{"as_of":"2026-08-15T22:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8cc2f88778ae141c701187e1944d9c92488e21dcfdcf8daf6f1e2aeb7bccf96e","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":"2026-08-15T06:32:42.880941+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":"2026-08-14T14:33:31.509614Z","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":"2026-08-14T10:24:04.497929Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1506.06272","last_updated":"2015-06-20T17:25:38Z","snapshot_observed_at":"2026-08-14T22:43:38.021954Z","submitted_at":"2015-06-20T17:25:38Z","title":"Aligning where to see and what to tell: image caption with region-based attention and scene factorization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.06272","snapshot_observed_at":"2026-08-14T14:33:31.509614Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.02923","last_updated":"2020-04-15T02:01:07Z","snapshot_observed_at":"2026-08-15T08:20:11.207619Z","submitted_at":"2019-08-08T04:07:39Z","title":"Image Captioning using Facial Expression and Attention","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-14T14:33:31.509614Z"},"links":{"cited_paper":"/paper/1506.06272","citing_paper":"/paper/1908.02923"},"observation_digest":"sha256:55fdc9ca973c6e7d0129d4c5e97a81359dd41f34a011cdd3a5173240192cf9ae","observation_id":"7a07c55a-0a78-46d3-8fca-b4c851a7dcc4","resolution":{"observed_at":"2026-08-14T14:33:31.509614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.06272","last_updated":"2015-06-20T17:25:38Z","snapshot_observed_at":"2026-08-14T22:43:38.021954Z","submitted_at":"2015-06-20T17:25:38Z","title":"Aligning where to see and what to tell: image caption with region-based attention and scene factorization","version":1},"cited_work":{"arxiv_id":"1506.06272","doi":null,"metadata_source":"pith","pith_arxiv_id":"1506.06272","snapshot_observed_at":"2026-08-14T10:24:04.497929Z","title":"Aligning where to see and what to tell: image caption with region-based attention and scene factorization","venue":"cs.CV","work_id":"bbd3a833-f995-456a-9beb-da1c61fb9606","year":2015},"citing_paper":{"arxiv_id":"1908.11310","last_updated":"2019-08-29T15:50:28Z","snapshot_observed_at":"2026-08-15T12:47:07.687597Z","submitted_at":"2019-08-29T15:50:28Z","title":"Aesthetic Image Captioning From Weakly-Labelled Photographs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T10:24:04.242861Z"},"links":{"cited_paper":"/paper/1506.06272","citing_paper":"/paper/1908.11310"},"observation_digest":"sha256:42463949c93ee3014128cf0287177a5bd7b8a5d772b9bc819d2ec36a1deb115a","observation_id":"c0b7c5fd-4dd8-45ae-aa33-81386a6a2014","resolution":{"observed_at":"2026-08-14T10:24:04.504036Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1506.06272/citation-record","integrity":"/paper/1506.06272/integrity","json":"/paper/1506.06272/citation-record.json","paper":"/paper/1506.06272"},"outbound":[],"paper":{"arxiv_id":"1506.06272","last_updated":"2015-06-20T17:25:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T22:43:38.021954Z","submitted_at":"2015-06-20T17:25:38Z","title":"Aligning where to see and what to tell: image caption with region-based attention and scene factorization"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1506.06272."}