{"as_of":"2026-08-09T06:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0a0efaa4d30fab86eadfb421bbe3722f452d61449c06a48483e7e6ea78c490d5","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:03:20.260110Z","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":"2026-05-18T14:41:30.171123Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.13115","last_updated":"2023-03-29T18:26:34Z","snapshot_observed_at":"2026-08-08T21:30:42.058320Z","submitted_at":"2022-05-26T02:46:09Z","title":"Fine-grained Image Captioning with CLIP Reward","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.13115","snapshot_observed_at":"2026-08-07T15:03:20.260110Z","title":"Fine- grained image captioning with clip reward.arXiv preprint arXiv:2205.13115, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16652","last_updated":"2025-06-07T18:03:28Z","snapshot_observed_at":"2026-08-07T23:38:06.220698Z","submitted_at":"2025-05-22T13:19:57Z","title":"Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:03:20.260110Z"},"links":{"cited_paper":"/paper/2205.13115","citing_paper":"/paper/2505.16652"},"observation_digest":"sha256:161ad73cc4feb736742c73aa563661a3f1a49f734ec9f4bbfa96ac891aa92e20","observation_id":"983bf124-daaa-4ea4-b362-a13ce4860e92","resolution":{"observed_at":"2026-08-07T15:03:20.260110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.13115","last_updated":"2023-03-29T18:26:34Z","snapshot_observed_at":"2026-08-08T21:30:42.058320Z","submitted_at":"2022-05-26T02:46:09Z","title":"Fine-grained Image Captioning with CLIP Reward","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.13115","snapshot_observed_at":"2026-08-07T00:58:06.678094Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.12411","last_updated":"2025-06-14T09:08:34Z","snapshot_observed_at":"2026-08-08T14:12:42.435678Z","submitted_at":"2025-06-14T09:08:34Z","title":"InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:06.678094Z"},"links":{"cited_paper":"/paper/2205.13115","citing_paper":"/paper/2506.12411"},"observation_digest":"sha256:2ddc1c007a2ad2b00149e9cdfbadb7a645fbb752fac09c66bfdf9b5e374cb542","observation_id":"276f4202-75b9-43d5-b962-9ca78f2917a6","resolution":{"observed_at":"2026-08-07T00:58:06.678094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.13115","last_updated":"2023-03-29T18:26:34Z","snapshot_observed_at":"2026-08-08T21:30:42.058320Z","submitted_at":"2022-05-26T02:46:09Z","title":"Fine-grained Image Captioning with CLIP Reward","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.13115","snapshot_observed_at":"2026-08-06T05:04:22.275679Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02419","last_updated":"2025-08-04T13:40:59Z","snapshot_observed_at":"2026-08-09T04:34:42.470802Z","submitted_at":"2025-08-04T13:40:59Z","title":"Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T05:04:22.275679Z"},"links":{"cited_paper":"/paper/2205.13115","citing_paper":"/paper/2508.02419"},"observation_digest":"sha256:fb613bde1ed6342d85c1e2cc0b76f8a0587e42b907719cd94bc3dc164755d5a5","observation_id":"fae5e868-8fd5-43e6-92a9-ed7f29afb72c","resolution":{"observed_at":"2026-08-06T05:04:22.275679Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.13115","last_updated":"2023-03-29T18:26:34Z","snapshot_observed_at":"2026-08-08T21:30:42.058320Z","submitted_at":"2022-05-26T02:46:09Z","title":"Fine-grained Image Captioning with CLIP Reward","version":2},"cited_work":{"arxiv_id":"2205.13115","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.13115","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fine-grained image captioning with clip reward","venue":null,"work_id":"a292fa5c-e5fc-4d8e-8969-2fbe8dd4bcc0","year":2022},"citing_paper":{"arxiv_id":"2509.19207","last_updated":"2026-05-12T09:10:11Z","snapshot_observed_at":"2026-07-31T23:01:48.318669Z","submitted_at":"2025-09-23T16:28:51Z","title":"Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T14:41:20.403259Z"},"links":{"cited_paper":"/paper/2205.13115","citing_paper":"/paper/2509.19207"},"observation_digest":"sha256:2d76596bd9edd94a98f2e0768d8b988443a7648d88120841678f19c80dd32144","observation_id":"9fd07743-f4d3-4744-b35b-0ba5248616c4","resolution":{"observed_at":"2026-05-18T14:41:30.173527Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2205.13115/citation-record","integrity":"/paper/2205.13115/integrity","json":"/paper/2205.13115/citation-record.json","paper":"/paper/2205.13115"},"outbound":[],"paper":{"arxiv_id":"2205.13115","last_updated":"2023-03-29T18:26:34Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T21:30:42.058320Z","submitted_at":"2022-05-26T02:46:09Z","title":"Fine-grained Image Captioning with CLIP Reward"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2205.13115."}