{"as_of":"2026-08-18T04:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b18b8e309a4316251741e206f650489936fdceb07048bc2be8260230a121dc75","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":20,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:44:46.598114Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-07T12:33:45.021126Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2402.05070","last_updated":"2024-08-20T19:14:31Z","snapshot_observed_at":"2026-08-14T17:53:51.886327Z","submitted_at":"2024-02-07T18:21:17Z","title":"A Roadmap to Pluralistic Alignment","version":3},"reference_index":279,"source":"arxiv_source","source_observed_at":"2026-05-16T14:37:53.279275Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2402.05070"},"observation_digest":"sha256:90c811286b07619561796119e7ff30b57f07d1e7b6f7e5bf10c515c0a5d75840","observation_id":"4a8f6943-03bf-4117-baa5-36fa9e476602","resolution":{"observed_at":"2026-05-16T14:37:53.483023Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-12T04:35:59.543008Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01233","last_updated":"2024-12-02T07:54:55Z","snapshot_observed_at":"2026-08-15T22:41:09.800294Z","submitted_at":"2024-12-02T07:54:55Z","title":"Best Practices for Large Language Models in Radiology","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-12T04:35:59.543008Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2412.01233"},"observation_digest":"sha256:756620a816b0576256e5d3de16781333ebe0d26f9997a3fc3e68cee1909d8512","observation_id":"f5014e00-5819-44b8-abeb-3b4fe7587bdc","resolution":{"observed_at":"2026-08-12T04:35:59.543008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-11T11:08:56.453684Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.15797","last_updated":"2024-12-20T11:14:29Z","snapshot_observed_at":"2026-08-16T20:47:21.715777Z","submitted_at":"2024-12-20T11:14:29Z","title":"Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T11:08:56.453684Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2412.15797"},"observation_digest":"sha256:6238d206a469b091100262e94470044fc4a26abfc163deb69f232e549ec50d0e","observation_id":"41ebfd6e-55d1-4d26-aa73-a81c4ff590db","resolution":{"observed_at":"2026-08-11T11:08:56.453684Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-10T21:17:48.408445Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.05336","last_updated":"2025-01-09T16:02:51Z","snapshot_observed_at":"2026-08-15T11:21:12.805156Z","submitted_at":"2025-01-09T16:02:51Z","title":"Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T21:17:48.408445Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2501.05336"},"observation_digest":"sha256:1169961fd05c088e0560ec3f919897acbb223e4edb67e233eb02d47da6dc15fa","observation_id":"efdfe643-d800-4bc3-926e-b785708aa619","resolution":{"observed_at":"2026-08-10T21:17:48.408445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-09T14:18:05.620575Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06806","last_updated":"2025-07-12T07:19:28Z","snapshot_observed_at":"2026-08-18T03:37:43.958504Z","submitted_at":"2025-02-03T22:24:22Z","title":"Logits are All We Need to Adapt Closed Models","version":4},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T14:18:05.620575Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2502.06806"},"observation_digest":"sha256:1fd93c732fee577432b0130ac8cec5ccdbca240ff00350e59157ea4c6b866b05","observation_id":"b1a42d7a-320b-4931-8a4a-d2ca0e46e4fa","resolution":{"observed_at":"2026-08-09T14:18:05.620575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-16T10:44:46.598114Z","title":"Tuning language models by proxy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.17421","last_updated":"2026-06-28T12:07:24Z","snapshot_observed_at":"2026-08-17T22:04:11.561702Z","submitted_at":"2025-04-24T10:24:35Z","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","version":2},"reference_index":138,"source":"pdf_text","source_observed_at":"2026-08-16T10:44:46.598114Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2504.17421"},"observation_digest":"sha256:684294a251b0225144d30d842cb47ce76874f63c147bc635641717c56b1e067b","observation_id":"69377ed7-c5cd-44dc-8fc3-e00252a25a9d","resolution":{"observed_at":"2026-08-16T10:44:46.598114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-07T15:37:58.926261Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14436","last_updated":"2025-05-20T14:42:03Z","snapshot_observed_at":"2026-08-14T12:11:12.180698Z","submitted_at":"2025-05-20T14:42:03Z","title":"Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