{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FDBBIDFAVDBI3WYVJCCJL4YRFE","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":"2208f780574a3c8c3ac81e50377f55cb128520a248c60a56c94968c790950463","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T21:42:40Z","title_canon_sha256":"58f0b2eff84d792a6db57ffa9b134b606fbce94aca5bd4d35a2c2628ee829048"},"schema_version":"1.0","source":{"id":"2303.14829","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14829","created_at":"2026-07-05T06:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14829v2","created_at":"2026-07-05T06:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14829","created_at":"2026-07-05T06:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"FDBBIDFAVDBI","created_at":"2026-07-05T06:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"FDBBIDFAVDBI3WYV","created_at":"2026-07-05T06:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"FDBBIDFA","created_at":"2026-07-05T06:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:e6a1bfea0dd333052d57b297b2accf8584a352a566cb26d3357ff0e80b87990f","target":"graph","created_at":"2026-07-05T06:17:49Z","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/2303.14829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating grammatically and semantically correct captions in video captioning is a challenging task. The captions generated from the existing methods are either word-by-word that do not align with grammatical structure or miss key information from the input videos. To address these issues, we introduce a novel global-local fusion network, with a Global-Local Fusion Block (GLFB) that encodes and fuses features from different parts of speech (POS) components with visual-spatial features. We use novel combinations of different POS components - 'determinant + subject', 'auxiliary verb', 'verb', a","authors_text":"Adrian Hilton, Armin Mustafa, Asmar Nadeem, Graham Thomas, Robert Dawes","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T21:42:40Z","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14829","kind":"arxiv","version":2},"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":"sha256:8b631a03f32d541c0b624fe0a68e02e5dc3fda4b54b04eaec56f79bd7ef7d0d1","target":"record","created_at":"2026-07-05T06:17:49Z","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":"2208f780574a3c8c3ac81e50377f55cb128520a248c60a56c94968c790950463","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T21:42:40Z","title_canon_sha256":"58f0b2eff84d792a6db57ffa9b134b606fbce94aca5bd4d35a2c2628ee829048"},"schema_version":"1.0","source":{"id":"2303.14829","kind":"arxiv","version":2}},"canonical_sha256":"28c2140ca0a8c28ddb15488495f311291d8d2235ae9711321064bfd8eb20b7db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28c2140ca0a8c28ddb15488495f311291d8d2235ae9711321064bfd8eb20b7db","first_computed_at":"2026-07-05T06:17:49.061484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:49.061484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IXz1CnKrMQnuP/AQRw5KJte0908/TKE8QZtBD4K+NKJpeZDzAmmC8BtsK3UnupFeuGFGUzpjKZvfZ3Gt2umuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:49.061904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14829","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b631a03f32d541c0b624fe0a68e02e5dc3fda4b54b04eaec56f79bd7ef7d0d1","sha256:e6a1bfea0dd333052d57b297b2accf8584a352a566cb26d3357ff0e80b87990f"],"state_sha256":"c4db3e61f15fba19ecec3cb9b06738b1055a97817ebe0c4ef24fca23b0018f13"}