{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6KXTAOUYDGFLUSLRXCHRYGCWAJ","short_pith_number":"pith:6KXTAOUY","canonical_record":{"source":{"id":"2408.11286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T02:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"667b50d958bff48b1e11ea7026172bd513c033223cfccd60285c78904d09d79c","abstract_canon_sha256":"dde9566ec16c197ace510d419d2df49c5baf6f706bcc142f99f07b19e4348972"},"schema_version":"1.0"},"canonical_sha256":"f2af303a98198aba4971b88f1c18560268babcad67e22f72ea3c824ee8723c4c","source":{"kind":"arxiv","id":"2408.11286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11286","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11286v2","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11286","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"pith_short_12","alias_value":"6KXTAOUYDGFL","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"pith_short_16","alias_value":"6KXTAOUYDGFLUSLR","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"pith_short_8","alias_value":"6KXTAOUY","created_at":"2026-07-05T08:57:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6KXTAOUYDGFLUSLRXCHRYGCWAJ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T02:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"667b50d958bff48b1e11ea7026172bd513c033223cfccd60285c78904d09d79c","abstract_canon_sha256":"dde9566ec16c197ace510d419d2df49c5baf6f706bcc142f99f07b19e4348972"},"schema_version":"1.0"},"canonical_sha256":"f2af303a98198aba4971b88f1c18560268babcad67e22f72ea3c824ee8723c4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:59.376836Z","signature_b64":"38Z7lOo/agNgeOkBvWhLsoGDSIp0rZ6UIF7/aMlwQIH3WwH9np0huUbkkuXPWAkTf2r24sRycrHdLSFob+mgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2af303a98198aba4971b88f1c18560268babcad67e22f72ea3c824ee8723c4c","last_reissued_at":"2026-07-05T08:57:59.376392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:59.376392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11286","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbGzbQZH0+WeBIUK/z2TmbMLu8MR12IL0W2nkrD71OZRf+bpKgOXH3By9IuOn77UrYe1uBHPtk9c4X9TfCB0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:50.916126Z"},"content_sha256":"1ca8a634a6fef8bf4c349629cfb81c4f65a23d176ce0de9c1a5fe0c6123a7a7b","schema_version":"1.0","event_id":"sha256:1ca8a634a6fef8bf4c349629cfb81c4f65a23d176ce0de9c1a5fe0c6123a7a7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6KXTAOUYDGFLUSLRXCHRYGCWAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Emotion Open-vocabulary Recognition Based on Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongkai Tang, MengYing Ge, Mingyang Li","submitted_at":"2024-08-21T02:17:18Z","abstract_excerpt":"Multimodal emotion recognition is a task of great concern. However, traditional data sets are based on fixed labels, resulting in models that often focus on main emotions and ignore detailed emotional changes in complex scenes. This report introduces the solution of using MLLMs technology to generate open-vocabulary emotion labels from a video. The solution includes the use of framework, data generation and processing, training methods, results generation and multi-model co-judgment. In the MER-OV (Open-Word Emotion Recognition) of the MER2024 challenge, our method achieved significant advanta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11286","kind":"arxiv","version":2},"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/2408.11286/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":"2026-07-05T08:57:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ldcAakxEfw6J9FDNcsWw8Qg8vGfFboJWd9NY/vHWB5jwDpW0/P2vL17pl/n7h2wuGzKGzwvv2Sb8dHk9j/yCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:50.916795Z"},"content_sha256":"6a848323509602dc2d9a2b92bf9a9c671c1c6c5f9fbb8cdec37b6f5cc564c0b1","schema_version":"1.0","event_id":"sha256:6a848323509602dc2d9a2b92bf9a9c671c1c6c5f9fbb8cdec37b6f5cc564c0b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ/bundle.json","state_url":"https://pith.science/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ/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":"2026-07-09T05:56:50Z","links":{"resolver":"https://pith.science/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ","bundle":"https://pith.science/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ/bundle.json","state":"https://pith.science/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KXTAOUYDGFLUSLRXCHRYGCWAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KXTAOUYDGFLUSLRXCHRYGCWAJ","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":"dde9566ec16c197ace510d419d2df49c5baf6f706bcc142f99f07b19e4348972","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T02:17:18Z","title_canon_sha256":"667b50d958bff48b1e11ea7026172bd513c033223cfccd60285c78904d09d79c"},"schema_version":"1.0","source":{"id":"2408.11286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11286","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11286v2","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11286","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"pith_short_12","alias_value":"6KXTAOUYDGFL","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"pith_short_16","alias_value":"6KXTAOUYDGFLUSLR","created_at":"2026-07-05T08:57:59Z"},{"alias_kind":"pith_short_8","alias_value":"6KXTAOUY","created_at":"2026-07-05T08:57:59Z"}],"graph_snapshots":[{"event_id":"sha256:6a848323509602dc2d9a2b92bf9a9c671c1c6c5f9fbb8cdec37b6f5cc564c0b1","target":"graph","created_at":"2026-07-05T08:57:59Z","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/2408.11286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal emotion recognition is a task of great concern. However, traditional data sets are based on fixed labels, resulting in models that often focus on main emotions and ignore detailed emotional changes in complex scenes. This report introduces the solution of using MLLMs technology to generate open-vocabulary emotion labels from a video. The solution includes the use of framework, data generation and processing, training methods, results generation and multi-model co-judgment. In the MER-OV (Open-Word Emotion Recognition) of the MER2024 challenge, our method achieved significant advanta","authors_text":"Dongkai Tang, MengYing Ge, Mingyang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T02:17:18Z","title":"Video Emotion Open-vocabulary Recognition Based on Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11286","kind":"arxiv","version":2},"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":"sha256:1ca8a634a6fef8bf4c349629cfb81c4f65a23d176ce0de9c1a5fe0c6123a7a7b","target":"record","created_at":"2026-07-05T08:57:59Z","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":"dde9566ec16c197ace510d419d2df49c5baf6f706bcc142f99f07b19e4348972","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T02:17:18Z","title_canon_sha256":"667b50d958bff48b1e11ea7026172bd513c033223cfccd60285c78904d09d79c"},"schema_version":"1.0","source":{"id":"2408.11286","kind":"arxiv","version":2}},"canonical_sha256":"f2af303a98198aba4971b88f1c18560268babcad67e22f72ea3c824ee8723c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2af303a98198aba4971b88f1c18560268babcad67e22f72ea3c824ee8723c4c","first_computed_at":"2026-07-05T08:57:59.376392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:59.376392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"38Z7lOo/agNgeOkBvWhLsoGDSIp0rZ6UIF7/aMlwQIH3WwH9np0huUbkkuXPWAkTf2r24sRycrHdLSFob+mgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:59.376836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ca8a634a6fef8bf4c349629cfb81c4f65a23d176ce0de9c1a5fe0c6123a7a7b","sha256:6a848323509602dc2d9a2b92bf9a9c671c1c6c5f9fbb8cdec37b6f5cc564c0b1"],"state_sha256":"3a1fafaa0b77e1a217d724e857112d7ed9595213f60e217b69c80c8ce36e604c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HGCMP57o9u1+Nd9weQHZBe+RPoC8KnaL8NfzHYVzCuxQCaLRDZijREG5mLawwXuHmGZe4rxBzWgH4EOX5wxYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:56:50.919961Z","bundle_sha256":"7dc6c4bb84ceef6931d4db4957059b43aac8c3cde433f961118001e8755b33b4"}}