T15:37:58.926261Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2505.14436"},"observation_digest":"sha256:79dc98e04ea617ff5fb6349060b5426f21d4353d116e9e428ddd5ed5e8e63d22","observation_id":"e32aa794-f5d7-4a2e-92c8-0823552377f8","resolution":{"observed_at":"2026-08-07T15:37:58.926261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-07T13:07:49.678073Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.23846","last_updated":"2025-05-28T17:50:01Z","snapshot_observed_at":"2026-08-17T15:50:14.193034Z","submitted_at":"2025-05-28T17:50:01Z","title":"Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:07:49.678073Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2505.23846"},"observation_digest":"sha256:775388956a9683c7bdcc4d53815be0bc7e5e6e5ce039d8afc2727b458898af58","observation_id":"fcb289a6-a2f4-4b35-b02e-0cc2d0a45638","resolution":{"observed_at":"2026-08-07T13:07:49.678073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-06T16:45:58.459933Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.12759","last_updated":"2025-07-17T03:31:36Z","snapshot_observed_at":"2026-08-15T17:16:00.550969Z","submitted_at":"2025-07-17T03:31:36Z","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T16:45:58.459933Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2507.12759"},"observation_digest":"sha256:029a1d022eda60e5835b03d1a3627acc19711836b883f12e31ef8963f5e10d05","observation_id":"48185574-370d-49dd-8c9f-6ea8dab5867c","resolution":{"observed_at":"2026-08-06T16:45:58.459933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-05T21:18:43.942431Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.09016","last_updated":"2025-09-10T05:08:47Z","snapshot_observed_at":"2026-08-09T06:48:43.608452Z","submitted_at":"2025-08-12T15:30:44Z","title":"A Survey on Training-free Alignment of Large Language Models","version":4},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-05T21:18:43.942431Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2508.09016"},"observation_digest":"sha256:62c2f077f5fd906ab4860920ba700d6f2b13a5a187d08640b33d76e59db0b6cd","observation_id":"a3f7c747-c499-49ab-a392-045e562f2926","resolution":{"observed_at":"2026-08-05T21:18:43.942431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2604.06377","last_updated":"2026-05-05T18:37:43Z","snapshot_observed_at":"2026-08-11T13:29:25.505319Z","submitted_at":"2026-04-07T19:02:10Z","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T18:36:44.401045Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2604.06377"},"observation_digest":"sha256:722a0b6363f79f1c72fafd709afc6675770ae5fb2dd8f527744d92e2d22a08ce","observation_id":"0447a07e-40a2-4891-b1f9-d0430be7c590","resolution":{"observed_at":"2026-05-11T00:15:56.453878Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2604.11446","last_updated":"2026-04-13T13:28:12Z","snapshot_observed_at":"2026-08-15T01:35:32.701722Z","submitted_at":"2026-04-13T13:28:12Z","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T16:07:20.180349Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2604.11446"},"observation_digest":"sha256:66c8d13f1e21e3fa356c6bf024c8cd6a0d956e4c12af5b1452ec16e0fa5fcabc","observation_id":"6b425db2-3532-46b7-93d3-477c1b3e4efb","resolution":{"observed_at":"2026-05-11T09:16:04.584157Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2604.15383","last_updated":"2026-04-16T02:30:41Z","snapshot_observed_at":"2026-08-11T04:27:04.271851Z","submitted_at":"2026-04-16T02:30:41Z","title":"Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T10:16:26.526986Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2604.15383"},"observation_digest":"sha256:d05c6e9f74f9dd05fcd34c0b1700f8baa3e8765674166b47eab44b20ca088993","observation_id":"9ad932fa-1dbe-4f2f-a761-b03deac132c5","resolution":{"observed_at":"2026-05-10T10:19:20.680811Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2605.20555","last_updated":"2026-05-19T23:15:18Z","snapshot_observed_at":"2026-08-15T15:49:27.996482Z","submitted_at":"2026-05-19T23:15:18Z","title":"Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-21T06:39:06.365240Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2605.20555"},"observation_digest":"sha256:b7c6e3f1823e441aa5c4f904bf14581e462a6849cb8850206667bb328b1e1cd7","observation_id":"72559b78-756f-4a17-ab44-4b65a2e8e7d7","resolution":{"observed_at":"2026-05-21T06:39:43.651320Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2606.05145","last_updated":"2026-06-03T17:50:26Z","snapshot_observed_at":"2026-08-17T11:27:01.860722Z","submitted_at":"2026-06-03T17:50:26Z","title":"Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-06-28T06:48:28.788806Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2606.05145"},"observation_digest":"sha256:a47a0908fb710c3eca1c15568046b71b45f3ef3feae75666477806d8b405f643","observation_id":"ab6a4246-7973-4358-8b72-a7543faf22f8","resolution":{"observed_at":"2026-07-02T07:46:45.672823Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":"2401.08565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-07T12:33:45.021126Z","title":"2401.08565 , archiveprefix =","venue":"cs.CL","work_id":"61c14142-6e00-4fc0-87aa-2ba793c4b9b8","year":2024},"citing_paper":{"arxiv_id":"2607.05394","last_updated":"2026-07-08T17:57:18Z","snapshot_observed_at":"2026-08-02T11:12:50.300654Z","submitted_at":"2026-07-06T17:59:58Z","title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","version":1},"reference_index":110,"source":"pdf_text","source_observed_at":"2026-07-07T12:31:42.224094Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2607.05394"},"observation_digest":"sha256:088ccc9f664fb15f2fa17461317d4606820e224c4dc565d0ad81ec21768292a6","observation_id":"cde6781f-db19-42ab-8564-a536ac633c9c","resolution":{"observed_at":"2026-07-07T12:33:45.022809Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-11T07:01:56.628017Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.05394","last_updated":"2026-07-08T17:57:18Z","snapshot_observed_at":"2026-08-02T11:12:50.300654Z","submitted_at":"2026-07-06T17:59:58Z","title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","version":2},"reference_index":106,"source":"pdf_text","source_observed_at":"2026-07-11T07:01:56.628017Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2607.05394"},"observation_digest":"sha256:963d9076827b3adfa2b6f9ddda1fe8748c173fee502e4afb4a9f326e81e0fbdb","observation_id":"1957543d-eade-4ff2-8eb8-308fa5535ebc","resolution":{"observed_at":"2026-07-11T07:01:56.628017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-07-14T05:09:00.865375Z","title":"Tuning language models by proxy.arXiv preprint arXiv:2401.08565, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.11505","last_updated":"2026-07-13T12:56:21Z","snapshot_observed_at":"2026-08-15T06:15:17.745652Z","submitted_at":"2026-07-13T12:56:21Z","title":"Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T05:09:00.865375Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2607.11505"},"observation_digest":"sha256:2d0365f02473ab2dac7c311f78e48d12ba3bca0b1e4b1edaec4048c407934ffb","observation_id":"9780541d-452f-4e6e-86cf-3b72c5293382","resolution":{"observed_at":"2026-07-14T05:09:00.865375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-01T00:26:23.349392Z","title":"arXiv preprint arXiv:2401.08565 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26246","last_updated":"2026-07-28T20:31:48Z","snapshot_observed_at":"2026-08-12T12:03:15.179459Z","submitted_at":"2026-07-28T20:31:48Z","title":"Weak-to-Strong On-Policy Distillation","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-01T00:26:23.349392Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2607.26246"},"observation_digest":"sha256:ee372a0f7fbafb90b787512177fcb004d404376eb3063375bc79290880e9dab2","observation_id":"8d2eae3d-df45-4cb0-b8b3-41f5bfc8df15","resolution":{"observed_at":"2026-08-01T00:26:23.349392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08565","snapshot_observed_at":"2026-08-15T20:49:47.311952Z","title":"Smith , title =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.12913","last_updated":"2026-08-13T07:56:16Z","snapshot_observed_at":"2026-08-16T23:11:16.712466Z","submitted_at":"2026-08-13T07:56:16Z","title":"Decoupled Contrastive Decoding via Expert-Aligned Drafting","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-15T20:49:47.311952Z"},"links":{"cited_paper":"/paper/2401.08565","citing_paper":"/paper/2608.12913"},"observation_digest":"sha256:cf55854a187f4670922526ea29f6b2e6aab2ff84b0fe7bbc3926ad183da3885e","observation_id":"0854683a-1627-4ed5-b620-9a39239e3261","resolution":{"observed_at":"2026-08-15T20:49:47.311952Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2401.08565/citation-record","integrity":"/paper/2401.08565/integrity","json":"/paper/2401.08565/citation-record.json","paper":"/paper/2401.08565"},"outbound":[],"paper":{"arxiv_id":"2401.08565","last_updated":"2024-08-23T05:21:44Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:27:01.586325Z","submitted_at":"2024-01-16T18:49:55Z","title":"Tuning Language Models by Proxy"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2401.08565."}