{"as_of":"2026-08-20T21:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:10a67e265a56ff5943784ade419fad503bead85cdae3a6ca3124a9b5cbfa3faa","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T21:03:13.295499Z","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":"2026-08-07T21:03:13.402174Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1706.05461","last_updated":"2017-07-10T00:44:45Z","snapshot_observed_at":"2026-08-18T19:44:22.990581Z","submitted_at":"2017-06-17T00:39:04Z","title":"Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text","version":3},"cited_work":{"arxiv_id":"1706.05461","doi":null,"metadata_source":"pith","pith_arxiv_id":"1706.05461","snapshot_observed_at":"2026-08-07T21:03:13.402174Z","title":"Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text","venue":"cs.CV","work_id":"413a5862-a12d-4722-a6a7-65e8f0f9766f","year":2017},"citing_paper":{"arxiv_id":"2502.09573","last_updated":"2025-04-25T22:35:16Z","snapshot_observed_at":"2026-08-17T18:18:21.309579Z","submitted_at":"2025-02-13T18:31:17Z","title":"Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T21:03:13.295499Z"},"links":{"cited_paper":"/paper/1706.05461","citing_paper":"/paper/2502.09573"},"observation_digest":"sha256:445aafbfcbb5dfc12ee9681380d90748faef4812e87818ea9087bb452d6e2cb9","observation_id":"be6885a3-3740-4ae4-bd0e-13f3421c0db6","resolution":{"observed_at":"2026-08-07T21:03:13.409766Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1706.05461/citation-record","integrity":"/paper/1706.05461/integrity","json":"/paper/1706.05461/citation-record.json","paper":"/paper/1706.05461"},"outbound":[],"paper":{"arxiv_id":"1706.05461","last_updated":"2017-07-10T00:44:45Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T19:44:22.990581Z","submitted_at":"2017-06-17T00:39:04Z","title":"Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1706.05461."}