{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZJBSO5YDCP3AXBA75YBIGT42AM","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":"9bff63630896e950ce18286c588601cea7dbb12d5368653f8ff858f2378f58d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T03:35:27Z","title_canon_sha256":"bae25b9b62da143cc1b7254c22ab3a6d9e7724689978808895bb9ac2d5d6b1df"},"schema_version":"1.0","source":{"id":"2310.04991","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04991","created_at":"2026-07-05T06:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04991v3","created_at":"2026-07-05T06:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04991","created_at":"2026-07-05T06:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZJBSO5YDCP3A","created_at":"2026-07-05T06:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZJBSO5YDCP3AXBA7","created_at":"2026-07-05T06:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZJBSO5YD","created_at":"2026-07-05T06:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:d1d2665d0f18c828ebabfac540124d601ba58874167ee4e7e9d63161f353a052","target":"graph","created_at":"2026-07-05T06:59:36Z","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/2310.04991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text generation task. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions. To effectively integrate visual and auditory information, Video-Teller builds upon the image-based BLIP-2 model and introduces a cascaded Q-Forme","authors_text":"Haogeng Liu, Hongxia Yang, Huaibo Huang, Linjie Yang, Qihang Fan, Ran He, Tingkai Liu, Yunzhe Tao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T03:35:27Z","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04991","kind":"arxiv","version":3},"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":"sha256:05e2e2a95669d1bad3f6d54c17654b50a435ad80ea3abde35c3a3b6cb5ae5de0","target":"record","created_at":"2026-07-05T06:59:36Z","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":"9bff63630896e950ce18286c588601cea7dbb12d5368653f8ff858f2378f58d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-08T03:35:27Z","title_canon_sha256":"bae25b9b62da143cc1b7254c22ab3a6d9e7724689978808895bb9ac2d5d6b1df"},"schema_version":"1.0","source":{"id":"2310.04991","kind":"arxiv","version":3}},"canonical_sha256":"ca4327770313f60b841fee02834f9a033784298d52499b9b73f618fb426d2720","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca4327770313f60b841fee02834f9a033784298d52499b9b73f618fb426d2720","first_computed_at":"2026-07-05T06:59:36.076117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:36.076117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XjNmkd40XnZiluBjUPhFjdfX7fNcgRqt8O8NBTxMxz8ExU1bPWXiE9KTKPt0vq7EiNQgQg1z8JXNSOXtMiFSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:36.076655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04991","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05e2e2a95669d1bad3f6d54c17654b50a435ad80ea3abde35c3a3b6cb5ae5de0","sha256:d1d2665d0f18c828ebabfac540124d601ba58874167ee4e7e9d63161f353a052"],"state_sha256":"ba0165d59db75a4b821c46534b9ade791bf90fa2f1cbaf9c70420b2f788d989e"}