{"as_of":"2026-08-06T08:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:152833144b3a893ef4921d8b5067c22639f1379f2c938e1c2280ef0d80b3f227","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T06:37:34.840129Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.21984/citation-record","integrity":"/paper/2605.21984/integrity","json":"/paper/2605.21984/citation-record.json","paper":"/paper/2605.21984"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Amershi, D","venue":null,"work_id":"e7905e62-3354-45bb-96c7-f0bbe4e1b7b0","year":2019},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:bef9cf096488c7a20c4de0bc5d8183fb0216cd6bc5867f29ffad3891956b3b29","observation_id":"fe2cd991-c4b3-4371-9fe2-83b7b9328721","resolution":{"observed_at":"2026-05-22T06:46:12.487277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13282","last_updated":"2025-01-23T00:17:48Z","snapshot_observed_at":"2026-08-04T14:29:09.653355Z","submitted_at":"2025-01-23T00:17:48Z","title":"Experience with GitHub Copilot for Developer Productivity at Zoominfo","version":1},"cited_work":{"arxiv_id":"2501.13282","doi":"10.48550/arxiv.2501.13282","metadata_source":"arxiv_reference","pith_arxiv_id":"2501.13282","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Bakal, A","venue":"ArXiv.org","work_id":"bebae1c4-d659-43b6-987c-82dde8e64579","year":2025},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2501.13282","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:bd4fb1379670d2447049e821a384ea0e67e75024f3241115e5a1efbcc66a9335","observation_id":"b1d00ca7-94a1-4783-bcf6-8931ed68a7ae","resolution":{"observed_at":"2026-05-22T06:41:10.777816Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.14255","last_updated":"2022-07-28T17:40:47Z","snapshot_observed_at":"2026-08-03T04:07:30.689454Z","submitted_at":"2022-07-28T17:40:47Z","title":"Efficient Training of Language Models to Fill in the Middle","version":1},"cited_work":{"arxiv_id":"2207.14255","doi":"10.48550/arxiv.2207.14255","metadata_source":"pith","pith_arxiv_id":"2207.14255","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Efficient Training of Language Models to Fill in the Middle","venue":"cs.CL","work_id":"54afe4f8-4d93-4829-99ae-2a27143a9641","year":2022},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2207.14255","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:384748e0b0ef0d70316c414e1f757f00faf5df6dc812e842714a912e44192cab","observation_id":"b58f2b7f-6a1a-4a85-be89-8210b6ee9528","resolution":{"observed_at":"2026-05-22T06:41:10.801115Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09390","last_updated":"2023-12-14T23:07:33Z","snapshot_observed_at":"2026-07-06T17:02:09.539730Z","submitted_at":"2023-12-14T23:07:33Z","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","version":1},"cited_work":{"arxiv_id":"2312.09390","doi":"10.48550/arxiv.2312.09390","metadata_source":"pith","pith_arxiv_id":"2312.09390","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Burns, P","venue":"cs.CL","work_id":"4a21c761-9a3d-4f84-a55d-5779da5da28f","year":2023},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2312.09390","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:43a62fe7a4ff2ca67b6b6f63bca8300bd6c441a3f8c5662691e5487493c00380","observation_id":"e0bccba7-a27d-4e04-8a15-84edc45fbe7c","resolution":{"observed_at":"2026-05-22T06:41:10.797126Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-07-13T23:49:45.539419+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T23:49:45.539419+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15217","last_updated":"2023-09-11T17:25:24Z","snapshot_observed_at":"2026-08-03T19:11:09.671782Z","submitted_at":"2023-07-27T22:29:25Z","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","version":2},"cited_work":{"arxiv_id":"2307.15217","doi":"10.48550/arxiv.2307.15217","metadata_source":"pith","pith_arxiv_id":"2307.15217","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","venue":"cs.AI","work_id":"73fe40c4-d27f-4883-a2f1-52ea228f44fd","year":2023},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2307.15217","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:5371bd4e1cca7ab2af863a8758b09db4cc66a5f26c66cbdd49793c092d01da40","observation_id":"85dbb226-d4be-4a22-8545-5ed867158fa0","resolution":{"observed_at":"2026-05-22T06:41:10.792145Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-07-12T05:49:19.412323+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T05:49:19.412323+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2511.03773","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T20:05:34.030607Z","title":"Scaling