{"as_of":"2026-08-08T23:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:71068161fe850c3816143b06debdb17a3d79a8956c7ea1722c20672ed9618296","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:11:08.003956Z","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":"2026-05-17T05:53:26.298633Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.18835","last_updated":"2023-11-30T18:59:51Z","snapshot_observed_at":"2026-07-06T16:55:13.127567Z","submitted_at":"2023-11-30T18:59:51Z","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","version":1},"cited_work":{"arxiv_id":"2311.18835","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.18835","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Instructseq: Unifying vision tasks with instruction-conditioned multi-modal sequence generation","venue":null,"work_id":"6aac037a-ce2c-4853-ada5-4ab1ec49ab8d","year":2023},"citing_paper":{"arxiv_id":"2502.04326","last_updated":"2026-03-01T04:35:41Z","snapshot_observed_at":"2026-07-06T20:32:23.502480Z","submitted_at":"2025-02-06T18:59:40Z","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-17T05:53:26.066674Z"},"links":{"cited_paper":"/paper/2311.18835","citing_paper":"/paper/2502.04326"},"observation_digest":"sha256:28d759f30a63a84cc086b3714bf589c32b3198988b6d2b51dbca192ed076db3c","observation_id":"decfed49-ea61-4acd-9e1f-7c3396f89a33","resolution":{"observed_at":"2026-05-17T05:53:26.301327Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.18835","last_updated":"2023-11-30T18:59:51Z","snapshot_observed_at":"2026-07-06T16:55:13.127567Z","submitted_at":"2023-11-30T18:59:51Z","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.18835","snapshot_observed_at":"2026-08-07T14:11:08.003956Z","title":"Instructseq: Unifying vision tasks with instruction- conditioned multi-modal sequence generation.arXiv preprint arXiv:2311.18835, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.19990","last_updated":"2025-05-28T11:35:26Z","snapshot_observed_at":"2026-08-07T13:59:43.810989Z","submitted_at":"2025-05-26T13:45:27Z","title":"Progressive Scaling Visual Object Tracking","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:11:08.003956Z"},"links":{"cited_paper":"/paper/2311.18835","citing_paper":"/paper/2505.19990"},"observation_digest":"sha256:5be84887c32e9b210e2d1a1a0517d5737c74f74a4dd67b1a9c569f08376249d0","observation_id":"e1f29e1b-1d99-4539-ab8e-1bd3c5a34a20","resolution":{"observed_at":"2026-08-07T14:11:08.003956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.18835","last_updated":"2023-11-30T18:59:51Z","snapshot_observed_at":"2026-07-06T16:55:13.127567Z","submitted_at":"2023-11-30T18:59:51Z","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.18835","snapshot_observed_at":"2026-08-07T14:01:49.041500Z","title":"Instructseq: Unifying vision tasks with instruction-conditioned multi-modal sequence generation.arXiv preprint arXiv:2311.18835, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20199","last_updated":"2025-05-26T16:40:22Z","snapshot_observed_at":"2026-08-07T13:55:14.930246Z","submitted_at":"2025-05-26T16:40:22Z","title":"Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:01:49.041500Z"},"links":{"cited_paper":"/paper/2311.18835","citing_paper":"/paper/2505.20199"},"observation_digest":"sha256:b56f58011b55e1354b02cc8cd21fbd276891aeba499934fae2a0f1a3ccdb0138","observation_id":"3e2aa6d7-ad04-4180-b363-38dd18886222","resolution":{"observed_at":"2026-08-07T14:01:49.041500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.18835/citation-record","integrity":"/paper/2311.18835/integrity","json":"/paper/2311.18835/citation-record.json","paper":"/paper/2311.18835"},"outbound":[],"paper":{"arxiv_id":"2311.18835","last_updated":"2023-11-30T18:59:51Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:55:13.127567Z","submitted_at":"2023-11-30T18:59:51Z","title":"InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2311.18835."}