{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WKWDRUWKWZHQXRSCH5SM2WUV2R","short_pith_number":"pith:WKWDRUWK","canonical_record":{"source":{"id":"2110.06691","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-13T13:03:08Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"38f61bb23c0d0ec2a52564306b4d0567f9d1645b28c8ab4f29b2ca167f1a6f52","abstract_canon_sha256":"46e3846d35d3fa4ff4e9d188c95e4a105d17258cb614fd46e1d0afd9ca02109e"},"schema_version":"1.0"},"canonical_sha256":"b2ac38d2cab64f0bc6423f64cd5a95d47b5992afd53081d49001afd601227e90","source":{"kind":"arxiv","id":"2110.06691","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06691","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06691v2","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06691","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"WKWDRUWKWZHQ","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"WKWDRUWKWZHQXRSC","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"WKWDRUWK","created_at":"2026-07-05T04:09:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WKWDRUWKWZHQXRSCH5SM2WUV2R","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06691","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-13T13:03:08Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"38f61bb23c0d0ec2a52564306b4d0567f9d1645b28c8ab4f29b2ca167f1a6f52","abstract_canon_sha256":"46e3846d35d3fa4ff4e9d188c95e4a105d17258cb614fd46e1d0afd9ca02109e"},"schema_version":"1.0"},"canonical_sha256":"b2ac38d2cab64f0bc6423f64cd5a95d47b5992afd53081d49001afd601227e90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:15.789561Z","signature_b64":"wFNCCpa18Q2auNML3XoLXfExjmFiIcOQ3F1K2uQr7tHbzGtQTX3d0l0R+FBu5M1B2z8UpGLjQQwgQCBJPr2YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2ac38d2cab64f0bc6423f64cd5a95d47b5992afd53081d49001afd601227e90","last_reissued_at":"2026-07-05T04:09:15.789122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:15.789122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06691","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":"2026-07-05T04:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fdP/8DXmhNfbiKn7skJYY9x7d9AnDyNHZvQER5meyS72MVPBFzKnHUCujnBqr4cnSPoFXeom4iFgZavipxZ8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:40:21.431308Z"},"content_sha256":"aa5a00500f56a0432e34d0ec9e86d9adea9f6810f3edffb34ad303be4f9f4a99","schema_version":"1.0","event_id":"sha256:aa5a00500f56a0432e34d0ec9e86d9adea9f6810f3edffb34ad303be4f9f4a99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WKWDRUWKWZHQXRSCH5SM2WUV2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse Audio Captioning via Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jianyuan Sun, Mark D. Plumbley, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2021-10-13T13:03:08Z","abstract_excerpt":"Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum likelihood estimation (MLE),which tends to make captions generic, simple and deterministic. As different people may describe an audio clip from different aspects using distinct words and grammars, we argue that an audio captioning system should have the ability to generate diverse captions for a fixed audio clip and across similar audio clips. To address this probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06691","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/2110.06691/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":"2026-07-05T04:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0t4hAQsg5KOfVnuyInmfrn1OvGe1vN/w/LMii84xVyRw03958Jd9Utk+ub8aTfJgDms5GMckRnUTVzYfWIoaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:40:21.432200Z"},"content_sha256":"6ead36a01609dbfe8f685ad8beec325ad4590cbb226c89762017a8b931edf760","schema_version":"1.0","event_id":"sha256:6ead36a01609dbfe8f685ad8beec325ad4590cbb226c89762017a8b931edf760"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R/bundle.json","state_url":"https://pith.science/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R/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":"2026-08-15T17:40:21Z","links":{"resolver":"https://pith.science/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R","bundle":"https://pith.science/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R/bundle.json","state":"https://pith.science/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKWDRUWKWZHQXRSCH5SM2WUV2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WKWDRUWKWZHQXRSCH5SM2WUV2R","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":"46e3846d35d3fa4ff4e9d188c95e4a105d17258cb614fd46e1d0afd9ca02109e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-13T13:03:08Z","title_canon_sha256":"38f61bb23c0d0ec2a52564306b4d0567f9d1645b28c8ab4f29b2ca167f1a6f52"},"schema_version":"1.0","source":{"id":"2110.06691","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06691","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06691v2","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06691","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"WKWDRUWKWZHQ","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"WKWDRUWKWZHQXRSC","created_at":"2026-07-05T04:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"WKWDRUWK","created_at":"2026-07-05T04:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:6ead36a01609dbfe8f685ad8beec325ad4590cbb226c89762017a8b931edf760","target":"graph","created_at":"2026-07-05T04:09:15Z","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/2110.06691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum likelihood estimation (MLE),which tends to make captions generic, simple and deterministic. As different people may describe an audio clip from different aspects using distinct words and grammars, we argue that an audio captioning system should have the ability to generate diverse captions for a fixed audio clip and across similar audio clips. To address this probl","authors_text":"Jianyuan Sun, Mark D. Plumbley, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-13T13:03:08Z","title":"Diverse Audio Captioning via Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06691","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:aa5a00500f56a0432e34d0ec9e86d9adea9f6810f3edffb34ad303be4f9f4a99","target":"record","created_at":"2026-07-05T04:09:15Z","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":"46e3846d35d3fa4ff4e9d188c95e4a105d17258cb614fd46e1d0afd9ca02109e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-13T13:03:08Z","title_canon_sha256":"38f61bb23c0d0ec2a52564306b4d0567f9d1645b28c8ab4f29b2ca167f1a6f52"},"schema_version":"1.0","source":{"id":"2110.06691","kind":"arxiv","version":2}},"canonical_sha256":"b2ac38d2cab64f0bc6423f64cd5a95d47b5992afd53081d49001afd601227e90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2ac38d2cab64f0bc6423f64cd5a95d47b5992afd53081d49001afd601227e90","first_computed_at":"2026-07-05T04:09:15.789122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:15.789122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wFNCCpa18Q2auNML3XoLXfExjmFiIcOQ3F1K2uQr7tHbzGtQTX3d0l0R+FBu5M1B2z8UpGLjQQwgQCBJPr2YBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:15.789561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06691","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa5a00500f56a0432e34d0ec9e86d9adea9f6810f3edffb34ad303be4f9f4a99","sha256:6ead36a01609dbfe8f685ad8beec325ad4590cbb226c89762017a8b931edf760"],"state_sha256":"cb0ed450cd2b8fd17849b7e138258bd4485d7e6e45e413f62d7ef9f9a8d55272"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3U0Qg2Ez81QwAUJ3yEzCeSu8FBro9MfGAYLTliGV0rAuSQt4kRafdKfuBsph6i3uAlaMJKq8P2gIKlqy5v9YCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:40:21.436683Z","bundle_sha256":"fe1f3cb9218c97b69f42cac1b9579df10511c05ae1c3e6ad9286635682ecadc6"}}