{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6VFWJJVLXYSYOL3HT3ZAKUZHDN","short_pith_number":"pith:6VFWJJVL","canonical_record":{"source":{"id":"2407.20962","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T16:43:24Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"335c37f76fdd2adb20d5d0d61f9cdd6cdda5a33339d801957eab0060d0c530fa","abstract_canon_sha256":"ec2094f9c2b5ffddc6db0c8aac94816b324672198a7df19b4b88908509966734"},"schema_version":"1.0"},"canonical_sha256":"f54b64a6abbe25872f679ef20553271b735c6205ac232532d3f0d4a0d19eec81","source":{"kind":"arxiv","id":"2407.20962","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20962","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20962v3","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20962","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"6VFWJJVLXYSY","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"6VFWJJVLXYSYOL3H","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"6VFWJJVL","created_at":"2026-07-05T09:50:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6VFWJJVLXYSYOL3HT3ZAKUZHDN","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20962","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T16:43:24Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"335c37f76fdd2adb20d5d0d61f9cdd6cdda5a33339d801957eab0060d0c530fa","abstract_canon_sha256":"ec2094f9c2b5ffddc6db0c8aac94816b324672198a7df19b4b88908509966734"},"schema_version":"1.0"},"canonical_sha256":"f54b64a6abbe25872f679ef20553271b735c6205ac232532d3f0d4a0d19eec81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:04.285168Z","signature_b64":"v2x64LnfRDy7zoskYojf6Bjw3r+lAa0w3vy+rQqjrazzamPSEGeXJMvt6Tr/Uf0psbaA83RlTcg+V1lWfo/cDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f54b64a6abbe25872f679ef20553271b735c6205ac232532d3f0d4a0d19eec81","last_reissued_at":"2026-07-05T09:50:04.284556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:04.284556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20962","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":"2026-07-05T09:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BwIGm6f/qUHLVdmmAB/ityDZBbBcMpij8GnkZj4CLfDSx8E01ndNzlJC24KmChII9vyxh8VQgPkTSBBwmC6qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:59:32.354296Z"},"content_sha256":"6f9d34e72dc71f2ccf2bffe901c2c1f32ec88314fa63678655971ce95e27c801","schema_version":"1.0","event_id":"sha256:6f9d34e72dc71f2ccf2bffe901c2c1f32ec88314fa63678655971ce95e27c801"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6VFWJJVLXYSYOL3HT3ZAKUZHDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aosong Cheng, Jiahao Pan, Mengfei Li, Pengjun Fang, Qifeng Chen, Qifeng Liu, Rongyu Zhang, Ruibin Yuan, Shanghang Zhang, Wei Xue, Wenhan Luo, Xiaowei Chi, Xingqun Qi, Yanbing Jiang, Yatian Wang, Yike Guo, Yingqing He, Zeyue Tian, Zhaoyang Liu","submitted_at":"2024-07-30T16:43:24Z","abstract_excerpt":"Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text descriptions for visual frames, considering audio to be weakly related information. They usually overlook exploring the potential of inherent audio-visual correlation, leading to monotonous annotation within each modality instead of comprehensive and precise descriptions. Such ignorance results in the difficulty of multiple cross-modality studies. To fulfill this gap, we present MMTrail, a large-scale multi-modality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20962","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/2407.20962/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":"2026-07-05T09:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A8VC9LJCdvG2vkk662YDsAShae0EdC7gKqxKsiMoI6YLRt7Gy0KPn8TRN8vA71J+dqzmTfMCDFsuWy6FEk+kAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:59:32.354688Z"},"content_sha256":"5eda38dc2745244c2fac630344355b24981927c8bdfa5ed6fd95619aae5b7542","schema_version":"1.0","event_id":"sha256:5eda38dc2745244c2fac630344355b24981927c8bdfa5ed6fd95619aae5b7542"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN/bundle.json","state_url":"https://pith.science/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN/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":"2026-08-04T07:59:32Z","links":{"resolver":"https://pith.science/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN","bundle":"https://pith.science/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN/bundle.json","state":"https://pith.science/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6VFWJJVLXYSYOL3HT3ZAKUZHDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6VFWJJVLXYSYOL3HT3ZAKUZHDN","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":"ec2094f9c2b5ffddc6db0c8aac94816b324672198a7df19b4b88908509966734","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T16:43:24Z","title_canon_sha256":"335c37f76fdd2adb20d5d0d61f9cdd6cdda5a33339d801957eab0060d0c530fa"},"schema_version":"1.0","source":{"id":"2407.20962","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20962","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20962v3","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20962","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"6VFWJJVLXYSY","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"6VFWJJVLXYSYOL3H","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"6VFWJJVL","created_at":"2026-07-05T09:50:04Z"}],"graph_snapshots":[{"event_id":"sha256:5eda38dc2745244c2fac630344355b24981927c8bdfa5ed6fd95619aae5b7542","target":"graph","created_at":"2026-07-05T09:50:04Z","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/2407.20962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text descriptions for visual frames, considering audio to be weakly related information. They usually overlook exploring the potential of inherent audio-visual correlation, leading to monotonous annotation within each modality instead of comprehensive and precise descriptions. Such ignorance results in the difficulty of multiple cross-modality studies. To fulfill this gap, we present MMTrail, a large-scale multi-modality ","authors_text":"Aosong Cheng, Jiahao Pan, Mengfei Li, Pengjun Fang, Qifeng Chen, Qifeng Liu, Rongyu Zhang, Ruibin Yuan, Shanghang Zhang, Wei Xue, Wenhan Luo, Xiaowei Chi, Xingqun Qi, Yanbing Jiang, Yatian Wang, Yike Guo, Yingqing He, Zeyue Tian, Zhaoyang Liu","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T16:43:24Z","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20962","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":"sha256:6f9d34e72dc71f2ccf2bffe901c2c1f32ec88314fa63678655971ce95e27c801","target":"record","created_at":"2026-07-05T09:50:04Z","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":"ec2094f9c2b5ffddc6db0c8aac94816b324672198a7df19b4b88908509966734","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T16:43:24Z","title_canon_sha256":"335c37f76fdd2adb20d5d0d61f9cdd6cdda5a33339d801957eab0060d0c530fa"},"schema_version":"1.0","source":{"id":"2407.20962","kind":"arxiv","version":3}},"canonical_sha256":"f54b64a6abbe25872f679ef20553271b735c6205ac232532d3f0d4a0d19eec81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f54b64a6abbe25872f679ef20553271b735c6205ac232532d3f0d4a0d19eec81","first_computed_at":"2026-07-05T09:50:04.284556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:04.284556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v2x64LnfRDy7zoskYojf6Bjw3r+lAa0w3vy+rQqjrazzamPSEGeXJMvt6Tr/Uf0psbaA83RlTcg+V1lWfo/cDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:04.285168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20962","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f9d34e72dc71f2ccf2bffe901c2c1f32ec88314fa63678655971ce95e27c801","sha256:5eda38dc2745244c2fac630344355b24981927c8bdfa5ed6fd95619aae5b7542"],"state_sha256":"540e32c6396386a60eb139cf3401b86a1bf74bf567cd9d22710fa704482d8086"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCUsJ52Zq0Q4aMjS1w9Bns5FpOSitnFUrJVonUZ9Dj9EmG2T2Oqe5HVPLCoz9IJIxtJJ6ZJvzDVjiyCavKCwDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:59:32.357442Z","bundle_sha256":"c8a633e6c5048fe40e623ea932739279b85880bf764f13b3bc16ebd3fb7d94bc"}}