{"as_of":"2026-08-05T14:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:894530d5163fa4ddaef83eb842d68a59b6ed8ff16669d52ade3657af99c8a0ea","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-03T21:31:31.831806Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+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/2607.01232/citation-record","integrity":"/paper/2607.01232/integrity","json":"/paper/2607.01232/citation-record.json","paper":"/paper/2607.01232"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.10978","last_updated":"2025-10-28T15:11:36Z","snapshot_observed_at":"2026-07-29T19:20:21.974239Z","submitted_at":"2025-05-16T08:26:59Z","title":"Group-in-Group Policy Optimization for LLM Agent Training","version":3},"cited_work":{"arxiv_id":"2505.10978","doi":"10.48550/arxiv.2505.10978","metadata_source":"pith","pith_arxiv_id":"2505.10978","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Group-in-Group Policy Optimization for LLM Agent Training","venue":"cs.LG","work_id":"bc65d492-e6ba-4522-874c-43d2f4fc5191","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2505.10978","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:26704f4aac101a3552e1ed95038fc99771ce0b429f44fd43a97ee63a0eea1ade","observation_id":"08e4578a-29a2-4a68-869d-b50b05ecec62","resolution":{"observed_at":"2026-07-03T21:38:58.218916Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.12228","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T21:38:58.223615Z","title":"arXiv preprint arXiv:2603.12228 , year=","venue":null,"work_id":"4c6f6214-fded-4960-a687-a6e433a3ff39","year":2026},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:14530a9edc0d5f34bcb37d4d0051339d619607cc8841203dbc72caa9623d9db7","observation_id":"87e7d526-e2d1-4913-ae10-4e5456e6b594","resolution":{"observed_at":"2026-07-03T21:38:58.225176Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41586-025-09422-z","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T03:06:43.562716Z","title":"doi: 10.1038/s41586-025-09422-z","venue":"Nature","work_id":"9835b482-5032-4135-93dd-82a066677569","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:d761a9a547e60a6418a81b128bc02e8badf0fc2d176851d0b783033fc16dba68","observation_id":"388bc0d0-f8e6-4930-8b8e-daa21d6ba12c","resolution":{"observed_at":"2026-07-03T21:38:58.143642Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-03T22:08:21.094896+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T22:08:21.094896+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22312","last_updated":"2025-05-29T09:07:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-28T12:56:04Z","title":"Skywork Open Reasoner 1 Technical Report","version":2},"cited_work":{"arxiv_id":"2505.22312","doi":"10.48550/arxiv.2505.22312","metadata_source":"pith","pith_arxiv_id":"2505.22312","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Skywork Open Reasoner 1 Technical Report","venue":"cs.LG","work_id":"27740ebb-6704-4ef9-8878-5b81d4269869","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2505.22312","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:4630d5289ea32db49f97698ea98bdf1b8484a2484673a7d89a0ca39fbcba61d2","observation_id":"5f6cbcb8-cba1-474f-83df-b75394535779","resolution":{"observed_at":"2026-07-03T21:38:58.231652Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2512.15764","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T21:38:58.232438Z","title":null,"venue":null,"work_id":"263801e7-bc3a-4e17-8207-109b94d445d2","year":null},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:4816ad0a2f252c78c2215aa96302c56d69f2fdec9df9dbeab77d91166b039be6","observation_id":"15dc8aef-0ff7-47d8-898c-b591865c5069","resolution":{"observed_at":"2026-07-03T21:38:58.233859Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2511.00056","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T21:38:58.240174Z","title":"Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin","venue":null,"work_id":"0865ecf6-a598-41b9-b6ab-9c753ef60266","year":null},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:6ea253f9303f676ef2f4eced7cb5b444670921dcc6067ac1547ca0b1293b5aea","observation_id":"2536fceb-2d62-4ee3-9e29-945a7be7f1a9","resolution":{"observed_at":"2026-07-03T21:38:58.241686Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2506.22638","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T21:38:58.237605Z","title":"Layer importance for mathematical reasoning is forged in pre-training and invariant after post-training.arXiv preprint arXiv:2506.22638","venue":null,"work_id":"04831b81-1ce5-454a-b711-347b64ffe40b","year":null},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:85f91a259c5fb799cfbc95ee2ee06f4b83f130d5a0bb50c9310d289f285bbebb","observation_id":"62079cd2-02a8-44bf-9a90-cab3dea7f5fb","resolution":{"observed_at":"2026-07-03T21:38:58.239083Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":"2402.03300","doi":"10.1016/0004-3702(73)90011-8","metadata_source":"pith","pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","venue":"cs.CL","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":2024},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:eae86743cf326936c209a2373c5fbdb34389d76cdcffc6b6e023404ec2323b70","observation_id":"95811a6e-b862-4222-9363-0b890c83df91","resolution":{"observed_at":"2026-07-03T21:38:58.209283Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17875","last_updated":"2025-04-08T09:44:28Z","snapshot_observed_at":"2026-07-06T19:38:26.783620Z","submitted_at":"2024-10-23T13:47:05Z","title":"Understanding