{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z5LEDNXBBIS6SRVRTRZ6DXFIHL","short_pith_number":"pith:Z5LEDNXB","canonical_record":{"source":{"id":"2505.02331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T03:00:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3134381c6b0e45a5903dac9bcbe1034c5c9893fe8744e4d31336cdfc532bb78d","abstract_canon_sha256":"4e85b53e0fd14eb09864aa1beac0fe97f1642e16c77d616783a3f178cbd41838"},"schema_version":"1.0"},"canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","source":{"kind":"arxiv","id":"2505.02331","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02331","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02331v2","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02331","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"Z5LEDNXBBIS6","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"Z5LEDNXBBIS6SRVR","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"Z5LEDNXB","created_at":"2026-07-05T11:47:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z5LEDNXBBIS6SRVRTRZ6DXFIHL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T03:00:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3134381c6b0e45a5903dac9bcbe1034c5c9893fe8744e4d31336cdfc532bb78d","abstract_canon_sha256":"4e85b53e0fd14eb09864aa1beac0fe97f1642e16c77d616783a3f178cbd41838"},"schema_version":"1.0"},"canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:22.532017Z","signature_b64":"Qmpj6Qua9iPSuJ+ey8QB8lR/GfHCnrrTGXnB2X2eBwQnu0pY08qvNNRJfQebCmMUfOHOmsAewKVSeUWf6D56Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","last_reissued_at":"2026-07-05T11:47:22.531534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:22.531534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02331","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":"2026-07-05T11:47:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MThxkCPmiCxJf3A7mF5Eor/0ooufKMN5txYiLI2poXtTE4IUp1FmpG4hwDjKyswx/Z9Ly5nG6Zb4eFtIqT4eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:57:15.688471Z"},"content_sha256":"dcd94b08bdf844615e747b774b9d91b4b0611f8d5c8ecaec57036e26e355b6de","schema_version":"1.0","event_id":"sha256:dcd94b08bdf844615e747b774b9d91b4b0611f8d5c8ecaec57036e26e355b6de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z5LEDNXBBIS6SRVRTRZ6DXFIHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Hao Cheng, Jia Li, Meng Wang, Richang Hong, Yichao He, Zhenzhen Hu, Zhiwei Zhao","submitted_at":"2025-05-05T03:00:51Z","abstract_excerpt":"Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02331","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/2505.02331/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":"2026-07-05T11:47:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpLXpnhn7HgwjGgn+VE2r+q2jAgb2zUMMg06GBJ+KZK+z/xqf/ruCW1Xh5ePmEbe7SqpsvhMhznbhx/KbSWhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:57:15.689002Z"},"content_sha256":"a2da229e6c7cb5fab8071d80d0448481dce0cc1fd3b438bcaa8fb74db9cca4d7","schema_version":"1.0","event_id":"sha256:a2da229e6c7cb5fab8071d80d0448481dce0cc1fd3b438bcaa8fb74db9cca4d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/bundle.json","state_url":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/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":"2026-08-20T14:57:15Z","links":{"resolver":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL","bundle":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/bundle.json","state":"https://pith.science/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5LEDNXBBIS6SRVRTRZ6DXFIHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z5LEDNXBBIS6SRVRTRZ6DXFIHL","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":"4e85b53e0fd14eb09864aa1beac0fe97f1642e16c77d616783a3f178cbd41838","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T03:00:51Z","title_canon_sha256":"3134381c6b0e45a5903dac9bcbe1034c5c9893fe8744e4d31336cdfc532bb78d"},"schema_version":"1.0","source":{"id":"2505.02331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02331","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02331v2","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02331","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"pith_short_12","alias_value":"Z5LEDNXBBIS6","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"pith_short_16","alias_value":"Z5LEDNXBBIS6SRVR","created_at":"2026-07-05T11:47:22Z"},{"alias_kind":"pith_short_8","alias_value":"Z5LEDNXB","created_at":"2026-07-05T11:47:22Z"}],"graph_snapshots":[{"event_id":"sha256:a2da229e6c7cb5fab8071d80d0448481dce0cc1fd3b438bcaa8fb74db9cca4d7","target":"graph","created_at":"2026-07-05T11:47:22Z","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/2505.02331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However, AVER remains challenging due to the inherent ambiguity of emotional expressions, cross-modal expressive disparities, and the scarcity of reliably annotated data. Recent self-supervised AVER approaches have introduced strong multimodal representations, yet they predominantly rely on modality-specific encoders and coarse content-level alignment, limiting fine-grained emotional semantic modeling. To address these issu","authors_text":"Hao Cheng, Jia Li, Meng Wang, Richang Hong, Yichao He, Zhenzhen Hu, Zhiwei Zhao","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T03:00:51Z","title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02331","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:dcd94b08bdf844615e747b774b9d91b4b0611f8d5c8ecaec57036e26e355b6de","target":"record","created_at":"2026-07-05T11:47:22Z","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":"4e85b53e0fd14eb09864aa1beac0fe97f1642e16c77d616783a3f178cbd41838","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T03:00:51Z","title_canon_sha256":"3134381c6b0e45a5903dac9bcbe1034c5c9893fe8744e4d31336cdfc532bb78d"},"schema_version":"1.0","source":{"id":"2505.02331","kind":"arxiv","version":2}},"canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf5641b6e10a25e946b19c73e1dca83aedc7857594ceb7fba8a7d8369dec7145","first_computed_at":"2026-07-05T11:47:22.531534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:22.531534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qmpj6Qua9iPSuJ+ey8QB8lR/GfHCnrrTGXnB2X2eBwQnu0pY08qvNNRJfQebCmMUfOHOmsAewKVSeUWf6D56Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:22.532017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcd94b08bdf844615e747b774b9d91b4b0611f8d5c8ecaec57036e26e355b6de","sha256:a2da229e6c7cb5fab8071d80d0448481dce0cc1fd3b438bcaa8fb74db9cca4d7"],"state_sha256":"79d89c45098dbb45eaebddee4748ce4ddd5e68a533260d6ee6b4ab40d109ef3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yoI3SNrtv5MVF6vAptw//Z0dnmou9OcfiEkGh3zZD+gR1H7cgyVODSK0KQJW7Slj2gWEi4FWHGqKZOld0W/SCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T14:57:15.693753Z","bundle_sha256":"254cb018ba9ae21c8e0f3552f0a8522d054e5535cbb77762c734c9790dcdee80"}}