{"as_of":"2026-08-08T06:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:00486a6f23c64e755ae5e75313114f59fa61549b9b0e3cc81e40cecefb7a96e1","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":"2026-08-08T06:32:00.761636+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":"2026-08-03T20:23:03.468092Z","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":"2026-06-29T00:02:50.367534Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.07999","last_updated":"2020-10-15T19:56:47Z","snapshot_observed_at":"2026-08-06T22:24:57.346555Z","submitted_at":"2020-10-15T19:56:47Z","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","version":1},"cited_work":{"arxiv_id":"2010.07999","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.07999","snapshot_observed_at":"2026-06-29T00:02:50.367534Z","title":"arXiv preprint arXiv:2010.07999 (2020)","venue":null,"work_id":"f3d20ef4-7491-467f-b582-cb7c09692d65","year":2010},"citing_paper":{"arxiv_id":"2204.00598","last_updated":"2022-05-27T17:52:50Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-01T17:43:13Z","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-16T09:50:00.546571Z"},"links":{"cited_paper":"/paper/2010.07999","citing_paper":"/paper/2204.00598"},"observation_digest":"sha256:30aa2fe4f44e66525e56f09f0debcec3578aeab801b36374934a495066e6cf5e","observation_id":"9477c127-d44f-4bdb-917c-f7a180aa6b77","resolution":{"observed_at":"2026-05-16T09:50:00.745593Z","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":"2010.07999","last_updated":"2020-10-15T19:56:47Z","snapshot_observed_at":"2026-08-06T22:24:57.346555Z","submitted_at":"2020-10-15T19:56:47Z","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.07999","snapshot_observed_at":"2026-08-03T20:23:03.468092Z","title":"What is more likely to happen next? video-and-language future event prediction.arXiv preprint arXiv:2010.07999,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2511.20272","last_updated":"2026-07-03T06:27:17Z","snapshot_observed_at":"2026-08-03T20:22:57.328566Z","submitted_at":"2025-11-25T12:58:32Z","title":"VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T20:23:03.468092Z"},"links":{"cited_paper":"/paper/2010.07999","citing_paper":"/paper/2511.20272"},"observation_digest":"sha256:90693e978f9a5cf9f69fe74400feacf85050dc51d538febd9d33e4d3da9ebba2","observation_id":"d511dc7e-7895-4907-9c2b-c3b73d49c0dd","resolution":{"observed_at":"2026-08-03T20:23:03.468092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.07999","last_updated":"2020-10-15T19:56:47Z","snapshot_observed_at":"2026-08-06T22:24:57.346555Z","submitted_at":"2020-10-15T19:56:47Z","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","version":1},"cited_work":{"arxiv_id":"2010.07999","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.07999","snapshot_observed_at":"2026-06-29T00:02:50.367534Z","title":"arXiv preprint arXiv:2010.07999 (2020)","venue":null,"work_id":"f3d20ef4-7491-467f-b582-cb7c09692d65","year":2010},"citing_paper":{"arxiv_id":"2605.31069","last_updated":"2026-05-29T09:38:43Z","snapshot_observed_at":"2026-08-07T07:32:37.435310Z","submitted_at":"2026-05-29T09:38:43Z","title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T23:16:42.001361Z"},"links":{"cited_paper":"/paper/2010.07999","citing_paper":"/paper/2605.31069"},"observation_digest":"sha256:84b9f65e9b1394221f9a6ce7042b69705c83b07d78fcbaa46204fd008dbbed47","observation_id":"033c1df6-e4df-4cc8-bc32-2caa3818711f","resolution":{"observed_at":"2026-06-29T00:02:50.368907Z","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/2010.07999/citation-record","integrity":"/paper/2010.07999/integrity","json":"/paper/2010.07999/citation-record.json","paper":"/paper/2010.07999"},"outbound":[],"paper":{"arxiv_id":"2010.07999","last_updated":"2020-10-15T19:56:47Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T22:24:57.346555Z","submitted_at":"2020-10-15T19:56:47Z","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction"},"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 3 inbound Pith citation observations for arXiv:2010.07999."}