{"as_of":"2026-08-08T02:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:81a85e9435f2721e2ce72f0e8c90e828ac786213fc4061c7061398102a6f8038","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T14:11:40.911809Z","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":"2026-08-07T12:09:11.789944Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.08723","last_updated":"2022-10-17T16:27:09Z","snapshot_observed_at":"2026-07-06T12:19:25.743466Z","submitted_at":"2021-12-16T09:21:18Z","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.08723","snapshot_observed_at":"2026-08-07T14:11:40.911809Z","title":"arXiv preprint arXiv:2112.08723 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.19849","last_updated":"2025-08-02T00:31:18Z","snapshot_observed_at":"2026-08-07T14:03:04.066911Z","submitted_at":"2025-05-26T11:35:04Z","title":"HIT Model: A Hierarchical Interaction-Enhanced Two-Tower Model for Pre-Ranking Systems","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T14:11:40.911809Z"},"links":{"cited_paper":"/paper/2112.08723","citing_paper":"/paper/2505.19849"},"observation_digest":"sha256:5611acb4ea54c78f9ea382d070f232c08f978413ff9a8b4d073fd302a4e59c88","observation_id":"526f8695-ce91-4902-b56c-2febef92932f","resolution":{"observed_at":"2026-08-07T14:11:40.911809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.08723","last_updated":"2022-10-17T16:27:09Z","snapshot_observed_at":"2026-07-06T12:19:25.743466Z","submitted_at":"2021-12-16T09:21:18Z","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","version":2},"cited_work":{"arxiv_id":"2112.08723","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.08723","snapshot_observed_at":"2026-08-07T12:09:11.789944Z","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","venue":"cs.CL","work_id":"f5198516-2426-4c6b-998e-4c081fe13468","year":2021},"citing_paper":{"arxiv_id":"2506.00479","last_updated":"2025-05-31T09:10:43Z","snapshot_observed_at":"2026-08-07T12:02:00.195241Z","submitted_at":"2025-05-31T09:10:43Z","title":"EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T12:09:09.309361Z"},"links":{"cited_paper":"/paper/2112.08723","citing_paper":"/paper/2506.00479"},"observation_digest":"sha256:676a22bb41eefd9eed281d38349698f5af996b2edefab26ce04d62a4cbd11db4","observation_id":"02d43063-5dfa-4778-8c3a-a58d4b5a1cd2","resolution":{"observed_at":"2026-08-07T12:09:11.842112Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2112.08723/citation-record","integrity":"/paper/2112.08723/integrity","json":"/paper/2112.08723/citation-record.json","paper":"/paper/2112.08723"},"outbound":[],"paper":{"arxiv_id":"2112.08723","last_updated":"2022-10-17T16:27:09Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T12:19:25.743466Z","submitted_at":"2021-12-16T09:21:18Z","title":"Distilled Dual-Encoder Model for Vision-Language Understanding"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2112.08723."}