{"as_of":"2026-08-08T04:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:650926e329e973c6db30bd9c0e15a1bc32c9976cace45e00678ff80afffd58fd","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T05:49:53.561200Z","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":"2026-08-06T18:44:54.549994Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.12423","last_updated":"2024-06-19T22:20:40Z","snapshot_observed_at":"2026-07-06T17:05:27.005904Z","submitted_at":"2023-12-19T18:53:01Z","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12423","snapshot_observed_at":"2026-08-07T05:49:53.561200Z","title":"Jack of all tasks, master of many: Designing general-purpose coarse-to-fine vision-language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07016","last_updated":"2025-06-13T19:05:47Z","snapshot_observed_at":"2026-08-07T11:48:30.543139Z","submitted_at":"2025-06-08T06:34:29Z","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","version":2},"reference_index":110,"source":"pdf_text","source_observed_at":"2026-08-07T05:49:53.561200Z"},"links":{"cited_paper":"/paper/2312.12423","citing_paper":"/paper/2506.07016"},"observation_digest":"sha256:c80e38b3a6f88bcaa24e9f26b3d50f6117aa71a1b0b0e52761cbcc9b60d04696","observation_id":"f46c4f5b-6f22-451a-b49f-263f50a3fd1c","resolution":{"observed_at":"2026-08-07T05:49:53.561200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12423","last_updated":"2024-06-19T22:20:40Z","snapshot_observed_at":"2026-07-06T17:05:27.005904Z","submitted_at":"2023-12-19T18:53:01Z","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12423","snapshot_observed_at":"2026-08-06T22:41:11.061406Z","title":"Jack of all tasks, master of many: Designing general-purpose coarse-to-fine vision- language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21080","last_updated":"2025-06-26T08:09:16Z","snapshot_observed_at":"2026-08-07T17:47:39.726590Z","submitted_at":"2025-06-26T08:09:16Z","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T22:41:11.061406Z"},"links":{"cited_paper":"/paper/2312.12423","citing_paper":"/paper/2506.21080"},"observation_digest":"sha256:e5d31bb5a6a51c5e6b8e3bb2d504304a99a7e13df1c5fe74b7ac2a0e22d3cbba","observation_id":"6226041d-62b7-4d13-82ff-75218f735c81","resolution":{"observed_at":"2026-08-06T22:41:11.061406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12423","last_updated":"2024-06-19T22:20:40Z","snapshot_observed_at":"2026-07-06T17:05:27.005904Z","submitted_at":"2023-12-19T18:53:01Z","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","version":2},"cited_work":{"arxiv_id":"2312.12423","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.12423","snapshot_observed_at":"2026-08-06T18:44:54.549994Z","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","venue":"cs.CV","work_id":"0edd3769-7de6-4073-a34a-2476f539431e","year":2023},"citing_paper":{"arxiv_id":"2608.04698","last_updated":"2026-08-05T11:07:22Z","snapshot_observed_at":"2026-08-08T03:11:44.919049Z","submitted_at":"2026-08-05T11:07:22Z","title":"Teaching MLLMs to Say No: Generalized Referring Expression Comprehension via Refusal Calibrated GRPO","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T18:44:46.348688Z"},"links":{"cited_paper":"/paper/2312.12423","citing_paper":"/paper/2608.04698"},"observation_digest":"sha256:d219b4373d3453e4671f7c317bdcf8fc8668b3a585076bc8129decb7cbb7b6b1","observation_id":"aa5a5238-fd1f-413c-a830-951424b64e50","resolution":{"observed_at":"2026-08-06T18:44:54.593433Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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/2312.12423/citation-record","integrity":"/paper/2312.12423/integrity","json":"/paper/2312.12423/citation-record.json","paper":"/paper/2312.12423"},"outbound":[],"paper":{"arxiv_id":"2312.12423","last_updated":"2024-06-19T22:20:40Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:05:27.005904Z","submitted_at":"2023-12-19T18:53:01Z","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model"},"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 3 inbound Pith citation observations for arXiv:2312.12423."}