{"as_of":"2026-08-08T17:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:97fe0bcd1b575e0e9e1725c3a5e85e002c6f631d34dc0b42c194edcca383fd75","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:23:12.555613Z","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":"2026-07-02T12:46:56.770108Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.00161","last_updated":"2025-03-30T14:31:41Z","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T11:54:55Z","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00161","snapshot_observed_at":"2026-08-07T10:23:12.555613Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05501","last_updated":"2025-06-05T18:36:33Z","snapshot_observed_at":"2026-08-07T20:35:29.372904Z","submitted_at":"2025-06-05T18:36:33Z","title":"FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T10:23:12.555613Z"},"links":{"cited_paper":"/paper/2412.00161","citing_paper":"/paper/2506.05501"},"observation_digest":"sha256:f9498e5185726f2d45661f44d8f1508c3403504325c4d8c537ec335e7613c262","observation_id":"c139af4a-b154-427e-9360-3ae217bb71dd","resolution":{"observed_at":"2026-08-07T10:23:12.555613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00161","last_updated":"2025-03-30T14:31:41Z","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T11:54:55Z","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","version":2},"cited_work":{"arxiv_id":"2412.00161","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.00161","snapshot_observed_at":"2026-07-02T12:46:56.770108Z","title":null,"venue":null,"work_id":"e44d4e78-49c4-43f3-9eb5-3e24a58f60bd","year":2025},"citing_paper":{"arxiv_id":"2606.05736","last_updated":"2026-06-04T05:55:15Z","snapshot_observed_at":"2026-07-06T23:45:42.379051Z","submitted_at":"2026-06-04T05:55:15Z","title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T01:52:44.785582Z"},"links":{"cited_paper":"/paper/2412.00161","citing_paper":"/paper/2606.05736"},"observation_digest":"sha256:45bbb8ebf454f054fe0de6324b1cc6cf706352d66714059d52614b56240d3757","observation_id":"ad8db802-3408-4c6c-b710-e779351b9078","resolution":{"observed_at":"2026-07-02T12:46:56.771532Z","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/2412.00161/citation-record","integrity":"/paper/2412.00161/integrity","json":"/paper/2412.00161/citation-record.json","paper":"/paper/2412.00161"},"outbound":[],"paper":{"arxiv_id":"2412.00161","last_updated":"2025-03-30T14:31:41Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:59:11.046948Z","submitted_at":"2024-11-29T11:54:55Z","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.00161."}