agent learning via experience synthesis","venue":null,"work_id":"07901808-801a-418a-aa0f-4fbaebfab139","year":2026},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:6a04cc77ee7b8c439c57cea6e1405ce503a02f2388cd8615f5c6b04a82994a93","observation_id":"a88346b7-d73a-4c27-9ff8-14081bf257b4","resolution":{"observed_at":"2026-05-22T06:41:10.787332Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.12901","last_updated":"2019-04-29T18:40:15Z","snapshot_observed_at":"2026-07-06T07:49:17.886466Z","submitted_at":"2019-04-29T18:40:15Z","title":"Challenges of Real-World Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"1904.12901","doi":null,"metadata_source":"pith","pith_arxiv_id":"1904.12901","snapshot_observed_at":"2026-07-03T12:48:11.128704Z","title":"Challenges of Real-World Reinforcement Learning","venue":"cs.LG","work_id":"fc99449a-80f4-4f37-a028-7b3774c78bf6","year":2019},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/1904.12901","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:d695600a649c4cf3f122acc57b9096a1118c4dfc5636820d5550ab0cf6a2571b","observation_id":"cb86744f-254a-491f-b6f6-05b45c2464ac","resolution":{"observed_at":"2026-05-22T06:41:10.782219Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05999","last_updated":"2023-04-09T14:31:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-12T16:25:26Z","title":"InCoder: A Generative Model for Code Infilling and Synthesis","version":3},"cited_work":{"arxiv_id":"2204.05999","doi":"10.48550/arxiv.2204.05999","metadata_source":"pith","pith_arxiv_id":"2204.05999","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"InCoder: A Generative Model for Code Infilling and Synthesis","venue":"cs.SE","work_id":"e98a5559-529d-48b1-833c-b85b662f190c","year":2022},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2204.05999","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:bc3b0709182f5204af393a50b33a8bdc88a2ec3355f1588b36cf771351ce116f","observation_id":"2fce3314-36b4-4e47-a22a-e24a1a2bad7f","resolution":{"observed_at":"2026-05-22T06:41:10.772913Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11644","last_updated":"2023-10-02T06:12:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-20T16:14:25Z","title":"Textbooks Are All You Need","version":2},"cited_work":{"arxiv_id":"2306.11644","doi":"10.48550/arxiv.2306.11644","metadata_source":"pith","pith_arxiv_id":"2306.11644","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Textbooks Are All You Need","venue":"cs.CL","work_id":"9b14eca2-9e41-4755-88ac-c3e7b67253f5","year":2023},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2306.11644","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:7ab82b82d05c3c0b635c765f0f4c0b1b303cb479fd1a841e0f5bf112611bf3f7","observation_id":"a26e147f-85b6-4689-84c3-6f2260ba1973","resolution":{"observed_at":"2026-05-22T06:41:10.768553Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14196","last_updated":"2024-01-26T09:23:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-25T14:17:53Z","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","version":2},"cited_work":{"arxiv_id":"2401.14196","doi":"10.48550/arxiv.2401.14196","metadata_source":"pith","pith_arxiv_id":"2401.14196","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","venue":"cs.SE","work_id":"f22dae5a-27e2-41d0-a061-c4286418dee3","year":2024},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2401.14196","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:7615e849bedcdea61dc3512b4e14c55bfe5d37d9384c220ad71e73401161d163","observation_id":"56254546-81d1-48ef-b006-16a0f1e8cdb0","resolution":{"observed_at":"2026-05-22T06:41:10.764164Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-07-11T06:20:38.664414+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T06:20:38.664414+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10964","last_updated":"2020-05-05T22:00:44Z","snapshot_observed_at":"2026-08-02T02:53:18.136026Z","submitted_at":"2020-04-23T04:21:19Z","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","version":3},"cited_work":{"arxiv_id":"2004.10964","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.10964","snapshot_observed_at":"2026-07-05T17:21:18.056837Z","title":"Don’t stop pretraining: Adapt language models to domains and