{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:734JDURIEEII3RGOQU5Y47FSX5","short_pith_number":"pith:734JDURI","canonical_record":{"source":{"id":"2501.07978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T09:52:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecf7b1da258b8a07e720cf3d7e2a4c514d4c19318fe30b8c0df5a5179eec61c5","abstract_canon_sha256":"24b9337959b4d910604fce2684c661f02fca307b68a0c15a0c7dbd88289a5415"},"schema_version":"1.0"},"canonical_sha256":"fef891d22821108dc4ce853b8e7cb2bf700ba2f337ea1d9b8f795e3faa4b3783","source":{"kind":"arxiv","id":"2501.07978","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07978","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07978v1","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07978","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"734JDURIEEII","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"734JDURIEEII3RGO","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"734JDURI","created_at":"2026-07-05T10:00:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:734JDURIEEII3RGOQU5Y47FSX5","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T09:52:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecf7b1da258b8a07e720cf3d7e2a4c514d4c19318fe30b8c0df5a5179eec61c5","abstract_canon_sha256":"24b9337959b4d910604fce2684c661f02fca307b68a0c15a0c7dbd88289a5415"},"schema_version":"1.0"},"canonical_sha256":"fef891d22821108dc4ce853b8e7cb2bf700ba2f337ea1d9b8f795e3faa4b3783","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:53.281627Z","signature_b64":"+yzQVMPhchwbCi27T9itgknAVHpzclB8jPhy6bL1YRh+waznE9d24kK3U9xsJ3ObO78+DnParYW/vFuvTkyVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fef891d22821108dc4ce853b8e7cb2bf700ba2f337ea1d9b8f795e3faa4b3783","last_reissued_at":"2026-07-05T10:00:53.281075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:53.281075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07978","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71Pobm/oVEtAJa3eXEqJ2KC4zKOv7d/HrwZ899L/njjWJiQ6JObrVYTcKCnyBCH7kqvY/ZLzGRFT+u280SSLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:26:37.217835Z"},"content_sha256":"05f88e4e2770f6416d716ee5ca258dd45778886a395e9e3f5ccd12a171e64a68","schema_version":"1.0","event_id":"sha256:05f88e4e2770f6416d716ee5ca258dd45778886a395e9e3f5ccd12a171e64a68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:734JDURIEEII3RGOQU5Y47FSX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual Awareness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyuan Sun, Jiaxing Zhao, Xiang Chen, Xihan Wei","submitted_at":"2025-01-14T09:52:56Z","abstract_excerpt":"Facial expression captioning has found widespread application across various domains. Recently, the emergence of video Multimodal Large Language Models (MLLMs) has shown promise in general video understanding tasks. However, describing facial expressions within videos poses two major challenges for these models: (1) the lack of adequate datasets and benchmarks, and (2) the limited visual token capacity of video MLLMs. To address these issues, this paper introduces a new instruction-following dataset tailored for dynamic facial expression caption. The dataset comprises 5,033 high-quality video "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07978","kind":"arxiv","version":1},"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/2501.07978/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":"2026-07-05T10:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8oh4dB0/VMd0BqDg4By2mQt/HHfXYQQvQyWAtA9n7ltTiivJiPTWq9HF9BdCS2kmmrXl+xbZ4sM2JpFBWALfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:26:37.218520Z"},"content_sha256":"9fe355b27559c7988c59f1f95206657bc0d1b869b24c87b3679618cafc908358","schema_version":"1.0","event_id":"sha256:9fe355b27559c7988c59f1f95206657bc0d1b869b24c87b3679618cafc908358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/734JDURIEEII3RGOQU5Y47FSX5/bundle.json","state_url":"https://pith.science/pith/734JDURIEEII3RGOQU5Y47FSX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/734JDURIEEII3RGOQU5Y47FSX5/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":"2026-08-11T19:26:37Z","links":{"resolver":"https://pith.science/pith/734JDURIEEII3RGOQU5Y47FSX5","bundle":"https://pith.science/pith/734JDURIEEII3RGOQU5Y47FSX5/bundle.json","state":"https://pith.science/pith/734JDURIEEII3RGOQU5Y47FSX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/734JDURIEEII3RGOQU5Y47FSX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:734JDURIEEII3RGOQU5Y47FSX5","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":"24b9337959b4d910604fce2684c661f02fca307b68a0c15a0c7dbd88289a5415","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T09:52:56Z","title_canon_sha256":"ecf7b1da258b8a07e720cf3d7e2a4c514d4c19318fe30b8c0df5a5179eec61c5"},"schema_version":"1.0","source":{"id":"2501.07978","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07978","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07978v1","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07978","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"734JDURIEEII","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_16","alias_value":"734JDURIEEII3RGO","created_at":"2026-07-05T10:00:53Z"},{"alias_kind":"pith_short_8","alias_value":"734JDURI","created_at":"2026-07-05T10:00:53Z"}],"graph_snapshots":[{"event_id":"sha256:9fe355b27559c7988c59f1f95206657bc0d1b869b24c87b3679618cafc908358","target":"graph","created_at":"2026-07-05T10:00:53Z","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/2501.07978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Facial expression captioning has found widespread application across various domains. Recently, the emergence of video Multimodal Large Language Models (MLLMs) has shown promise in general video understanding tasks. However, describing facial expressions within videos poses two major challenges for these models: (1) the lack of adequate datasets and benchmarks, and (2) the limited visual token capacity of video MLLMs. To address these issues, this paper introduces a new instruction-following dataset tailored for dynamic facial expression caption. The dataset comprises 5,033 high-quality video ","authors_text":"Boyuan Sun, Jiaxing Zhao, Xiang Chen, Xihan Wei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T09:52:56Z","title":"Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual Awareness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07978","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":"sha256:05f88e4e2770f6416d716ee5ca258dd45778886a395e9e3f5ccd12a171e64a68","target":"record","created_at":"2026-07-05T10:00:53Z","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":"24b9337959b4d910604fce2684c661f02fca307b68a0c15a0c7dbd88289a5415","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T09:52:56Z","title_canon_sha256":"ecf7b1da258b8a07e720cf3d7e2a4c514d4c19318fe30b8c0df5a5179eec61c5"},"schema_version":"1.0","source":{"id":"2501.07978","kind":"arxiv","version":1}},"canonical_sha256":"fef891d22821108dc4ce853b8e7cb2bf700ba2f337ea1d9b8f795e3faa4b3783","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fef891d22821108dc4ce853b8e7cb2bf700ba2f337ea1d9b8f795e3faa4b3783","first_computed_at":"2026-07-05T10:00:53.281075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:53.281075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+yzQVMPhchwbCi27T9itgknAVHpzclB8jPhy6bL1YRh+waznE9d24kK3U9xsJ3ObO78+DnParYW/vFuvTkyVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:53.281627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07978","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f88e4e2770f6416d716ee5ca258dd45778886a395e9e3f5ccd12a171e64a68","sha256:9fe355b27559c7988c59f1f95206657bc0d1b869b24c87b3679618cafc908358"],"state_sha256":"a0a41ce904e593d15e274557fd9b4272d3983ab9351d497108d5d66f3af1d9a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQJuweSRQtb+vfKUWVQdGsRunfG3AB0//06ZA4eVwh/TClxoC/LfIO0BzFLN2AMF+IOgk+IdNfwc4d87QCLHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:26:37.224312Z","bundle_sha256":"bbe3d024c602df263c5f6bda3e22cc2f6cb6a0dba7595343dabd782e8839f1cf"}}