{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IFHJHNIBWNZHSGBNH27BUXFJTL","short_pith_number":"pith:IFHJHNIB","canonical_record":{"source":{"id":"2309.07925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T03:19:10Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"d339ccb67d2f2692d526fd6f59b5cf8b9263cf1cc4b18d3c37795ba4f0201434","abstract_canon_sha256":"5cdbff8e9f6e33d06478f5f6db39c4bd1edda13a702c387de5803173c3e477c0"},"schema_version":"1.0"},"canonical_sha256":"414e93b501b37279182d3ebe1a5ca99af0bce3377d196f3af830f2d74c0b5c08","source":{"kind":"arxiv","id":"2309.07925","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07925","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07925v1","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07925","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"IFHJHNIBWNZH","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"IFHJHNIBWNZHSGBN","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"IFHJHNIB","created_at":"2026-07-05T06:50:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IFHJHNIBWNZHSGBNH27BUXFJTL","target":"record","payload":{"canonical_record":{"source":{"id":"2309.07925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T03:19:10Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"d339ccb67d2f2692d526fd6f59b5cf8b9263cf1cc4b18d3c37795ba4f0201434","abstract_canon_sha256":"5cdbff8e9f6e33d06478f5f6db39c4bd1edda13a702c387de5803173c3e477c0"},"schema_version":"1.0"},"canonical_sha256":"414e93b501b37279182d3ebe1a5ca99af0bce3377d196f3af830f2d74c0b5c08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:59.324965Z","signature_b64":"/7wlWaZ6UW5i5298/4disAjag8jDAD3wwWgZ7sCJjLVSvPtELAahhoqOYo/Rb1qjoPNeQOfey9O/hAB86GjmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414e93b501b37279182d3ebe1a5ca99af0bce3377d196f3af830f2d74c0b5c08","last_reissued_at":"2026-07-05T06:50:59.324500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:59.324500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.07925","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":"2026-07-05T06:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17JN6cl8Dv6fa9I6Cgouw9oTfbRrQyQQKPyhd/YGr9o/8tGYck28TINienY0lm885G/FntTU2vY8SYBoMqaBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:13:05.043974Z"},"content_sha256":"a3eef57895bfd4cf26dc48f69bc57e1c9b0e23b7439b642890307beac5620e14","schema_version":"1.0","event_id":"sha256:a3eef57895bfd4cf26dc48f69bc57e1c9b0e23b7439b642890307beac5620e14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IFHJHNIBWNZHSGBNH27BUXFJTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenxi Wang, Hang Chen, Haotian Wang, Hengshun Zhou, Jiefeng Ma, Jie Zhang, Jun Du, Pengfei Hu, Qing Wang, Shi Cheng, Ya Jiang, Yan Song, Yuxuan Xi, Yuzhe Weng","submitted_at":"2023-09-11T03:19:10Z","abstract_excerpt":"In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion. Then, we introduce a joint decoding structure for emotion classification and valence regression in the decoding stage. A multi-task loss based on uncertainty is also designed to optimize the whole process. Finally, by combining three different structu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07925","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/2309.07925/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":"2026-07-05T06:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrUbX/TyyocYFqLQZQ0XyedbJUpQwR+x3+cRq332zATaqyp/gs39db2Q6o80jBbs+vpfuz/w4PlAOh+Ys1pKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:13:05.044375Z"},"content_sha256":"460312e35b68e53dc93959142724e8ac90626ad232370b57d3aba3fbeffef01f","schema_version":"1.0","event_id":"sha256:460312e35b68e53dc93959142724e8ac90626ad232370b57d3aba3fbeffef01f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFHJHNIBWNZHSGBNH27BUXFJTL/bundle.json","state_url":"https://pith.science/pith/IFHJHNIBWNZHSGBNH27BUXFJTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFHJHNIBWNZHSGBNH27BUXFJTL/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":"2026-07-06T18:13:05Z","links":{"resolver":"https://pith.science/pith/IFHJHNIBWNZHSGBNH27BUXFJTL","bundle":"https://pith.science/pith/IFHJHNIBWNZHSGBNH27BUXFJTL/bundle.json","state":"https://pith.science/pith/IFHJHNIBWNZHSGBNH27BUXFJTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFHJHNIBWNZHSGBNH27BUXFJTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IFHJHNIBWNZHSGBNH27BUXFJTL","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":"5cdbff8e9f6e33d06478f5f6db39c4bd1edda13a702c387de5803173c3e477c0","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T03:19:10Z","title_canon_sha256":"d339ccb67d2f2692d526fd6f59b5cf8b9263cf1cc4b18d3c37795ba4f0201434"},"schema_version":"1.0","source":{"id":"2309.07925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07925","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07925v1","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07925","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"IFHJHNIBWNZH","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"IFHJHNIBWNZHSGBN","created_at":"2026-07-05T06:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"IFHJHNIB","created_at":"2026-07-05T06:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:460312e35b68e53dc93959142724e8ac90626ad232370b57d3aba3fbeffef01f","target":"graph","created_at":"2026-07-05T06:50:59Z","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/2309.07925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion. Then, we introduce a joint decoding structure for emotion classification and valence regression in the decoding stage. A multi-task loss based on uncertainty is also designed to optimize the whole process. Finally, by combining three different structu","authors_text":"Chenxi Wang, Hang Chen, Haotian Wang, Hengshun Zhou, Jiefeng Ma, Jie Zhang, Jun Du, Pengfei Hu, Qing Wang, Shi Cheng, Ya Jiang, Yan Song, Yuxuan Xi, Yuzhe Weng","cross_cats":["cs.AI","cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T03:19:10Z","title":"Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07925","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:a3eef57895bfd4cf26dc48f69bc57e1c9b0e23b7439b642890307beac5620e14","target":"record","created_at":"2026-07-05T06:50:59Z","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":"5cdbff8e9f6e33d06478f5f6db39c4bd1edda13a702c387de5803173c3e477c0","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-11T03:19:10Z","title_canon_sha256":"d339ccb67d2f2692d526fd6f59b5cf8b9263cf1cc4b18d3c37795ba4f0201434"},"schema_version":"1.0","source":{"id":"2309.07925","kind":"arxiv","version":1}},"canonical_sha256":"414e93b501b37279182d3ebe1a5ca99af0bce3377d196f3af830f2d74c0b5c08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"414e93b501b37279182d3ebe1a5ca99af0bce3377d196f3af830f2d74c0b5c08","first_computed_at":"2026-07-05T06:50:59.324500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:59.324500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/7wlWaZ6UW5i5298/4disAjag8jDAD3wwWgZ7sCJjLVSvPtELAahhoqOYo/Rb1qjoPNeQOfey9O/hAB86GjmAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:59.324965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3eef57895bfd4cf26dc48f69bc57e1c9b0e23b7439b642890307beac5620e14","sha256:460312e35b68e53dc93959142724e8ac90626ad232370b57d3aba3fbeffef01f"],"state_sha256":"f691a45e6f823271dbf6f6fdfa47020085a9456131260ee8c95dcbfb37550e74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B80MGo+HfBqkABaVnL2hDY6zfYper8BB9LQ8KOSkFcSPG0TUtxaOxKfubny77QXIRIrbgDjafFvf4mlRiCgVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:13:05.046587Z","bundle_sha256":"930a7c112a6c6e6d078ada7bb409af41b88d901d9f672c43a2b66936a4121a1f"}}