tasks","venue":"cs.CL","work_id":"7474b2b4-b1ac-4816-aa36-5e59e1cde1e5","year":2020},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2004.10964","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:54b0647e3d527e07d217e93f84a19fdeca46a5050de6dfc36678ed4a7eec1939","observation_id":"18d646ff-63ba-4ec5-97a3-a691ee81490d","resolution":{"observed_at":"2026-05-22T06:41:10.759241Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.14946","last_updated":"2025-05-20T22:14:44Z","snapshot_observed_at":"2026-08-03T02:14:06.794305Z","submitted_at":"2025-05-20T22:14:44Z","title":"Reinforcement Learning from User Feedback","version":1},"cited_work":{"arxiv_id":"2505.14946","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.14946","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reinforcement learning from user feedback","venue":null,"work_id":"ea1aaa24-6f20-4478-b8b9-2937494a0a37","year":2025},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2505.14946","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:2953541353966b08b372b1008f32b136ed13dd026fbbf7f958b51bb13932324f","observation_id":"be025eea-7c21-41ee-bd3e-2b19cfe6c51b","resolution":{"observed_at":"2026-05-22T06:41:10.732700Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15556","last_updated":"2022-03-29T13:38:03Z","snapshot_observed_at":"2026-07-06T12:54:11.616335Z","submitted_at":"2022-03-29T13:38:03Z","title":"Training Compute-Optimal Large Language Models","version":1},"cited_work":{"arxiv_id":"2203.15556","doi":"10.1098/rsta.2024.0522","metadata_source":"pith","pith_arxiv_id":"2203.15556","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Training Compute-Optimal Large Language Models","venue":"cs.CL","work_id":"b2faf28d-86b7-429c-bc42-469458efc246","year":2022},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2203.15556","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:46748cffa2cfbb864b8f1bf57f59ce7f6ff13249977fc2ab819433debe488048","observation_id":"865bf3de-d5f4-4e28-a103-e8f70b141bbf","resolution":{"observed_at":"2026-05-22T06:41:10.736913Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":"2001.08361","doi":"10.1145/3616855.3635845","metadata_source":"pith","pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Laws for Neural Language Models","venue":"cs.LG","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","year":2020},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:738f60999ba6e69f78d4d9dd58387900ac99489a0dd9ea55b09d691e88f8d7b1","observation_id":"e0e1dd31-d37e-46ac-a712-c893c4bc90a6","resolution":{"observed_at":"2026-05-22T06:41:10.740988Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"e9b09963-9090-437b-a802-568c6799ac1a","year":2008},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:115d2883e2eec8682f2ae1b061558b0098313a02cd3e9a27f7adc9add49e55b0","observation_id":"607e726f-ec26-4c5c-89e8-a9825a0dd7cf","resolution":{"observed_at":"2026-05-22T06:46:12.483020Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12050","last_updated":"2024-02-16T19:52:45Z","snapshot_observed_at":"2026-08-04T03:15:05.902705Z","submitted_at":"2023-05-20T00:45:15Z","title":"AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation","version":2},"cited_work":{"arxiv_id":"2305.12050","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.12050","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Murali, C","venue":null,"work_id":"8f4b0f47-d9d6-47d6-b944-c3b9cfabd214","year":2023},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2305.12050","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:1350a2e6403b67fd591401a3295181d8f369b45d794749d24e43d0e3c3b52562","observation_id":"9fa53fc0-cc1f-444b-847d-caf1d37b253a","resolution":{"observed_at":"2026-05-22T06:41:10.754897Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.04123","last_updated":"2026-06-04T19:57:38Z","snapshot_observed_at":"2026-08-03T18:55:54.928348Z","submitted_at":"2025-12-02T16:45:10Z","title":"Measuring Agents in Production","version":4},"cited_work":{"arxiv_id":"2512.04123","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.04123","snapshot_observed_at":"2026-07-03T13:58:21.454102Z","title":"Measuring agents in