{"as_of":"2026-08-13T01:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f1cb2c90876e0e8d7a3b70b1dbf03824386c14c4ad5c2dadefa727f11e9d51a4","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":"2026-08-12T06:34:41.77262+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":"2026-08-01T17:41:02.499008Z","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":"2026-05-22T09:01:19.378330Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2604.28123","last_updated":"2026-06-29T08:05:16Z","snapshot_observed_at":"2026-08-10T21:11:23.617148Z","submitted_at":"2026-04-30T17:12:53Z","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","version":3},"cited_work":{"arxiv_id":"2604.28123","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.28123","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","venue":"cs.CV","work_id":"48450ac4-4de3-4ab9-a128-dc1c1d638e03","year":2026},"citing_paper":{"arxiv_id":"2605.20342","last_updated":"2026-05-21T10:36:34Z","snapshot_observed_at":"2026-07-06T23:30:58.549353Z","submitted_at":"2026-05-19T18:01:26Z","title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-21T07:32:12.180233Z"},"links":{"cited_paper":"/paper/2604.28123","citing_paper":"/paper/2605.20342"},"observation_digest":"sha256:84293d23cd9e0b3fc48b57d52659f78f10236f245f40eed6a1ace766a307108c","observation_id":"df693869-c9f7-456a-af36-553ab2adbcb8","resolution":{"observed_at":"2026-05-21T07:34:02.543496Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.28123","last_updated":"2026-06-29T08:05:16Z","snapshot_observed_at":"2026-08-10T21:11:23.617148Z","submitted_at":"2026-04-30T17:12:53Z","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","version":3},"cited_work":{"arxiv_id":"2604.28123","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.28123","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","venue":"cs.CV","work_id":"48450ac4-4de3-4ab9-a128-dc1c1d638e03","year":2026},"citing_paper":{"arxiv_id":"2605.20342","last_updated":"2026-05-21T10:36:34Z","snapshot_observed_at":"2026-07-06T23:30:58.549353Z","submitted_at":"2026-05-19T18:01:26Z","title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-22T08:59:28.405218Z"},"links":{"cited_paper":"/paper/2604.28123","citing_paper":"/paper/2605.20342"},"observation_digest":"sha256:7ac2adf145e8854cee9e8ed2004460cdfb3608183338ac5aa5c8c1d99c6571f9","observation_id":"ee9f4ea0-3d77-455a-9db0-c087dd67995c","resolution":{"observed_at":"2026-05-22T09:01:19.381541Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.28123","last_updated":"2026-06-29T08:05:16Z","snapshot_observed_at":"2026-08-10T21:11:23.617148Z","submitted_at":"2026-04-30T17:12:53Z","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.28123","snapshot_observed_at":"2026-08-01T17:41:02.499008Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17572","last_updated":"2026-07-25T08:59:31Z","snapshot_observed_at":"2026-08-03T13:23:48.122079Z","submitted_at":"2026-07-20T05:30:40Z","title":"JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models","version":3},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-01T17:41:02.499008Z"},"links":{"cited_paper":"/paper/2604.28123","citing_paper":"/paper/2607.17572"},"observation_digest":"sha256:ddad7cd828fa2067d480d3856c396f88a0c39dd04450c04f2f5abab22f54a15f","observation_id":"9df066f1-39af-42f0-8258-929514611308","resolution":{"observed_at":"2026-08-01T17:41:02.499008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2604.28123/citation-record","integrity":"/paper/2604.28123/integrity","json":"/paper/2604.28123/citation-record.json","paper":"/paper/2604.28123"},"outbound":[],"paper":{"arxiv_id":"2604.28123","last_updated":"2026-06-29T08:05:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T21:11:23.617148Z","submitted_at":"2026-04-30T17:12:53Z","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2604.28123."}