), [2](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n* Auditing & Transparency: Inspect the data recipes and pretraining paths for regulatory compliance or research. [[1](https://www.google.com/goto?url=CAESfgHrOzAVd9pZK6hXPDhajqcIyrIpeoeKsOtolrBXNH59t2FmwwJ6HuF-YnkP1-EVgZEWX4T7kBh1XIkmkww2H4xJ8oprHeZCLafy4gXrndLDeynguHxNr21pz4Ein_w-Tws5-F6y0jfcbHLurOUXxmovED45PgVVy2GZwu4b7w), [2](https://www.google.com/goto?url=CAESaQHrOzAVV_6J7u0vQR70ckMfNhiCogECpGpN15fGLDhAZkGzPPDHW94cWHDI3yvNEPPIeJCWECt_JJh8NwwM53Wiwyx94U6j_n8S84uLcd-yOdbxGgO2_8_63OmgYRHsjdzAlH-iXL3LIA)]\n\nWould you like to know how to access the open-source code for OLMoTrace on GitHub/Hugging Face, or are you looking for details on a specific OLMo model version?\nAllen Institute for Artificial Intelligence\nGoing beyond open data – increasing transparency and trust in language models with OLMoTrace | Ai2\nFeature: OLMoTrace in Ai2 Playground traces language model outputs to multi-trillion-token training data in real time. Supported Models: OLMo 2 32B Instruct, OL...\narXiv\nOLMoTrace: Tracing Language Model Outputs Back to Trillions of Training ...\n[2504.07096] OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens Scheduled maintenance: Wednesday, October 28, 7:00 to 12:00 EDT (11:\nACL Anthology\nTracing Language Model Outputs Back to Trillions of Training Tokens\nWe present OLMOTRACE, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMOTRACE...\nX\nOlmo 3 is wired into OlmoTrace in the Ai2 Playground, so you don't just ... - X\nAi2 on X: \"Olmo 3 is wired into OlmoTrace in the Ai2 Playground, so you don't just see its behavior—you can trace it. For example, you can ask Olmo 3-Think (32B...\nTechzine Global\nAi2 introduces OLMoTrace: a peek inside LLM's - Techzine Global\nAfter generating an answer from OLMo in the Ai2 Playground, users can activate the tool by clicking the “Show OLMoTrace” button below the output. The tool then ...\nThe AI Economy | Ken Yeung\nMeet OLMoTrace: The Tool That Shows Where AI Gets Its Info\nKen Yeung Apr 09, 2025 1 Ai2 has launched a tool to help developers answer a critical question: Where do AI models get their data? Called OLMoTrace, it's an ope...","transcript_class":"CAPTURE-TIME VERBATIM RECORD — paste of the Overview expanded, with its source cards","transcript_complete":"complete as supplied","transcript_raw":"[OLMoTrace](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ) is an open-source system developed by the Allen Institute for Artificial Intelligence (Ai2) that traces language model outputs back to their multi-trillion-token training datasets in real time. [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ), [2](https://www.google.com/goto?url=CAESWAHrOzAVIeW0Bh-S4A2VvhIfG4x5GI442H2AG7c4YT-P8qSUHih41gNA2d_u0ez62uyi0CLMCuDxp107lq0nGROUCWBCMy5JoGWd2CZ7_vNcWWCs3Lu2iFg)]\nHow It Works\n\n* Real-Time Tracing: After a model generates a response in the Ai2 Playground, users can click the Show OLMoTrace button to highlight verbatim spans of text. [[1](https://www.google.com/goto?url=CAESkgEB6zswFSw37mmS0ky2JdwMbluTG9bXw6YrEyY7-RDR3C6gpGJF1AjuVzgdHaMhPrwWEs6-CqOPaBUaJmKtgKhm0K6DY4dgamujc7BlSKs3Q7zgBXwn4p50GiZOmvHB7LP_ros68_TLow3I8e5BC6voQvexCU7B9RANXq30erTczX0PJp4Eoot_gOSfIdL-s64rEQ), [2](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n* Source Retrieval: The tool matches output segments against training corpora (such as the Dolma datasets) and ranks up to 10 context documents using BM25 and unigram probabilities. [[1](https://www.google.com/goto?url=CAESaQHrOzAVV_6J7u0vQR70ckMfNhiCogECpGpN15fGLDhAZkGzPPDHW94cWHDI3yvNEPPIeJCWECt_JJh8NwwM53Wiwyx94U6j_n8S84uLcd-yOdbxGgO2_8_63OmgYRHsjdzAlH-iXL3LIA), [2](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n* Underlying