{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IOKY5FSI6H5TVHVQ4J4IMJZ3BW","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":"ea48713bc89285eebfdccd7e859d54c13206b560477921b25eca8b66a923a7b1","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T00:31:50Z","title_canon_sha256":"fdb6a0c86b4b232663a23c7b229b0672980b1ea78f93f2fc79c508b3f1bb28d7"},"schema_version":"1.0","source":{"id":"2107.09817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09817","created_at":"2026-07-05T02:59:39Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09817v1","created_at":"2026-07-05T02:59:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09817","created_at":"2026-07-05T02:59:39Z"},{"alias_kind":"pith_short_12","alias_value":"IOKY5FSI6H5T","created_at":"2026-07-05T02:59:39Z"},{"alias_kind":"pith_short_16","alias_value":"IOKY5FSI6H5TVHVQ","created_at":"2026-07-05T02:59:39Z"},{"alias_kind":"pith_short_8","alias_value":"IOKY5FSI","created_at":"2026-07-05T02:59:39Z"}],"graph_snapshots":[{"event_id":"sha256:79f34ba95005db814819e3c70a16eafc304bb22a9f3842108ef92e35ab9a56aa","target":"graph","created_at":"2026-07-05T02:59:39Z","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/2107.09817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio captioning aims to automatically generate a natural language description of an audio clip. Most captioning models follow an encoder-decoder architecture, where the decoder predicts words based on the audio features extracted by the encoder. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are often used as the audio encoder. However, CNNs can be limited in modelling temporal relationships among the time frames in an audio signal, while RNNs can be limited in modelling the long-range dependencies among the time frames. In this paper, we propose an Audio Captioning","authors_text":"Mark D. Plumbley, Qiushi Huang, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T00:31:50Z","title":"Audio Captioning Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09817","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":"sha256:88f66074c82b26c5a724d8b9c3703ac2f84dc9adc9be0c9449531873782f18c1","target":"record","created_at":"2026-07-05T02:59:39Z","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":"ea48713bc89285eebfdccd7e859d54c13206b560477921b25eca8b66a923a7b1","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-21T00:31:50Z","title_canon_sha256":"fdb6a0c86b4b232663a23c7b229b0672980b1ea78f93f2fc79c508b3f1bb28d7"},"schema_version":"1.0","source":{"id":"2107.09817","kind":"arxiv","version":1}},"canonical_sha256":"43958e9648f1fb3a9eb0e27886273b0d934507bbaccde9dc91a1f793062502b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43958e9648f1fb3a9eb0e27886273b0d934507bbaccde9dc91a1f793062502b6","first_computed_at":"2026-07-05T02:59:39.819583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:39.819583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aeIhugZwEeiG1z2TI4b+5VdDDhTVLioXY4WfXaOAbEYXLSePI7bXrUfJpq/Lcb+oOuEekrXdXUQhogEMg++UAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:39.819972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88f66074c82b26c5a724d8b9c3703ac2f84dc9adc9be0c9449531873782f18c1","sha256:79f34ba95005db814819e3c70a16eafc304bb22a9f3842108ef92e35ab9a56aa"],"state_sha256":"d311f4759f98ff58fa0e94b978b33b844b3bf47e4b62da3d8b9a8b0ef0de7caf"}