production","venue":"cs.CY","work_id":"8ecd2bdf-ac54-4351-bfde-0f9876fec59a","year":2025},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2512.04123","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:a1dad91796812e969dfcb7997ba8e158f37061a0f58670c3615ed1619a76b091","observation_id":"c3bec708-e189-4f44-b25d-bad7a0bf9a9b","resolution":{"observed_at":"2026-06-08T02:03:47.777191Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09857","last_updated":"2023-10-23T23:17:13Z","snapshot_observed_at":"2026-08-01T20:28:15.090086Z","submitted_at":"2023-05-17T00:05:24Z","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","version":2},"cited_work":{"arxiv_id":"2305.09857","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.09857","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Raheja, D","venue":null,"work_id":"9661e795-1fa8-40c8-9f56-eb32557c1649","year":2023},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2305.09857","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:760c98910eb7affd5549829e5e061cb01318c9751c577753ec6a376897c4031b","observation_id":"49dc7d42-1589-413a-8a81-6913141f277c","resolution":{"observed_at":"2026-05-22T06:41:10.722739Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.10297","last_updated":"2020-09-27T04:07:11Z","snapshot_observed_at":"2026-08-01T07:33:26.380394Z","submitted_at":"2020-09-22T03:10:49Z","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","version":2},"cited_work":{"arxiv_id":"2009.10297","doi":"10.48550/arxiv.2009.10297","metadata_source":"pith","pith_arxiv_id":"2009.10297","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","venue":"cs.SE","work_id":"5d08898b-ead1-4fdb-b4b6-23e796ce6214","year":2020},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2009.10297","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:611d3cb1cc9aac694d6a9c34370f55ca40d07a8b0a8dd437275832392ea46cc4","observation_id":"753e4b9b-a004-4b50-aa38-a956b7989e00","resolution":{"observed_at":"2026-05-22T06:41:10.727928Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03768","last_updated":"2021-03-14T22:44:38Z","snapshot_observed_at":"2026-07-06T10:02:33.297722Z","submitted_at":"2020-10-08T05:13:36Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","version":2},"cited_work":{"arxiv_id":"2010.03768","doi":"10.1109/cvpr.2001.990517","metadata_source":"pith","pith_arxiv_id":"2010.03768","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","venue":"cs.CL","work_id":"fa436f46-ec0a-4d2e-a0ff-e697def4a7be","year":2020},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2010.03768","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:83c927a4eba48df3c5f9f40a04a8cdb5781596d93da8673fe04a49176d8c5442","observation_id":"750a3829-d2ae-408b-a863-880325f82d3e","resolution":{"observed_at":"2026-05-22T06:41:10.717779Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-05-20T11:23:33.289391+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T11:23:33.289391+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.16856","last_updated":"2026-06-29T12:13:29Z","snapshot_observed_at":"2026-07-13T23:28:27.562632Z","submitted_at":"2026-03-17T17:57:49Z","title":"Online Experiential Learning for Language Models","version":2},"cited_work":{"arxiv_id":"2603.16856","doi":null,"metadata_source":"pith","pith_arxiv_id":"2603.16856","snapshot_observed_at":"2026-07-07T12:33:45.190220Z","title":"Online experiential learning for language models","venue":"cs.CL","work_id":"3fb60853-ab99-4f3e-8f4c-27017c08f0be","year":2026},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2603.16856","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:8cd2b0a49546970ae3ee1944c2d616ab71b5a401b1cc14cffcee856a0b3eeb8d","observation_id":"d6ce63a6-6829-420a-840f-6e9858894bbe","resolution":{"observed_at":"2026-06-30T03:17:28.982221Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.02547","last_updated":"2026-04-17T18:09:08Z","snapshot_observed_at":"2026-08-03T09:07:42.489237Z","submitted_at":"2025-09-02T17:46:26Z","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","version":5},"cited_work":{"arxiv_id":"2509.02547","doi":"10.48550/arxiv.2509.02547","metadata_source":"pith","pith_arxiv_id":"2509.02547","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","venue":"cs.AI","work_id":"87909127-da20-4ccc-8ae3-4a4a20ef81b7","year":2025},"citing_paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-22T06:37:34.840129Z"},"links":{"cited_paper":"/paper/2509.02547","citing_paper":"/paper/2605.21984"},"observation_digest":"sha256:cb67f4b6ff00efa75da21fd77f8d99b9e409b90e5936b86180609f5ba6a3c9b2","observation_id":"279c5188-7d12-4d1c-8ec6-32364f4b2214","resolution":{"observed_at":"2026-05-22T06:41:10.745267Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.21984","last_updated":"2026-05-21T04:34:00Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-02T23:47:40.908968Z","submitted_at":"2026-05-21T04:34:00Z","title":"Echo: Learning from Experience Data via User-Driven Refinement"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":20,"verified_fuzzy":1},"total_outbound_references":22},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2605.21984."}