{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MRMXTXHTNDNOAS55OXDE66V3MG","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":"444ac3cc1075efc2b45dd7cf878d038cfaaf2c4e9e86ec101feb91d014a960bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T02:43:53Z","title_canon_sha256":"78ee5b76de1b588fc2e784d1bae9721c24bd634df0660255956adc96a725290f"},"schema_version":"1.0","source":{"id":"2506.16701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16701","created_at":"2026-07-05T11:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16701v1","created_at":"2026-07-05T11:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16701","created_at":"2026-07-05T11:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"MRMXTXHTNDNO","created_at":"2026-07-05T11:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"MRMXTXHTNDNOAS55","created_at":"2026-07-05T11:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"MRMXTXHT","created_at":"2026-07-05T11:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:c84da37c58158f5dd4bd7ecc39d06e6ee6a31874c36ab843c658fa67692b8ead","target":"graph","created_at":"2026-07-05T11:24:41Z","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/2506.16701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that humans use to constitute an understanding of objects, human-object interactions, and activities - that have not been fully exploited. In this paper, we introduce a framework incorporating language-driven common sense priors to identify cluttered video action sequences from monocular views that are often heavily occluded. We propose: (1) A video context summary c","authors_text":"Chuhang Zou, Jaechul Kim, Narendra Ahuja, Suchen Wang, Xiaodan Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T02:43:53Z","title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16701","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":"sha256:584f28092aa34460fe98297f75094be2d1c6aeae3c184dc8f67d42ee1a8c4620","target":"record","created_at":"2026-07-05T11:24:41Z","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":"444ac3cc1075efc2b45dd7cf878d038cfaaf2c4e9e86ec101feb91d014a960bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T02:43:53Z","title_canon_sha256":"78ee5b76de1b588fc2e784d1bae9721c24bd634df0660255956adc96a725290f"},"schema_version":"1.0","source":{"id":"2506.16701","kind":"arxiv","version":1}},"canonical_sha256":"645979dcf368dae04bbd75c64f7abb61a32a1bf4173854d0846decde98a4f42c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"645979dcf368dae04bbd75c64f7abb61a32a1bf4173854d0846decde98a4f42c","first_computed_at":"2026-07-05T11:24:41.277381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:41.277381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zVO7AMxR6Xhkn5u8CcCPCPoSbF/We7ctTR8YExP5EKlTOqZr5fdc/4yqAntvuk2SDsgibDYR2Sb+T1NijiwMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:41.277887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:584f28092aa34460fe98297f75094be2d1c6aeae3c184dc8f67d42ee1a8c4620","sha256:c84da37c58158f5dd4bd7ecc39d06e6ee6a31874c36ab843c658fa67692b8ead"],"state_sha256":"74f8cfd37e65a5888a3d8cec9a2a534ca18662c85763ee4072bf84e6ac52e35e"}