{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JD3NCN2ZTII3AT5FICJY3MHVFR","short_pith_number":"pith:JD3NCN2Z","canonical_record":{"source":{"id":"2304.03586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-07T10:58:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9e1a877f6d040baa77caaacc4ed4b453a740cb3a69942e5e76fba5293e3bee50","abstract_canon_sha256":"3674f8516c4a29f0d65959e7beda27f423b24d70130796d87392f37c9071aedd"},"schema_version":"1.0"},"canonical_sha256":"48f6d137599a11b04fa540938db0f52c553aed9c8578716f14bf6cd4a10bf5d4","source":{"kind":"arxiv","id":"2304.03586","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03586","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03586v2","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03586","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"JD3NCN2ZTII3","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"JD3NCN2ZTII3AT5F","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"JD3NCN2Z","created_at":"2026-07-05T05:59:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JD3NCN2ZTII3AT5FICJY3MHVFR","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-07T10:58:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9e1a877f6d040baa77caaacc4ed4b453a740cb3a69942e5e76fba5293e3bee50","abstract_canon_sha256":"3674f8516c4a29f0d65959e7beda27f423b24d70130796d87392f37c9071aedd"},"schema_version":"1.0"},"canonical_sha256":"48f6d137599a11b04fa540938db0f52c553aed9c8578716f14bf6cd4a10bf5d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:24.446603Z","signature_b64":"gBsQSjB0uHEF+q+ECtK0IjL1aojgsdrl62g48F+0hgCGN3/VJ735cFWFFZetVDnSNrNdPvV6y3Jb1WBLwmPcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48f6d137599a11b04fa540938db0f52c553aed9c8578716f14bf6cd4a10bf5d4","last_reissued_at":"2026-07-05T05:59:24.446209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:24.446209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03586","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":"2026-07-05T05:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e2YaxxUdyh9GlxbOWztf/tgVJ3ejqmBoF5Pz+K+9L+o3EF3fXWtSnC3iY7qDYZ+MITlcpyNsnQMsdwwQbak/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T23:35:49.122725Z"},"content_sha256":"0fc578c9ed37fd2db657c7dbbf9b6e635fd04a91bda4fc6b4245be45e28bb1e5","schema_version":"1.0","event_id":"sha256:0fc578c9ed37fd2db657c7dbbf9b6e635fd04a91bda4fc6b4245be45e28bb1e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JD3NCN2ZTII3AT5FICJY3MHVFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Attention for Automated Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feiyang Xiao, Jian Guan, Qiaoxi Zhu, Wenwu Wang","submitted_at":"2023-04-07T10:58:12Z","abstract_excerpt":"State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing the long-time dependencies within an audio signal, thereby leading to potential performance degradation in audio captioning. This letter presents a novel method using graph attention (GraphAC) for encoder-decoder based audio captioning. In the encoder, a graph attention module is introduced after the PANNs to learn contextual association (i.e. the dependenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03586","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/2304.03586/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":"2026-07-05T05:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+TOPQaETSL2udxSS4UN00Z1neHVzmLGsDF+xUe+VYO+nhydV28mPA0ORSkeEepvljRmUVBZdH97HXxw1xlaJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T23:35:49.123099Z"},"content_sha256":"95cb4a381350b6ee41c479417df3b031dc3a8ac155891ee47c8556cea836b43a","schema_version":"1.0","event_id":"sha256:95cb4a381350b6ee41c479417df3b031dc3a8ac155891ee47c8556cea836b43a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JD3NCN2ZTII3AT5FICJY3MHVFR/bundle.json","state_url":"https://pith.science/pith/JD3NCN2ZTII3AT5FICJY3MHVFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JD3NCN2ZTII3AT5FICJY3MHVFR/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":"2026-07-14T23:35:49Z","links":{"resolver":"https://pith.science/pith/JD3NCN2ZTII3AT5FICJY3MHVFR","bundle":"https://pith.science/pith/JD3NCN2ZTII3AT5FICJY3MHVFR/bundle.json","state":"https://pith.science/pith/JD3NCN2ZTII3AT5FICJY3MHVFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JD3NCN2ZTII3AT5FICJY3MHVFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JD3NCN2ZTII3AT5FICJY3MHVFR","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":"3674f8516c4a29f0d65959e7beda27f423b24d70130796d87392f37c9071aedd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-07T10:58:12Z","title_canon_sha256":"9e1a877f6d040baa77caaacc4ed4b453a740cb3a69942e5e76fba5293e3bee50"},"schema_version":"1.0","source":{"id":"2304.03586","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03586","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03586v2","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03586","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"JD3NCN2ZTII3","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"JD3NCN2ZTII3AT5F","created_at":"2026-07-05T05:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"JD3NCN2Z","created_at":"2026-07-05T05:59:24Z"}],"graph_snapshots":[{"event_id":"sha256:95cb4a381350b6ee41c479417df3b031dc3a8ac155891ee47c8556cea836b43a","target":"graph","created_at":"2026-07-05T05:59:24Z","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/2304.03586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing the long-time dependencies within an audio signal, thereby leading to potential performance degradation in audio captioning. This letter presents a novel method using graph attention (GraphAC) for encoder-decoder based audio captioning. In the encoder, a graph attention module is introduced after the PANNs to learn contextual association (i.e. the dependenc","authors_text":"Feiyang Xiao, Jian Guan, Qiaoxi Zhu, Wenwu Wang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-07T10:58:12Z","title":"Graph Attention for Automated Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03586","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":"sha256:0fc578c9ed37fd2db657c7dbbf9b6e635fd04a91bda4fc6b4245be45e28bb1e5","target":"record","created_at":"2026-07-05T05:59:24Z","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":"3674f8516c4a29f0d65959e7beda27f423b24d70130796d87392f37c9071aedd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-07T10:58:12Z","title_canon_sha256":"9e1a877f6d040baa77caaacc4ed4b453a740cb3a69942e5e76fba5293e3bee50"},"schema_version":"1.0","source":{"id":"2304.03586","kind":"arxiv","version":2}},"canonical_sha256":"48f6d137599a11b04fa540938db0f52c553aed9c8578716f14bf6cd4a10bf5d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48f6d137599a11b04fa540938db0f52c553aed9c8578716f14bf6cd4a10bf5d4","first_computed_at":"2026-07-05T05:59:24.446209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:24.446209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gBsQSjB0uHEF+q+ECtK0IjL1aojgsdrl62g48F+0hgCGN3/VJ735cFWFFZetVDnSNrNdPvV6y3Jb1WBLwmPcCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:24.446603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03586","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fc578c9ed37fd2db657c7dbbf9b6e635fd04a91bda4fc6b4245be45e28bb1e5","sha256:95cb4a381350b6ee41c479417df3b031dc3a8ac155891ee47c8556cea836b43a"],"state_sha256":"00f201db623ad43fc8a43c726893189be0195f8332a86a83405b83739e4cae1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldLIzhjnkb3C2SfA5dOJJQxIHoM0FNSEfi/e2sURncfz5ZDesos2uHaraij6Vqvu0g5chcgyXQeTf8x4y7vmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T23:35:49.125377Z","bundle_sha256":"2d156eadcdd6e9ca6805dd852b722889d7defcac8240d96f9aff45bcb0bd4a70"}}