{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NZGBQNV57YWWOMDHVUVKWPOSST","short_pith_number":"pith:NZGBQNV5","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"},"canonical_sha256":"6e4c1836bdfe2d673067ad2aab3dd294c2019acbe714d9e38dbc32f53e8f95f6","source":{"kind":"arxiv","id":"2608.11013","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11013","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11013v1","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11013","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"NZGBQNV57YWW","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"NZGBQNV57YWWOMDH","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"NZGBQNV5","created_at":"2026-08-12T01:24:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NZGBQNV57YWWOMDHVUVKWPOSST","target":"record","payload":{"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"},"canonical_sha256":"6e4c1836bdfe2d673067ad2aab3dd294c2019acbe714d9e38dbc32f53e8f95f6","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"},"source_kind":"arxiv","source_id":"2608.11013","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-12T01:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zc00O9G4OdgQ0LGN/EfYky/Ei6VvWdGlFoltnQtnidYkNVUUmla78T+YHSs11Ryv7QqyLk9NgTAJ5AN+btwcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:22:13.124061Z"},"content_sha256":"90ae1cdaf729ec268087ff5e78cc801fee7ac0575b7266f863b8bee1e8521a0b","schema_version":"1.0","event_id":"sha256:90ae1cdaf729ec268087ff5e78cc801fee7ac0575b7266f863b8bee1e8521a0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NZGBQNV57YWWOMDHVUVKWPOSST","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-12T01:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zA7G4NYMJEAvoU53tjQGi1/ZPJcyX3Fyp/kTq/10mfHztzO/mbt1dkbuygyc+pHtBre9fNVF+MvK9rBue6rhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:22:13.124455Z"},"content_sha256":"3a6efa6f3abc82d2987a2362cc54d6fea11de1fdffdab84785b9ffbb266802de","schema_version":"1.0","event_id":"sha256:3a6efa6f3abc82d2987a2362cc54d6fea11de1fdffdab84785b9ffbb266802de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/bundle.json","state_url":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZGBQNV57YWWOMDHVUVKWPOSST/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":"2026-08-13T01:22:13Z","links":{"resolver":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST","bundle":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/bundle.json","state":"https://pith.science/pith/NZGBQNV57YWWOMDHVUVKWPOSST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZGBQNV57YWWOMDHVUVKWPOSST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NZGBQNV57YWWOMDHVUVKWPOSST","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":"aa67b99ce164c88fd37f637ceeda1a678029ef94b93b4891d078719ef4839ec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T14:57:44Z","title_canon_sha256":"8bafda41f619e3956d1132e7a05cef4e62e1aa44579e8414658c30551c6de167"},"schema_version":"1.0","source":{"id":"2608.11013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11013","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11013v1","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11013","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"NZGBQNV57YWW","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"NZGBQNV57YWWOMDH","created_at":"2026-08-12T01:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"NZGBQNV5","created_at":"2026-08-12T01:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:3a6efa6f3abc82d2987a2362cc54d6fea11de1fdffdab84785b9ffbb266802de","target":"graph","created_at":"2026-08-12T01:24:01Z","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/2608.11013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junbo Wang, Liangyu Fu, Xuecheng Wu, Ya Jing, Yuke Li, Zhiyong Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T14:57:44Z","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11013","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":"sha256:90ae1cdaf729ec268087ff5e78cc801fee7ac0575b7266f863b8bee1e8521a0b","target":"record","created_at":"2026-08-12T01:24:01Z","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":"aa67b99ce164c88fd37f637ceeda1a678029ef94b93b4891d078719ef4839ec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T14:57:44Z","title_canon_sha256":"8bafda41f619e3956d1132e7a05cef4e62e1aa44579e8414658c30551c6de167"},"schema_version":"1.0","source":{"id":"2608.11013","kind":"arxiv","version":1}},"canonical_sha256":"6e4c1836bdfe2d673067ad2aab3dd294c2019acbe714d9e38dbc32f53e8f95f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e4c1836bdfe2d673067ad2aab3dd294c2019acbe714d9e38dbc32f53e8f95f6","first_computed_at":"2026-08-12T01:24:01.087375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:24:01.087375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k+FZC4Lw5c+riUvu+ULGlUKXSk1YnLzEWbMLAK7ubTT4Mu4l3LibZ+G95pOJYiaxnIVVQRObxSbyoLbELY8SBg==","signature_status":"signed_v1","signed_at":"2026-08-12T01:24:01.089776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90ae1cdaf729ec268087ff5e78cc801fee7ac0575b7266f863b8bee1e8521a0b","sha256:3a6efa6f3abc82d2987a2362cc54d6fea11de1fdffdab84785b9ffbb266802de"],"state_sha256":"8118786117ef604286f7ccff928f3f018f55767ab79fd14ea055204588e1e1c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUUkM4j0G1F9npycVC+UE0YhBxrsrt9Ui30Ju0kxFvEIhyc2QzXb9N+PX/+L6QDb0pz7j8+CeOsM+dD8kRekCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:22:13.127166Z","bundle_sha256":"f6f4753ad96d48ab3841eb995b7fe346164ccf316b4a79d772186bb39879d1fe"}}