{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H2PKJ5YOJ4534MQ5JHJ2HFPNX3","short_pith_number":"pith:H2PKJ5YO","canonical_record":{"source":{"id":"2503.18407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T07:27:19Z","cross_cats_sorted":[],"title_canon_sha256":"7c1ee120677c59de456358e4d64eeecd64c679861ae25755ce15d4d3fab9bcf6","abstract_canon_sha256":"3167b91a015a5ef2b8fa73fbf62b46488af3daf8a5fcfd4121ee6609b923fd6c"},"schema_version":"1.0"},"canonical_sha256":"3e9ea4f70e4f3bbe321d49d3a395edbec3cdb840ba536a3ab85c285bd6c9777a","source":{"kind":"arxiv","id":"2503.18407","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18407","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18407v2","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18407","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"H2PKJ5YOJ453","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"H2PKJ5YOJ4534MQ5","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"H2PKJ5YO","created_at":"2026-07-05T10:38:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H2PKJ5YOJ4534MQ5JHJ2HFPNX3","target":"record","payload":{"canonical_record":{"source":{"id":"2503.18407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T07:27:19Z","cross_cats_sorted":[],"title_canon_sha256":"7c1ee120677c59de456358e4d64eeecd64c679861ae25755ce15d4d3fab9bcf6","abstract_canon_sha256":"3167b91a015a5ef2b8fa73fbf62b46488af3daf8a5fcfd4121ee6609b923fd6c"},"schema_version":"1.0"},"canonical_sha256":"3e9ea4f70e4f3bbe321d49d3a395edbec3cdb840ba536a3ab85c285bd6c9777a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:46.087851Z","signature_b64":"4NDeaGhweBVHGs+F1QCujwHJZYB05zDMwJ+s2FHtBdJ2bMdOKKm5ZvOIPu8f3pXw+AcZiqUYGIYp4IXMPFLNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e9ea4f70e4f3bbe321d49d3a395edbec3cdb840ba536a3ab85c285bd6c9777a","last_reissued_at":"2026-07-05T10:38:46.087364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:46.087364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.18407","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jxylcjRIwTHoWkcaMsarbQg/JXq2nBb/6hhxZL3tcpNLQbLUmmdXplwwCFCveJnKDDE5CPXn3ulnXEyGQ8rBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:51:04.888023Z"},"content_sha256":"e4d8579f22260b85eeecd492819921bed9d77f077dc9dd810efc69796747e400","schema_version":"1.0","event_id":"sha256:e4d8579f22260b85eeecd492819921bed9d77f077dc9dd810efc69796747e400"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H2PKJ5YOJ4534MQ5JHJ2HFPNX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VTD-CLIP: Video-to-Text Discretization via Prompting CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxuan Li, Pengfei Zhu, Qinghua Hu, Wencheng Zhu, Yuexin Wang","submitted_at":"2025-03-24T07:27:19Z","abstract_excerpt":"Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they often suffer from limited interpretability and poor generalization due to inadequate temporal modeling. To address these, we propose a simple yet effective video-to-text discretization framework. Our method repurposes the frozen text encoder to construct a visual codebook from video class labels due to the many-to-one contrastive alignment between visual and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18407","kind":"arxiv","version":2},"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/2503.18407/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtX6rntxivHHUiNeuD9Eo11vgIAW3hZvQFPOcK46fcZfMc+2PqpyZVFN3U0tFovleT6OOOBRaWHOXWSnLDCYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T17:51:04.888534Z"},"content_sha256":"36002a21be1bc6f436bcec984ca76dfce7671662b6dd38cf3d9b55f3cc813559","schema_version":"1.0","event_id":"sha256:36002a21be1bc6f436bcec984ca76dfce7671662b6dd38cf3d9b55f3cc813559"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3/bundle.json","state_url":"https://pith.science/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T17:51:04Z","links":{"resolver":"https://pith.science/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3","bundle":"https://pith.science/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3/bundle.json","state":"https://pith.science/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2PKJ5YOJ4534MQ5JHJ2HFPNX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H2PKJ5YOJ4534MQ5JHJ2HFPNX3","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":"3167b91a015a5ef2b8fa73fbf62b46488af3daf8a5fcfd4121ee6609b923fd6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T07:27:19Z","title_canon_sha256":"7c1ee120677c59de456358e4d64eeecd64c679861ae25755ce15d4d3fab9bcf6"},"schema_version":"1.0","source":{"id":"2503.18407","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18407","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18407v2","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18407","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"H2PKJ5YOJ453","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"H2PKJ5YOJ4534MQ5","created_at":"2026-07-05T10:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"H2PKJ5YO","created_at":"2026-07-05T10:38:46Z"}],"graph_snapshots":[{"event_id":"sha256:36002a21be1bc6f436bcec984ca76dfce7671662b6dd38cf3d9b55f3cc813559","target":"graph","created_at":"2026-07-05T10:38:46Z","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/2503.18407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they often suffer from limited interpretability and poor generalization due to inadequate temporal modeling. To address these, we propose a simple yet effective video-to-text discretization framework. Our method repurposes the frozen text encoder to construct a visual codebook from video class labels due to the many-to-one contrastive alignment between visual and ","authors_text":"Hongxuan Li, Pengfei Zhu, Qinghua Hu, Wencheng Zhu, Yuexin Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T07:27:19Z","title":"VTD-CLIP: Video-to-Text Discretization via Prompting CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18407","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:e4d8579f22260b85eeecd492819921bed9d77f077dc9dd810efc69796747e400","target":"record","created_at":"2026-07-05T10:38:46Z","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":"3167b91a015a5ef2b8fa73fbf62b46488af3daf8a5fcfd4121ee6609b923fd6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T07:27:19Z","title_canon_sha256":"7c1ee120677c59de456358e4d64eeecd64c679861ae25755ce15d4d3fab9bcf6"},"schema_version":"1.0","source":{"id":"2503.18407","kind":"arxiv","version":2}},"canonical_sha256":"3e9ea4f70e4f3bbe321d49d3a395edbec3cdb840ba536a3ab85c285bd6c9777a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e9ea4f70e4f3bbe321d49d3a395edbec3cdb840ba536a3ab85c285bd6c9777a","first_computed_at":"2026-07-05T10:38:46.087364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:46.087364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4NDeaGhweBVHGs+F1QCujwHJZYB05zDMwJ+s2FHtBdJ2bMdOKKm5ZvOIPu8f3pXw+AcZiqUYGIYp4IXMPFLNAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:46.087851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18407","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4d8579f22260b85eeecd492819921bed9d77f077dc9dd810efc69796747e400","sha256:36002a21be1bc6f436bcec984ca76dfce7671662b6dd38cf3d9b55f3cc813559"],"state_sha256":"b1709149c2fabb5a498b5055dca02525d68bc2a79dc131ccc0bdd76beebaa575"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uTl+ttNt4fEVk7uMZ8hYD5pAmi1+EM28HDINgC2L/ffEMVBIpCQZKrRqUVt96UFO9ztyM3/pxRcGAsiO04H2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T17:51:04.892615Z","bundle_sha256":"213453f28da179a5001d4687366d71cefd6ac5a2f23a9edf3f0a652e09641b67"}}