Tech: It uses an extended version of infini-gram with a parallel algorithm that reduces lookup complexity to \\(O(L \\log N)\\). [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n\nSupported Models\n\n* OLMo 2 32B Instruct\n* OLMo 2 13B Instruct\n* OLMoE 1B 7B Instruct\n* OLMo 3 family (including OLMo 3-Think 32B) [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ), [2](https://www.google.com/goto?url=CAESaQHrOzAVV_6J7u0vQR70ckMfNhiCogECpGpN15fGLDhAZkGzPPDHW94cWHDI3yvNEPPIeJCWECt_JJh8NwwM53Wiwyx94U6j_n8S84uLcd-yOdbxGgO2_8_63OmgYRHsjdzAlH-iXL3LIA)]\n\nKey Use Cases\n\n* Fact-Checking: Verify whether specific claims in a model's answer are backed by real training documents or generated from general parameters. [[1](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ), [2](https://www.google.com/goto?url=CAESkgEB6zswFSw37mmS0ky2JdwMbluTG9bXw6YrEyY7-RDR3C6gpGJF1AjuVzgdHaMhPrwWEs6-CqOPaBUaJmKtgKhm0K6DY4dgamujc7BlSKs3Q7zgBXwn4p50GiZOmvHB7LP_ros68_TLow3I8e5BC6voQvexCU7B9RANXq30erTczX0PJp4Eoot_gOSfIdL-s64rEQ)]\n* Hallucination Diagnosis: Spot where a model mixes up facts or memorized text from source files. [[1](https://www.google.com/goto?url=CAESZQHrOzAVTuCtZhUvlAC1FgYlT-ioaSAfiV6VG-c9osiVQ_FPlF62I3S48qKZjg6PnH3vYzrPeKi7Rar1Z4mDks0EMNRTl8vcyc5d0cIMWkhvQoo_giR_HHzJhHcmcAGkUssJqLjF), [2](https://www.google.com/goto?url=CAESWgHrOzAVoVYHLgJxMVIjxyaZx7wDArKB6jxCb1tOprJFofLF9_o_Lr6foJNzJ2skLWhN04W7o7uFmFuQkrV4xPmu8JuLWWjcOIm7uniqJ_3AgD9QQJlTrCUJTQ)]\n* Auditing & Transparency: Inspect the data recipes and pretraining paths for regulatory compliance or research. [[1](https://www.google.com/goto?url=CAESfgHrOzAVd9pZK6hXPDhajqcIyrIpeoeKsOtolrBXNH59t2FmwwJ6HuF-YnkP1-EVgZEWX4T7kBh1XIkmkww2H4xJ8oprHeZCLafy4gXrndLDeynguHxNr21pz4Ein_w-Tws5-F6y0jfcbHLurOUXxmovED45PgVVy2GZwu4b7w), [2](https://www.google.com/goto?url=CAESaQHrOzAVV_6J7u0vQR70ckMfNhiCogECpGpN15fGLDhAZkGzPPDHW94cWHDI3yvNEPPIeJCWECt_JJh8NwwM53Wiwyx94U6j_n8S84uLcd-yOdbxGgO2_8_63OmgYRHsjdzAlH-iXL3LIA)]\n\nWould you like to know how to access the open-source code for OLMoTrace on GitHub/Hugging Face, or are you looking for details on a specific OLMo model version?\nAllen Institute for Artificial Intelligence\nGoing beyond open data – increasing transparency and trust in language models with OLMoTrace | Ai2\nFeature: OLMoTrace in Ai2 Playground traces language model outputs to multi-trillion-token training data in real time. Supported Models: OLMo 2 32B Instruct, OL...\narXiv\nOLMoTrace: Tracing Language Model Outputs Back to Trillions of Training ...\n[2504.07096] OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens Scheduled maintenance: Wednesday, October 28, 7:00 to 12:00 EDT (11:\nACL Anthology\nTracing Language Model Outputs Back to Trillions of Training Tokens\nWe present OLMOTRACE, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMOTRACE...\nX\nOlmo 3 is wired into OlmoTrace in the Ai2 Playground, so you don't just ... - X\nAi2 on X: \"Olmo 3 is wired into OlmoTrace in the Ai2 Playground, so you don't just see its behavior—you can trace it. For example, you can ask Olmo 3-Think (32B...\nTechzine Global\nAi2 introduces OLMoTrace: a peek inside LLM's - Techzine Global\nAfter generating an answer from OLMo in the Ai2 Playground, users can activate the tool by clicking the “Show OLMoTrace” button below the output. The tool then ...\nThe AI Economy | Ken Yeung\nMeet OLMoTrace: The Tool That Shows Where AI Gets Its Info\nKen Yeung Apr 09, 2025 1 Ai2 has launched a tool to help developers answer a critical question: Where do AI models get their data? Called OLMoTrace, it's an ope...","transcript_read":"READ IN FULL 2026-10-29","turns":1},"slug":"olmotrace-aio-20261029"}