Layer Significance in LLM Alignment","version":3},"cited_work":{"arxiv_id":"2410.17875","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.17875","snapshot_observed_at":"2026-07-03T21:38:58.237859Z","title":"Understanding layer significance in llm alignment","venue":null,"work_id":"9592f0ce-5147-4358-8b98-4d2491b0e47d","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2410.17875","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:7661cb5882b7f4573de778e23d94ca6e9d47d65e558b29a4d062d827f756de66","observation_id":"8e9ae075-ee0c-4bb8-b5e5-a9566785ca00","resolution":{"observed_at":"2026-07-03T21:38:58.239487Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-06T00:11:39.666358Z","title":null,"venue":null,"work_id":"6a826020-7d7c-4151-b545-20427fc11944","year":2010},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:569ed5f7e312781ad8c646131f711593a906b1e5053a73739970e69b7ac1e761","observation_id":"9c18fd4d-62d5-431e-88ff-a5ba265b9917","resolution":{"observed_at":"2026-07-05T01:00:30.250735Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.02091","doi":"10.48550/arxiv.2510.02091","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"arXiv preprint arXiv:2510.02091 , year=","venue":null,"work_id":"760b6456-9bc5-4c5f-91f2-d6d02f61cdd6","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:1c2255e1237e9abb24b49b707bb5c652ae639572a4fd2553807a67eb22f181fe","observation_id":"4e855d53-d7e1-4176-9827-72c390d4802b","resolution":{"observed_at":"2026-07-03T21:38:58.225399Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":"2203.11171","doi":"10.1101/2025.04.03.646459","metadata_source":"pith","pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","venue":"cs.CL","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","year":2022},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:97c7d498f9ca2eacb51c8d8966544d238637afd1cd5681a3860c7ce52c324496","observation_id":"22579516-6af9-4851-aa97-2cc6017ab972","resolution":{"observed_at":"2026-07-03T21:38:58.236761Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:4d9b1cd6915012ca324268d186471f211a532d2af49935f8e1170aaafbe7f67d","observation_id":"f5022f28-e4a1-489c-8732-60ba8d263ba7","resolution":{"observed_at":"2026-07-03T21:38:58.234321Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14476","last_updated":"2025-05-20T01:37:34Z","snapshot_observed_at":"2026-08-02T01:40:54.187278Z","submitted_at":"2025-03-18T17:49:06Z","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","version":2},"cited_work":{"arxiv_id":"2503.14476","doi":"10.48550/arxiv.2503.14476","metadata_source":"pith","pith_arxiv_id":"2503.14476","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","venue":"cs.LG","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2503.14476","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:ddec1b23b89110ea3eb8dcf49c361c8fc06d28db7247c6ddb065fc658abbedc1","observation_id":"774f8104-9ddf-4b0a-9b99-0bf396d4da7b","resolution":{"observed_at":"2026-07-03T21:38:58.236451Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-24T09:23:06.254602+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T09:23:06.254602+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14381","last_updated":"2024-09-22T09:53:13Z","snapshot_observed_at":"2026-07-06T19:19:24.759288Z","submitted_at":"2024-09-22T09:53:13Z","title":"Investigating Layer Importance in Large Language Models","version":1},"cited_work":{"arxiv_id":"2409.14381","doi":"10.48550/arxiv.2409.14381","metadata_source":"arxiv_reference","pith_arxiv_id":"2409.14381","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Investigating layer importance in large language models","venue":"arXiv (Cornell University)","work_id":"fb01382b-98f8-4afa-8754-5530ed413f06","year":2025},"citing_paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-03T21:31:31.831806Z"},"links":{"cited_paper":"/paper/2409.14381","citing_paper":"/paper/2607.01232"},"observation_digest":"sha256:70220001b1cc210d0e0786d0843d03e4b05bc24a04f76006a9f78a3b89378787","observation_id":"863f83a1-83b8-42c2-a51a-3190a8161e1d","resolution":{"observed_at":"2026-07-03T21:38:58.228463Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.01232","last_updated":"2026-07-02T17:28:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T22:18:25.858077Z","submitted_at":"2026-07-01T17:59:54Z","title":"Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":1,"metadata_mismatch":8,"parse_uncertain":0,"unresolved":1,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":15},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2607.01232."}