{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TF7M26FLTA7FZNPS4ZGMPFMSC4","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":"119ab0fcac050249d0d7ac437e39a4e8b7837fcb2dee28b6c59d59be9f7cb731","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-06T12:11:43Z","title_canon_sha256":"760713fab31e90350c967cffa31f26afcda776eae26562b1df95b37ffa03a796"},"schema_version":"1.0","source":{"id":"2509.05695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05695","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05695v1","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05695","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"TF7M26FLTA7F","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"TF7M26FLTA7FZNPS","created_at":"2026-07-05T12:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"TF7M26FL","created_at":"2026-07-05T12:06:22Z"}],"graph_snapshots":[{"event_id":"sha256:4b6a67c84a0d30e86b5ca4fe40f7decf3701936eab25ce003445e5fccb4598e6","target":"graph","created_at":"2026-07-05T12:06:22Z","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/2509.05695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human action recognition often struggles with deep semantic understanding, complex contextual information, and fine-grained distinction, limitations that traditional methods frequently encounter when dealing with diverse video data. Inspired by the remarkable capabilities of large language models, this paper introduces LVLM-VAR, a novel framework that pioneers the application of pre-trained Vision-Language Large Models (LVLMs) to video action recognition, emphasizing enhanced accuracy and interpretability. Our method features a Video-to-Semantic-Tokens (VST) Module, which innovatively transfor","authors_text":"Boyu Jin, Jingwei Peng, Surasakdi Siripong, Zhixuan Qiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-06T12:11:43Z","title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05695","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":"sha256:7c2db5f3fc3a2615d344040284ba10ebc59945b3178e768cb01ec232f9065bb4","target":"record","created_at":"2026-07-05T12:06:22Z","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":"119ab0fcac050249d0d7ac437e39a4e8b7837fcb2dee28b6c59d59be9f7cb731","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-06T12:11:43Z","title_canon_sha256":"760713fab31e90350c967cffa31f26afcda776eae26562b1df95b37ffa03a796"},"schema_version":"1.0","source":{"id":"2509.05695","kind":"arxiv","version":1}},"canonical_sha256":"997ecd78ab983e5cb5f2e64cc79592172cb1cd7ba3783f5e9c2ca8d37e2b58f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"997ecd78ab983e5cb5f2e64cc79592172cb1cd7ba3783f5e9c2ca8d37e2b58f3","first_computed_at":"2026-07-05T12:06:22.547897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:22.547897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sXWbePR1ZIqX5acWGjQbjCmCYLrFk/3ysxpD22LPSAhAzKcPYQJ44snPH7MAXvJg9T3xBrJtCVw/BuMALKy3Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:22.548272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c2db5f3fc3a2615d344040284ba10ebc59945b3178e768cb01ec232f9065bb4","sha256:4b6a67c84a0d30e86b5ca4fe40f7decf3701936eab25ce003445e5fccb4598e6"],"state_sha256":"1c17fc52bcd4b7fe20a86c0222a1d25fd655760632543327e0e86ed58c16e006"}