{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TF7M26FLTA7FZNPS4ZGMPFMSC4","short_pith_number":"pith:TF7M26FL","schema_version":"1.0","canonical_sha256":"997ecd78ab983e5cb5f2e64cc79592172cb1cd7ba3783f5e9c2ca8d37e2b58f3","source":{"kind":"arxiv","id":"2509.05695","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyu Jin, Jingwei Peng, Surasakdi Siripong, Zhixuan Qiu","submitted_at":"2025-09-06T12:11:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.05695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-06T12:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"760713fab31e90350c967cffa31f26afcda776eae26562b1df95b37ffa03a796","abstract_canon_sha256":"119ab0fcac050249d0d7ac437e39a4e8b7837fcb2dee28b6c59d59be9f7cb731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:22.548272Z","signature_b64":"sXWbePR1ZIqX5acWGjQbjCmCYLrFk/3ysxpD22LPSAhAzKcPYQJ44snPH7MAXvJg9T3xBrJtCVw/BuMALKy3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"997ecd78ab983e5cb5f2e64cc79592172cb1cd7ba3783f5e9c2ca8d37e2b58f3","last_reissued_at":"2026-07-05T12:06:22.547897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:22.547897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boyu Jin, Jingwei Peng, Surasakdi Siripong, Zhixuan Qiu","submitted_at":"2025-09-06T12:11:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05695","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.05695/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.05695","created_at":"2026-07-05T12:06:22.547948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05695v1","created_at":"2026-07-05T12:06:22.547948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05695","created_at":"2026-07-05T12:06:22.547948+00:00"},{"alias_kind":"pith_short_12","alias_value":"TF7M26FLTA7F","created_at":"2026-07-05T12:06:22.547948+00:00"},{"alias_kind":"pith_short_16","alias_value":"TF7M26FLTA7FZNPS","created_at":"2026-07-05T12:06:22.547948+00:00"},{"alias_kind":"pith_short_8","alias_value":"TF7M26FL","created_at":"2026-07-05T12:06:22.547948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4","json":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4.json","graph_json":"https://pith.science/api/pith-number/TF7M26FLTA7FZNPS4ZGMPFMSC4/graph.json","events_json":"https://pith.science/api/pith-number/TF7M26FLTA7FZNPS4ZGMPFMSC4/events.json","paper":"https://pith.science/paper/TF7M26FL"},"agent_actions":{"view_html":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4","download_json":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4.json","view_paper":"https://pith.science/paper/TF7M26FL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05695&json=true","fetch_graph":"https://pith.science/api/pith-number/TF7M26FLTA7FZNPS4ZGMPFMSC4/graph.json","fetch_events":"https://pith.science/api/pith-number/TF7M26FLTA7FZNPS4ZGMPFMSC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4/action/storage_attestation","attest_author":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4/action/author_attestation","sign_citation":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4/action/citation_signature","submit_replication":"https://pith.science/pith/TF7M26FLTA7FZNPS4ZGMPFMSC4/action/replication_record"}},"created_at":"2026-07-05T12:06:22.547948+00:00","updated_at":"2026-07-05T12:06:22.547948+00:00"}