{"as_of":"2026-08-09T00:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:33fc8b8e54996a138845134ced34d5b26effe5c2b32a75e52a0f501cb44b4f51","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:34:54.149826Z","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":"2026-05-20T15:13:24.995061Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.02666","last_updated":"2025-08-29T15:47:44Z","snapshot_observed_at":"2026-08-07T15:56:21.317990Z","submitted_at":"2025-05-05T14:15:02Z","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02666","snapshot_observed_at":"2026-08-07T14:34:54.149826Z","title":"A survey on progress in llm alignment from the perspective of reward design.arXiv preprint arXiv:2505.02666, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18531","last_updated":"2025-05-24T05:50:07Z","snapshot_observed_at":"2026-08-08T01:18:16.590508Z","submitted_at":"2025-05-24T05:50:07Z","title":"Generative RLHF-V: Learning Principles from Multi-modal Human Preference","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:34:54.149826Z"},"links":{"cited_paper":"/paper/2505.02666","citing_paper":"/paper/2505.18531"},"observation_digest":"sha256:0e5d93a4adfe4eb3fb8ec4639bc8ab841a08c06dee208122e78828acb9654777","observation_id":"ee03b3fa-d2de-4e87-a295-f23b14920c33","resolution":{"observed_at":"2026-08-07T14:34:54.149826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02666","last_updated":"2025-08-29T15:47:44Z","snapshot_observed_at":"2026-08-07T15:56:21.317990Z","submitted_at":"2025-05-05T14:15:02Z","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02666","snapshot_observed_at":"2026-08-04T16:07:31.458650Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.16679","last_updated":"2025-09-20T13:11:28Z","snapshot_observed_at":"2026-08-04T16:07:24.699834Z","submitted_at":"2025-09-20T13:11:28Z","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-04T16:07:31.458650Z"},"links":{"cited_paper":"/paper/2505.02666","citing_paper":"/paper/2509.16679"},"observation_digest":"sha256:e02ccdb2665af1f969bbd11a5d4137779749ea8b9ab10d69b233b65a7fd30f38","observation_id":"6f62552a-42ae-461a-a31e-025c52a5da8e","resolution":{"observed_at":"2026-08-04T16:07:31.458650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02666","last_updated":"2025-08-29T15:47:44Z","snapshot_observed_at":"2026-08-07T15:56:21.317990Z","submitted_at":"2025-05-05T14:15:02Z","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","version":2},"cited_work":{"arxiv_id":"2505.02666","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.02666","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2505.02666 , year=","venue":null,"work_id":"3b8db2d1-37b0-4908-95fe-d34dee67ae60","year":2025},"citing_paper":{"arxiv_id":"2604.01346","last_updated":"2026-04-06T19:07:02Z","snapshot_observed_at":"2026-08-03T08:33:40.943733Z","submitted_at":"2026-04-01T19:57:33Z","title":"Safety, Security, and Cognitive Risks in World Models","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-13T22:35:46.126714Z"},"links":{"cited_paper":"/paper/2505.02666","citing_paper":"/paper/2604.01346"},"observation_digest":"sha256:9fe5b069077f8a7bd80e3699baff10460a77343cf027aeac2244232010ee398d","observation_id":"8b2e92cf-75a6-4f93-8c34-5cefa1a641c4","resolution":{"observed_at":"2026-05-13T22:38:22.250055Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02666","last_updated":"2025-08-29T15:47:44Z","snapshot_observed_at":"2026-08-07T15:56:21.317990Z","submitted_at":"2025-05-05T14:15:02Z","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","version":2},"cited_work":{"arxiv_id":"2505.02666","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.02666","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2505.02666 , year=","venue":null,"work_id":"3b8db2d1-37b0-4908-95fe-d34dee67ae60","year":2025},"citing_paper":{"arxiv_id":"2605.17458","last_updated":"2026-05-17T14:00:01Z","snapshot_observed_at":"2026-07-06T23:28:26.397778Z","submitted_at":"2026-05-17T14:00:01Z","title":"ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-05-20T15:11:27.420642Z"},"links":{"cited_paper":"/paper/2505.02666","citing_paper":"/paper/2605.17458"},"observation_digest":"sha256:4f6b726212e5064b50f893ec958f922b038d75acac435be54e3dea383bea67c4","observation_id":"a4536758-faa6-4355-8e41-137def431398","resolution":{"observed_at":"2026-05-20T15:13:24.997088Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.02666/citation-record","integrity":"/paper/2505.02666/integrity","json":"/paper/2505.02666/citation-record.json","paper":"/paper/2505.02666"},"outbound":[],"paper":{"arxiv_id":"2505.02666","last_updated":"2025-08-29T15:47:44Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T15:56:21.317990Z","submitted_at":"2025-05-05T14:15:02Z","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2505.02666."}