{"as_of":"2026-08-11T19:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ba827d55967f48583fba045367c9b8f64d05f8107b1c40872fb1b233f752ac0f","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":"2026-08-11T06:34:44.6726+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":"2026-08-10T22:06:47.567202Z","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":"2026-06-28T23:32:46.903689Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.06398","last_updated":"2021-09-14T02:02:36Z","snapshot_observed_at":"2026-07-06T11:47:24.136683Z","submitted_at":"2021-09-14T02:02:36Z","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","version":1},"cited_work":{"arxiv_id":"2109.06398","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.06398","snapshot_observed_at":"2026-06-28T23:32:46.903689Z","title":"InEuropean Conference on Com- puter Vision, pages 447–463","venue":null,"work_id":"c3e217e7-cb25-4260-8455-da3a3a84145e","year":2023},"citing_paper":{"arxiv_id":"2412.07157","last_updated":"2026-04-26T01:56:27Z","snapshot_observed_at":"2026-07-06T20:04:25.198952Z","submitted_at":"2024-12-10T03:34:56Z","title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-23T07:29:46.573683Z"},"links":{"cited_paper":"/paper/2109.06398","citing_paper":"/paper/2412.07157"},"observation_digest":"sha256:57fc5d9331f078e84524b29f0cc6b10fc2fb007ecb3b6ec64e74d05fcc05a761","observation_id":"cf35b4a5-24b4-4621-bc53-0236d1f20fa8","resolution":{"observed_at":"2026-05-23T07:32:43.105772Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06398","last_updated":"2021-09-14T02:02:36Z","snapshot_observed_at":"2026-07-06T11:47:24.136683Z","submitted_at":"2021-09-14T02:02:36Z","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.06398","snapshot_observed_at":"2026-08-10T22:06:47.567202Z","title":"Adaptive proposal generation network for temporal sentence localization in videos","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.02811","last_updated":"2025-04-22T06:27:44Z","snapshot_observed_at":"2026-08-11T16:53:38.990258Z","submitted_at":"2025-01-06T07:20:36Z","title":"First-place Solution for Streetscape Shop Sign Recognition Competition","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T22:06:47.567202Z"},"links":{"cited_paper":"/paper/2109.06398","citing_paper":"/paper/2501.02811"},"observation_digest":"sha256:ddf267dc18c118c9f32fc2e7a2a010f7bf7b69fe501d92f1e94bd6ad89e7f539","observation_id":"67e9516f-9fd2-401a-a1fa-52b46beca460","resolution":{"observed_at":"2026-08-10T22:06:47.567202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06398","last_updated":"2021-09-14T02:02:36Z","snapshot_observed_at":"2026-07-06T11:47:24.136683Z","submitted_at":"2021-09-14T02:02:36Z","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","version":1},"cited_work":{"arxiv_id":"2109.06398","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.06398","snapshot_observed_at":"2026-06-28T23:32:46.903689Z","title":"InEuropean Conference on Com- puter Vision, pages 447–463","venue":null,"work_id":"c3e217e7-cb25-4260-8455-da3a3a84145e","year":2023},"citing_paper":{"arxiv_id":"2605.30742","last_updated":"2026-05-29T02:16:11Z","snapshot_observed_at":"2026-08-09T06:15:54.969301Z","submitted_at":"2026-05-29T02:16:11Z","title":"Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T23:31:33.099164Z"},"links":{"cited_paper":"/paper/2109.06398","citing_paper":"/paper/2605.30742"},"observation_digest":"sha256:a2666e62533cede2d371f65bd56df221cbf7fade5a85d84a460ced0f08023285","observation_id":"3bb42465-9d27-47bb-b08f-8c81a9fcf83c","resolution":{"observed_at":"2026-06-28T23:32:46.905087Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.06398/citation-record","integrity":"/paper/2109.06398/integrity","json":"/paper/2109.06398/citation-record.json","paper":"/paper/2109.06398"},"outbound":[],"paper":{"arxiv_id":"2109.06398","last_updated":"2021-09-14T02:02:36Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T11:47:24.136683Z","submitted_at":"2021-09-14T02:02:36Z","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2109.06398."}