{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CBRSP5MCOAQBJPE2FFBN4NW7JX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3cd639ff54dcb69a0fd51207e1beba2a5623b916bce428027701259ec3d300a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-20T16:04:05Z","title_canon_sha256":"ae680e40a5a6da5651a0e177ca2dab5419b46410b69d0d4cb5520239e186075a"},"schema_version":"1.0","source":{"id":"1812.08658","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.08658","created_at":"2026-07-05T01:16:07Z"},{"alias_kind":"arxiv_version","alias_value":"1812.08658v3","created_at":"2026-07-05T01:16:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08658","created_at":"2026-07-05T01:16:07Z"},{"alias_kind":"pith_short_12","alias_value":"CBRSP5MCOAQB","created_at":"2026-07-05T01:16:07Z"},{"alias_kind":"pith_short_16","alias_value":"CBRSP5MCOAQBJPE2","created_at":"2026-07-05T01:16:07Z"},{"alias_kind":"pith_short_8","alias_value":"CBRSP5MC","created_at":"2026-07-05T01:16:07Z"}],"graph_snapshots":[{"event_id":"sha256:1eb40dc43010602514885b33cc898b92dd1e1055903b16df34ae886e33a79500","target":"graph","created_at":"2026-07-05T01:16:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1812.08658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less supervision. To encourage the development of image captioning models that can learn visual concepts from alternative data sources, such as object detection datasets, we present the first large-scale benchmark for this task. Dubbed 'nocaps', for novel object captioning at scale, our benchmark consists of","authors_text":"Devi Parikh, Dhruv Batra, Harsh Agrawal, Karan Desai, Mark Johnson, Peter Anderson, Rishabh Jain, Stefan Lee, Xinlei Chen, Yufei Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-20T16:04:05Z","title":"nocaps: novel object captioning at scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08658","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1cc04b7e02e68d3032f93141d73f5593d62fd77c490669f9e15e44fee00e0c33","target":"record","created_at":"2026-07-05T01:16:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3cd639ff54dcb69a0fd51207e1beba2a5623b916bce428027701259ec3d300a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-20T16:04:05Z","title_canon_sha256":"ae680e40a5a6da5651a0e177ca2dab5419b46410b69d0d4cb5520239e186075a"},"schema_version":"1.0","source":{"id":"1812.08658","kind":"arxiv","version":3}},"canonical_sha256":"106327f582702014bc9a2942de36df4de33ec44662c206cb8dd33dccfa2948b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"106327f582702014bc9a2942de36df4de33ec44662c206cb8dd33dccfa2948b0","first_computed_at":"2026-07-05T01:16:07.930646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:07.930646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Ijwn1/nMw2auyVzPWkXh6Vnsn6hrJdFnTXB5X7WYVQTq1L+Do8NaQjJ6w6qYIt+TiMsgnaad6znf6YlwLmaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:07.931116Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.08658","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cc04b7e02e68d3032f93141d73f5593d62fd77c490669f9e15e44fee00e0c33","sha256:1eb40dc43010602514885b33cc898b92dd1e1055903b16df34ae886e33a79500"],"state_sha256":"cb34da10cf30c2412edd8fe14381129310d145b9f5d57a00a8044234c02ac701"}