{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NZGBQNV57YWWOMDHVUVKWPOSST","short_pith_number":"pith:NZGBQNV5","schema_version":"1.0","canonical_sha256":"6e4c1836bdfe2d673067ad2aab3dd294c2019acbe714d9e38dbc32f53e8f95f6","source":{"kind":"arxiv","id":"2608.11013","version":1},"attestation_state":"computed","paper":{"title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junbo Wang, Liangyu Fu, Xuecheng Wu, Ya Jing, Yuke Li, Zhiyong Wang","submitted_at":"2026-08-11T14:57:44Z","abstract_excerpt":"Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap between the training (text-only) and the inference (video-only). Previous works attempt to bridge the gap through simple linear transformations. However, the inherent gap between text and video makes cross-modal representation space alignment insufficient, resulting in inaccurate sentences. To address this issue, we propose a novel zero-shot video captioning framework (WSV) consisting of two training stages, which first"},"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":"2608.11013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T14:57:44Z","cross_cats_sorted":[],"title_canon_sha256":"8bafda41f619e3956d1132e7a05cef4e62e1aa44579e8414658c30551c6de167","abstract_canon_sha256":"aa67b99ce164c88fd37f637ceeda1a678029ef94b93b4891d078719ef4839ec1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:24:01.089776Z","signature_b64":"k+FZC4Lw5c+riUvu+ULGlUKXSk1YnLzEWbMLAK7ubTT4Mu4l3LibZ+G95pOJYiaxnIVVQRObxSbyoLbELY8SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e4c1836bdfe2d673067ad2aab3dd294c2019acbe714d9e38dbc32f53e8f95f6","last_reissued_at":"2026-08-12T01:24:01.087375Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:24:01.087375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junbo Wang, Liangyu Fu, Xuecheng Wu, Ya Jing, Yuke Li, Zhiyong Wang","submitted_at":"2026-08-11T14:57:44Z","abstract_excerpt":"Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap between the training (text-only) and the inference (video-only). Previous works attempt to bridge the gap through simple linear transformations. However, the inherent gap between text and video makes cross-modal representation space alignment insufficient, resulting in inaccurate sentences. To address this issue, we propose a novel zero-shot video captioning framework (WSV) consisting of two training stages, which first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11013","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/2608.11013/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":"2608.11013","created_at":"2026-08-12T01:24:01.091718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11013v1","created_at":"2026-08-12T01:24:01.091718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11013","created_at":"2026-08-12T01:24:01.091718+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZGBQNV57YWW","created_at":"2026-08-12T01:24:01.091718+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZGBQNV57YWWOMDH","created_at":"2026-08-12T01:24:01.091718+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZGBQNV5","created_at":"2026-08-12T01:24:01.091718+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/NZGBQNV57YWWOMDHVUVKWPOSST","json":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST.json","graph_json":"https://pith.science/api/pith-number/NZGBQNV57YWWOMDHVUVKWPOSST/graph.json","events_json":"https://pith.science/api/pith-number/NZGBQNV57YWWOMDHVUVKWPOSST/events.json","paper":"https://pith.science/paper/NZGBQNV5"},"agent_actions":{"view_html":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST","download_json":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST.json","view_paper":"https://pith.science/paper/NZGBQNV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11013&json=true","fetch_graph":"https://pith.science/api/pith-number/NZGBQNV57YWWOMDHVUVKWPOSST/graph.json","fetch_events":"https://pith.science/api/pith-number/NZGBQNV57YWWOMDHVUVKWPOSST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/action/storage_attestation","attest_author":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/action/author_attestation","sign_citation":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/action/citation_signature","submit_replication":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/action/replication_record"}},"created_at":"2026-08-12T01:24:01.091718+00:00","updated_at":"2026-08-12T01:24:01.091718+00:00"}