{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H5VIDHLQRPNX6ZZDWQVWMXHCJ6","short_pith_number":"pith:H5VIDHLQ","canonical_record":{"source":{"id":"2403.12922","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"b251d311eff7861a2782ebc8f136c9d4a1738fe0ce3b155b77f14aa0d02c917d","abstract_canon_sha256":"7eb454d64544e9365b71ea6388d3f7f970ecdbfe3653e5d551e5c464caf281bf"},"schema_version":"1.0"},"canonical_sha256":"3f6a819d708bdb7f6723b42b665ce24fabb76063093301b913d258c6a65c9402","source":{"kind":"arxiv","id":"2403.12922","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12922","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12922v3","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12922","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"pith_short_12","alias_value":"H5VIDHLQRPNX","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"pith_short_16","alias_value":"H5VIDHLQRPNX6ZZD","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"pith_short_8","alias_value":"H5VIDHLQ","created_at":"2026-07-05T10:49:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H5VIDHLQRPNX6ZZDWQVWMXHCJ6","target":"record","payload":{"canonical_record":{"source":{"id":"2403.12922","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"b251d311eff7861a2782ebc8f136c9d4a1738fe0ce3b155b77f14aa0d02c917d","abstract_canon_sha256":"7eb454d64544e9365b71ea6388d3f7f970ecdbfe3653e5d551e5c464caf281bf"},"schema_version":"1.0"},"canonical_sha256":"3f6a819d708bdb7f6723b42b665ce24fabb76063093301b913d258c6a65c9402","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:05.588775Z","signature_b64":"snVIIfaK+kRiluKDxrttT0nPZkd02DB7aEq3RLnounPzfgp5ZYAgGKKFphCnNjbx8TvzlGKUqvh4sdVPIKhHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f6a819d708bdb7f6723b42b665ce24fabb76063093301b913d258c6a65c9402","last_reissued_at":"2026-07-05T10:49:05.588277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:05.588277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.12922","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYEY8sxho8xT96gt8Exy33J+Gc+5UJ26ekf8SI/L+nlS/i4rQ/PQHCQkBQZodcG/MJRfalARMTfiGKgVMOD+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:36:28.000505Z"},"content_sha256":"865f113d1a43733582b7e502039c41f7d75ceb0042a7201d09fb82647c4efe12","schema_version":"1.0","event_id":"sha256:865f113d1a43733582b7e502039c41f7d75ceb0042a7201d09fb82647c4efe12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H5VIDHLQRPNX6ZZDWQVWMXHCJ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual AD Narration with Interleaved Multimodal Sequence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanlin Wang, Kecheng Zheng, Limin Wang, Yujun Shen, Zhan Tong","submitted_at":"2024-03-19T17:27:55Z","abstract_excerpt":"The Audio Description (AD) task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies. With video feature, text, character bank and context information as inputs, the generated ADs are able to correspond to the characters by name and provide reasonable, contextual descriptions to help audience understand the storyline of movie. To achieve this goal, we propose to leverage pre-trained foundation models through a simple and unified framework to generate ADs with interleaved multimodal sequence as input, termed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12922","kind":"arxiv","version":3},"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/2403.12922/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":"2026-07-05T10:49:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BNsxXUwmYoafjrOy6DLP3c/4GzNf+geEazQEVoKMxADF1rZ6rNZCmlw1x/VYpugYK1iOfkIp/t/eRzl1ZLVRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:36:28.001416Z"},"content_sha256":"1319d1676927560145912cf4d5fd041460d112aaefb7e1f0952871e29e3a45eb","schema_version":"1.0","event_id":"sha256:1319d1676927560145912cf4d5fd041460d112aaefb7e1f0952871e29e3a45eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6/bundle.json","state_url":"https://pith.science/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6/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":"2026-08-11T03:36:28Z","links":{"resolver":"https://pith.science/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6","bundle":"https://pith.science/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6/bundle.json","state":"https://pith.science/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5VIDHLQRPNX6ZZDWQVWMXHCJ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H5VIDHLQRPNX6ZZDWQVWMXHCJ6","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":"7eb454d64544e9365b71ea6388d3f7f970ecdbfe3653e5d551e5c464caf281bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:27:55Z","title_canon_sha256":"b251d311eff7861a2782ebc8f136c9d4a1738fe0ce3b155b77f14aa0d02c917d"},"schema_version":"1.0","source":{"id":"2403.12922","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12922","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12922v3","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12922","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"pith_short_12","alias_value":"H5VIDHLQRPNX","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"pith_short_16","alias_value":"H5VIDHLQRPNX6ZZD","created_at":"2026-07-05T10:49:05Z"},{"alias_kind":"pith_short_8","alias_value":"H5VIDHLQ","created_at":"2026-07-05T10:49:05Z"}],"graph_snapshots":[{"event_id":"sha256:1319d1676927560145912cf4d5fd041460d112aaefb7e1f0952871e29e3a45eb","target":"graph","created_at":"2026-07-05T10:49:05Z","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/2403.12922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Audio Description (AD) task aims to generate descriptions of visual elements for visually impaired individuals to help them access long-form video content, like movies. With video feature, text, character bank and context information as inputs, the generated ADs are able to correspond to the characters by name and provide reasonable, contextual descriptions to help audience understand the storyline of movie. To achieve this goal, we propose to leverage pre-trained foundation models through a simple and unified framework to generate ADs with interleaved multimodal sequence as input, termed ","authors_text":"Hanlin Wang, Kecheng Zheng, Limin Wang, Yujun Shen, Zhan Tong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:27:55Z","title":"Contextual AD Narration with Interleaved Multimodal Sequence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12922","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":"sha256:865f113d1a43733582b7e502039c41f7d75ceb0042a7201d09fb82647c4efe12","target":"record","created_at":"2026-07-05T10:49:05Z","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":"7eb454d64544e9365b71ea6388d3f7f970ecdbfe3653e5d551e5c464caf281bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:27:55Z","title_canon_sha256":"b251d311eff7861a2782ebc8f136c9d4a1738fe0ce3b155b77f14aa0d02c917d"},"schema_version":"1.0","source":{"id":"2403.12922","kind":"arxiv","version":3}},"canonical_sha256":"3f6a819d708bdb7f6723b42b665ce24fabb76063093301b913d258c6a65c9402","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f6a819d708bdb7f6723b42b665ce24fabb76063093301b913d258c6a65c9402","first_computed_at":"2026-07-05T10:49:05.588277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:05.588277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snVIIfaK+kRiluKDxrttT0nPZkd02DB7aEq3RLnounPzfgp5ZYAgGKKFphCnNjbx8TvzlGKUqvh4sdVPIKhHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:05.588775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12922","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:865f113d1a43733582b7e502039c41f7d75ceb0042a7201d09fb82647c4efe12","sha256:1319d1676927560145912cf4d5fd041460d112aaefb7e1f0952871e29e3a45eb"],"state_sha256":"865520935c100d2690b4cb71b99cf52c54403400ecf566e891ce9880d34a6c26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNv3LOyP2GpSc2F6wEZVosvT9RN4LiN7SLLQqzycQotVIYSKnknSB/9RFmeGd0jEQoFj7SRAZ5KSFdxbJ+MCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:36:28.023937Z","bundle_sha256":"42eba06b2fbecc884ae46e406ca5af47daa8ff2962995d93dd533e3b6f5017d6"}}