{"as_of":"2026-08-08T15:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c63f69f0c10f238a93494ac5e5712827e8afb61877e45781d8806a1a4af7608d","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":"2026-08-05T10:58:16.959800Z","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":"2026-05-16T16:35:38.017184Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.13681","last_updated":"2022-02-18T05:50:50Z","snapshot_observed_at":"2026-08-05T16:29:39.348508Z","submitted_at":"2020-11-27T11:43:45Z","title":"Point and Ask: Incorporating Pointing into Visual Question Answering","version":4},"cited_work":{"arxiv_id":"2011.13681","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.13681","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point and ask: Incorporating pointing into vi- sual question answering","venue":null,"work_id":"6d179202-83f7-4f97-ad9b-26a8568517e6","year":2011},"citing_paper":{"arxiv_id":"2309.17421","last_updated":"2023-10-11T05:07:37Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-29T17:34:51Z","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-05-15T23:26:06.183574Z"},"links":{"cited_paper":"/paper/2011.13681","citing_paper":"/paper/2309.17421"},"observation_digest":"sha256:cc7d184562a981d1abdceb1ce15f692e8d12c7d73f6cb66677b3b09602cc69fa","observation_id":"f99e145e-68d4-4204-8212-b550b2da62d4","resolution":{"observed_at":"2026-05-15T23:26:06.376986Z","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":"2011.13681","last_updated":"2022-02-18T05:50:50Z","snapshot_observed_at":"2026-08-05T16:29:39.348508Z","submitted_at":"2020-11-27T11:43:45Z","title":"Point and Ask: Incorporating Pointing into Visual Question Answering","version":4},"cited_work":{"arxiv_id":"2011.13681","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.13681","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point and ask: Incorporating pointing into vi- sual question answering","venue":null,"work_id":"6d179202-83f7-4f97-ad9b-26a8568517e6","year":2011},"citing_paper":{"arxiv_id":"2312.16886","last_updated":"2023-12-30T04:59:21Z","snapshot_observed_at":"2026-07-29T22:12:01.108911Z","submitted_at":"2023-12-28T08:21:24Z","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-05-16T16:35:37.937462Z"},"links":{"cited_paper":"/paper/2011.13681","citing_paper":"/paper/2312.16886"},"observation_digest":"sha256:13483f02978e7fa9660c14c04b9a4761973e95606e099f680f89d541c3b13dc3","observation_id":"1ca7654c-62d6-4396-b761-4f444b76aa15","resolution":{"observed_at":"2026-05-16T16:35:38.019655Z","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":"2011.13681","last_updated":"2022-02-18T05:50:50Z","snapshot_observed_at":"2026-08-05T16:29:39.348508Z","submitted_at":"2020-11-27T11:43:45Z","title":"Point and Ask: Incorporating Pointing into Visual Question Answering","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13681","snapshot_observed_at":"2026-08-05T10:58:16.959800Z","title":"Point and ask: Incorporating pointing into visual question answering","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.03501","last_updated":"2025-09-03T17:33:20Z","snapshot_observed_at":"2026-08-07T14:11:47.550063Z","submitted_at":"2025-09-03T17:33:20Z","title":"Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T10:58:16.959800Z"},"links":{"cited_paper":"/paper/2011.13681","citing_paper":"/paper/2509.03501"},"observation_digest":"sha256:62ca330302331bc44484f80b2747a6f1593ec4c38eae16ec5db9e4bd1eb90a66","observation_id":"bd380dbb-488a-4b83-8b6c-16e9af6165b4","resolution":{"observed_at":"2026-08-05T10:58:16.959800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2011.13681/citation-record","integrity":"/paper/2011.13681/integrity","json":"/paper/2011.13681/citation-record.json","paper":"/paper/2011.13681"},"outbound":[],"paper":{"arxiv_id":"2011.13681","last_updated":"2022-02-18T05:50:50Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T16:29:39.348508Z","submitted_at":"2020-11-27T11:43:45Z","title":"Point and Ask: Incorporating Pointing into Visual Question Answering"},"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:2011.13681."}