{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FKI36F6BKJQNCSHYSQWSCLWMS3","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":"fff37aa5010a32bd9b9d0aba381a4169232244c702d2fa5cd489a8a924cb4387","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T10:02:22Z","title_canon_sha256":"2a5b1222112f646342ab525c202beb2750395b11704e783b71f6ff4999f5c77f"},"schema_version":"1.0","source":{"id":"2503.18507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18507","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18507v1","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18507","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"pith_short_12","alias_value":"FKI36F6BKJQN","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"pith_short_16","alias_value":"FKI36F6BKJQNCSHY","created_at":"2026-07-05T10:38:12Z"},{"alias_kind":"pith_short_8","alias_value":"FKI36F6B","created_at":"2026-07-05T10:38:12Z"}],"graph_snapshots":[{"event_id":"sha256:01e776e084fa80fc8f4e473881829327672ad98fb4249656df55da2cd6113eed","target":"graph","created_at":"2026-07-05T10:38:12Z","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/2503.18507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video-language alignment models are trained on sets of videos, each with an associated positive caption and a negative caption generated by large language models. A problem with this procedure is that negative captions may introduce linguistic biases, i.e., concepts are seen only as negatives and never associated with a video. While a solution would be to collect videos for the negative captions, existing databases lack the fine-grained variations needed to cover all possible negatives. In this work, we study whether synthetic videos can help to overcome this issue. Our preliminary anal","authors_text":"Elisa Ricci, Luca Zanella, Massimiliano Mancini, Sergey Tulyakov, Willi Menapace, Yiming Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T10:02:22Z","title":"Can Text-to-Video Generation help Video-Language Alignment?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18507","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:db539d4b0224117d7894155a2a0a34c48b654cab2d5d89eb66e57bda86cda58c","target":"record","created_at":"2026-07-05T10:38:12Z","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":"fff37aa5010a32bd9b9d0aba381a4169232244c702d2fa5cd489a8a924cb4387","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T10:02:22Z","title_canon_sha256":"2a5b1222112f646342ab525c202beb2750395b11704e783b71f6ff4999f5c77f"},"schema_version":"1.0","source":{"id":"2503.18507","kind":"arxiv","version":1}},"canonical_sha256":"2a91bf17c15260d148f8942d212ecc96c78cb756a358055c7dfee149001937ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a91bf17c15260d148f8942d212ecc96c78cb756a358055c7dfee149001937ab","first_computed_at":"2026-07-05T10:38:12.142059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:12.142059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ko4JwzrpjTLbmOUL4jZcgDsihXdrXhCmI9q5WpjIpEAmlxFPDl+wtzPmC72pmFZhz+hdtFH1hLX3kNNAc4aABA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:12.142746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db539d4b0224117d7894155a2a0a34c48b654cab2d5d89eb66e57bda86cda58c","sha256:01e776e084fa80fc8f4e473881829327672ad98fb4249656df55da2cd6113eed"],"state_sha256":"21e4bbed6005363f6902b5ca135d3464503f30cd9df01076894185fa4ed457c4"}