{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2IZSRPKYJ5MYBCVBRFC26RZPQT","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":"d2788eaa1ec8583307202050861ee203686d2b36d569a506f45dc01439dde3f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-22T15:30:54Z","title_canon_sha256":"3ee017f47af96d191717a8362669a250a911a3ac4381297f529b751de608c896"},"schema_version":"1.0","source":{"id":"2304.11431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11431","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11431v1","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11431","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"2IZSRPKYJ5MY","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"2IZSRPKYJ5MYBCVB","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"2IZSRPKY","created_at":"2026-07-05T06:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:4c4e3f3260a249debe2e2e3b0cf7874f978ddd671ee7507f2c9f05eba09ccaa6","target":"graph","created_at":"2026-07-05T06:03:32Z","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/2304.11431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning (VC) is a fast-moving, cross-disciplinary area of research that bridges work in the fields of computer vision, natural language processing (NLP), linguistics, and human-computer interaction. In essence, VC involves understanding a video and describing it with language. Captioning is used in a host of applications from creating more accessible interfaces (e.g., low-vision navigation) to video question answering (V-QA), video retrieval and content generation. This survey covers deep learning-based VC, including but, not limited to, attention-based architectures, graph networks, ","authors_text":"Abbas Khosravi, Abduallah Mohamed, Daniel McDuff, Erik Cambria, Farhad Pourpanah, Fatih Porikli, Meenakshi Kollati, Mohammad Ghavamzadeh, Moloud Abdar, Shuicheng Yan, Swaraja Kuraparthi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-22T15:30:54Z","title":"A Review of Deep Learning for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11431","kind":"arxiv","version":1},"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":"sha256:1970a844c8b7c0b063517295ca5c966101afffa0237392799df8f54e7bf7714f","target":"record","created_at":"2026-07-05T06:03:32Z","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":"d2788eaa1ec8583307202050861ee203686d2b36d569a506f45dc01439dde3f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-22T15:30:54Z","title_canon_sha256":"3ee017f47af96d191717a8362669a250a911a3ac4381297f529b751de608c896"},"schema_version":"1.0","source":{"id":"2304.11431","kind":"arxiv","version":1}},"canonical_sha256":"d23328bd584f59808aa18945af472f84d23448382976b6d5a7a886ba41e00db7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d23328bd584f59808aa18945af472f84d23448382976b6d5a7a886ba41e00db7","first_computed_at":"2026-07-05T06:03:32.643234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:32.643234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J2ZbzHRPSxDRkgQeTdqUdbaaxlW0tqr1Cly3tPubW5QxQB21W7t6V2gB3MIL9ZeVJF+1GeEkSwnmQpkNWunbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:32.643670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1970a844c8b7c0b063517295ca5c966101afffa0237392799df8f54e7bf7714f","sha256:4c4e3f3260a249debe2e2e3b0cf7874f978ddd671ee7507f2c9f05eba09ccaa6"],"state_sha256":"b82ce11d2250e706ca76bbc51ca7f0fbf513ebae84aa76d8a16d37a9ab66cbcb"}