{"as_of":"2026-08-13T03:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:396472d55c2b0db34a352dfdb91f8ad2841e9a39acef9af89cc7af86ab470837","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T12:47:17.345702Z","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":"2026-05-11T20:46:13.589892Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1708.01641","last_updated":"2017-08-04T18:57:52Z","snapshot_observed_at":"2026-08-07T11:53:24.167018Z","submitted_at":"2017-08-04T18:57:52Z","title":"Localizing Moments in Video with Natural Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.01641","snapshot_observed_at":"2026-08-11T12:47:17.345702Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.13845","last_updated":"2025-02-24T03:37:59Z","snapshot_observed_at":"2026-08-11T14:35:32.643550Z","submitted_at":"2024-12-18T13:38:06Z","title":"Do Language Models Understand Time?","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T12:47:17.345702Z"},"links":{"cited_paper":"/paper/1708.01641","citing_paper":"/paper/2412.13845"},"observation_digest":"sha256:c536731ccb930409dc7835e26a1a59488deb6658bdee32b1b16a013be1e20feb","observation_id":"d98d0760-e99f-4f4b-95cf-b737423006b9","resolution":{"observed_at":"2026-08-11T12:47:17.345702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.01641","last_updated":"2017-08-04T18:57:52Z","snapshot_observed_at":"2026-08-07T11:53:24.167018Z","submitted_at":"2017-08-04T18:57:52Z","title":"Localizing Moments in Video with Natural Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.01641","snapshot_observed_at":"2026-08-07T11:26:13.424298Z","title":"A.; Wang, O.; Shechtman, E.; Sivic, J.; Darrell, T.; and Russell, B","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02448","last_updated":"2025-06-03T05:12:48Z","snapshot_observed_at":"2026-08-09T22:02:05.904966Z","submitted_at":"2025-06-03T05:12:48Z","title":"VidEvent: A Large Dataset for Understanding Dynamic Evolution of Events in Videos","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T11:26:13.424298Z"},"links":{"cited_paper":"/paper/1708.01641","citing_paper":"/paper/2506.02448"},"observation_digest":"sha256:6538ea37aeb5f22b86e41998079ddd190f1392d5f593c78b8f2fa01756b97519","observation_id":"82a166ee-239b-4fe5-afe9-e358b162ea9a","resolution":{"observed_at":"2026-08-07T11:26:13.424298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.01641","last_updated":"2017-08-04T18:57:52Z","snapshot_observed_at":"2026-08-07T11:53:24.167018Z","submitted_at":"2017-08-04T18:57:52Z","title":"Localizing Moments in Video with Natural Language","version":1},"cited_work":{"arxiv_id":"1708.01641","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1708.01641","snapshot_observed_at":"2026-07-04T22:06:58.751821Z","title":null,"venue":null,"work_id":"4fba7254-4558-4da9-929c-9e8df737aef0","year":2017},"citing_paper":{"arxiv_id":"2604.23198","last_updated":"2026-04-25T08:09:31Z","snapshot_observed_at":"2026-08-10T23:28:22.417916Z","submitted_at":"2026-04-25T08:09:31Z","title":"StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-08T08:04:15.238840Z"},"links":{"cited_paper":"/paper/1708.01641","citing_paper":"/paper/2604.23198"},"observation_digest":"sha256:8d57c4a5f78db1ec40724a5f68bc386f17bed688623936df805b4ce3809ab65b","observation_id":"edf1b84f-16b8-4360-ad6d-c45d1a51f2be","resolution":{"observed_at":"2026-07-04T22:06:58.751821Z","resolver_source":"arxiv_id","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":"1708.01641","last_updated":"2017-08-04T18:57:52Z","snapshot_observed_at":"2026-08-07T11:53:24.167018Z","submitted_at":"2017-08-04T18:57:52Z","title":"Localizing Moments in Video with Natural Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.01641","snapshot_observed_at":"2026-08-01T18:04:12.732459Z","title":"Localizing moments in video with natural language, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.17423","last_updated":"2026-07-19T22:04:33Z","snapshot_observed_at":"2026-08-05T19:15:04.907010Z","submitted_at":"2026-07-19T22:04:33Z","title":"TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T18:04:12.732459Z"},"links":{"cited_paper":"/paper/1708.01641","citing_paper":"/paper/2607.17423"},"observation_digest":"sha256:a784c068fdaeba295c713c0e9b04c0c8a9e1b0eabcfc7c5befa18c796a9fec2f","observation_id":"139f3aab-6821-4eeb-b534-d7e821f6df95","resolution":{"observed_at":"2026-08-01T18:04:12.732459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1708.01641/citation-record","integrity":"/paper/1708.01641/integrity","json":"/paper/1708.01641/citation-record.json","paper":"/paper/1708.01641"},"outbound":[],"paper":{"arxiv_id":"1708.01641","last_updated":"2017-08-04T18:57:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T11:53:24.167018Z","submitted_at":"2017-08-04T18:57:52Z","title":"Localizing Moments in Video with Natural Language"},"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 4 inbound Pith citation observations for arXiv:1708.01641."}