{"as_of":"2026-08-06T12:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e8fc9e64376b0d48fd9c0b18daff09ff2fe2cb58261d20b93f03a4a2b2a97f0f","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T16:26:34.918099Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T01:37:30.511368Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.02790","last_updated":"2025-01-06T06:17:56Z","snapshot_observed_at":"2026-07-06T20:16:53.338035Z","submitted_at":"2025-01-06T06:17:56Z","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","version":1},"cited_work":{"arxiv_id":"2501.02790","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.02790","snapshot_observed_at":"2026-07-03T01:37:30.511368Z","title":"Segmenting text and learning their rewards for improved rlhf in language model","venue":null,"work_id":"745c87a0-8433-4dc8-a1f0-b6df236314f6","year":2025},"citing_paper":{"arxiv_id":"2604.13602","last_updated":"2026-04-15T08:11:34Z","snapshot_observed_at":"2026-07-06T23:01:32.542040Z","submitted_at":"2026-04-15T08:11:34Z","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","version":1},"reference_index":117,"source":"pdf_text","source_observed_at":"2026-05-10T13:58:53.430492Z"},"links":{"cited_paper":"/paper/2501.02790","citing_paper":"/paper/2604.13602"},"observation_digest":"sha256:52c17c32bee8cb7590d682432ac1cf9d6eee48b9f3970fed80f041a3845f956e","observation_id":"b5923323-4fcb-4b42-9458-093c65a4a7df","resolution":{"observed_at":"2026-05-10T14:00:28.401522Z","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":"2501.02790","last_updated":"2025-01-06T06:17:56Z","snapshot_observed_at":"2026-07-06T20:16:53.338035Z","submitted_at":"2025-01-06T06:17:56Z","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","version":1},"cited_work":{"arxiv_id":"2501.02790","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.02790","snapshot_observed_at":"2026-07-03T01:37:30.511368Z","title":"Segmenting text and learning their rewards for improved rlhf in language model","venue":null,"work_id":"745c87a0-8433-4dc8-a1f0-b6df236314f6","year":2025},"citing_paper":{"arxiv_id":"2604.21160","last_updated":"2026-04-23T00:01:40Z","snapshot_observed_at":"2026-08-03T02:31:06.414610Z","submitted_at":"2026-04-23T00:01:40Z","title":"Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-09T23:00:14.031709Z"},"links":{"cited_paper":"/paper/2501.02790","citing_paper":"/paper/2604.21160"},"observation_digest":"sha256:cd8bbb852054f70912b006e464f81e5589f90c36038f4f1f1124ca324d20398f","observation_id":"35917a05-ad3b-432d-881f-e8f9db0b75b6","resolution":{"observed_at":"2026-05-09T23:04:18.030277Z","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":"2501.02790","last_updated":"2025-01-06T06:17:56Z","snapshot_observed_at":"2026-07-06T20:16:53.338035Z","submitted_at":"2025-01-06T06:17:56Z","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","version":1},"cited_work":{"arxiv_id":"2501.02790","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.02790","snapshot_observed_at":"2026-07-03T01:37:30.511368Z","title":"Segmenting text and learning their rewards for improved rlhf in language model","venue":null,"work_id":"745c87a0-8433-4dc8-a1f0-b6df236314f6","year":2025},"citing_paper":{"arxiv_id":"2606.09711","last_updated":"2026-06-08T16:32:54Z","snapshot_observed_at":"2026-07-06T23:49:03.237958Z","submitted_at":"2026-06-08T16:32:54Z","title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","version":1},"reference_index":151,"source":"arxiv_source","source_observed_at":"2026-06-27T16:26:34.918099Z"},"links":{"cited_paper":"/paper/2501.02790","citing_paper":"/paper/2606.09711"},"observation_digest":"sha256:9f8ac167911fc51a52ee77748ecc783f6f63a0654449358beb643f0c67df1554","observation_id":"26de573c-73ff-40fa-a7b8-64a60a72c502","resolution":{"observed_at":"2026-07-03T01:37:30.512754Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/2501.02790/citation-record","integrity":"/paper/2501.02790/integrity","json":"/paper/2501.02790/citation-record.json","paper":"/paper/2501.02790"},"outbound":[],"paper":{"arxiv_id":"2501.02790","last_updated":"2025-01-06T06:17:56Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T20:16:53.338035Z","submitted_at":"2025-01-06T06:17:56Z","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model"},"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":"2026-08-06T06:34:29.942622+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 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2501.02790."}