{"as_of":"2026-08-13T11:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:30df5c4847b4943cc726f4fb8d9800c05055418e22aa40a54e33a2fe15b63ca9","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":"2026-08-13T06:32:02.005865+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":"2026-08-06T15:08:17.062076Z","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":"2026-08-06T15:08:17.221159Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.01708","last_updated":"2024-08-03T08:25:26Z","snapshot_observed_at":"2026-08-12T23:09:14.256653Z","submitted_at":"2024-08-03T08:25:26Z","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","version":1},"cited_work":{"arxiv_id":"2408.01708","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.01708","snapshot_observed_at":"2026-08-06T15:08:17.221159Z","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","venue":"cs.CV","work_id":"b49a4660-ea30-4e88-9e2a-260d40980a52","year":2024},"citing_paper":{"arxiv_id":"2507.16736","last_updated":"2025-07-22T16:21:32Z","snapshot_observed_at":"2026-08-10T21:27:25.505831Z","submitted_at":"2025-07-22T16:21:32Z","title":"DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T15:08:17.062076Z"},"links":{"cited_paper":"/paper/2408.01708","citing_paper":"/paper/2507.16736"},"observation_digest":"sha256:6f129dfa9305b1c328c14d836df1c6630426730c4c27ccda2eb399ad14fa99c4","observation_id":"a88f623c-48e8-465d-aa97-1869e8388663","resolution":{"observed_at":"2026-08-06T15:08:17.303096Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.01708","last_updated":"2024-08-03T08:25:26Z","snapshot_observed_at":"2026-08-12T23:09:14.256653Z","submitted_at":"2024-08-03T08:25:26Z","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.01708","snapshot_observed_at":"2026-08-03T14:32:00.019011Z","title":"Avesformer: Efficient trans- former design for real-time audio-visual segmentation.arXiv preprint arXiv:2408.01708, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.20117","last_updated":"2026-06-29T07:20:38Z","snapshot_observed_at":"2026-08-03T14:31:55.232086Z","submitted_at":"2025-12-23T07:21:21Z","title":"Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T14:32:00.019011Z"},"links":{"cited_paper":"/paper/2408.01708","citing_paper":"/paper/2512.20117"},"observation_digest":"sha256:af6cc06839240c422a37366105b2550ab5f83197da12c22a46142df048a0acc4","observation_id":"eaa7c24f-d031-4083-b417-1a1cf78f0ec6","resolution":{"observed_at":"2026-08-03T14:32:00.019011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2408.01708/citation-record","integrity":"/paper/2408.01708/integrity","json":"/paper/2408.01708/citation-record.json","paper":"/paper/2408.01708"},"outbound":[],"paper":{"arxiv_id":"2408.01708","last_updated":"2024-08-03T08:25:26Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T23:09:14.256653Z","submitted_at":"2024-08-03T08:25:26Z","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2408.01708."}