{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FEC3TV3ZK3KDQBACDDFTRGZ42G","short_pith_number":"pith:FEC3TV3Z","canonical_record":{"source":{"id":"2108.02752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-05T17:34:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"73355a6ac37d99be78b0fc4c1c471a2feeb8f4de5c65d2bf273f44e411a7fed8","abstract_canon_sha256":"523bcc4b399b800ed6ff9f7c9ccd7d926f438613976a0fd9ee095c691aefd213"},"schema_version":"1.0"},"canonical_sha256":"2905b9d77956d438040218cb389b3cd1a6d54d1e932b21d5e444e88573ff8aa1","source":{"kind":"arxiv","id":"2108.02752","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02752","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02752v1","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02752","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"FEC3TV3ZK3KD","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"FEC3TV3ZK3KDQBAC","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"FEC3TV3Z","created_at":"2026-07-05T03:03:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FEC3TV3ZK3KDQBACDDFTRGZ42G","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-05T17:34:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"73355a6ac37d99be78b0fc4c1c471a2feeb8f4de5c65d2bf273f44e411a7fed8","abstract_canon_sha256":"523bcc4b399b800ed6ff9f7c9ccd7d926f438613976a0fd9ee095c691aefd213"},"schema_version":"1.0"},"canonical_sha256":"2905b9d77956d438040218cb389b3cd1a6d54d1e932b21d5e444e88573ff8aa1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:35.960150Z","signature_b64":"pqORrMYAU4F51qIjszBMy0XXEIPnV1OIXdnXM4tbiueig5W8Fe++H0TPCkis2uH5n2ybzY+adr9uTnnbVeWgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2905b9d77956d438040218cb389b3cd1a6d54d1e932b21d5e444e88573ff8aa1","last_reissued_at":"2026-07-05T03:03:35.959708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:35.959708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02752","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":"2026-07-05T03:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJDLA6XoSiYGt8alagUXmf+kPrVtPnhzQSyN0w2RxyizGEGezZwNr2E1EVDaWfUwuL5RbilOpW7Sd6YColXADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:21:02.406870Z"},"content_sha256":"cf17749ce60104b210d53cd9dd60816c4d44dccf92a4f2b97d9e682baf88f31b","schema_version":"1.0","event_id":"sha256:cf17749ce60104b210d53cd9dd60816c4d44dccf92a4f2b97d9e682baf88f31b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FEC3TV3ZK3KDQBACDDFTRGZ42G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Gengyun Chen, H Lilian Tang, Jingqian Wu, Jinzheng Zhao, Mark D. Plumbley, Qiushi Huang, Shengchen Li, Tom Ko, Wenwu Wang, Xinhao Mei, Xi Shao, Xubo Liu, Yusong Wu","submitted_at":"2021-08-05T17:34:32Z","abstract_excerpt":"Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture, where the decoder predicts words based on audio features extracted by the encoder. To improve the proposed system, transfer learning from either an upstream audio-related task or a large in-domain dataset is introduced to mitigate the problem induced by data scarcity. Besides, evaluation metrics are incorporated into the optimization of the model with reinforcement learning, which helps address the problem of ``expos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02752","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/2108.02752/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":"2026-07-05T03:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uP0mCfp40aOTZiVrPsXwah7l6uSaImYV78u5tq3IKiaZoqn1qBKSGlxyzfi+3ZeNQDHRj7/pyBd1FaoGEcNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:21:02.407510Z"},"content_sha256":"10c8a2e50c2a7424008b05fdbbe1dd0707f35070022196b23639916204d4bd40","schema_version":"1.0","event_id":"sha256:10c8a2e50c2a7424008b05fdbbe1dd0707f35070022196b23639916204d4bd40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G/bundle.json","state_url":"https://pith.science/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G/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":"2026-07-06T23:21:02Z","links":{"resolver":"https://pith.science/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G","bundle":"https://pith.science/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G/bundle.json","state":"https://pith.science/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEC3TV3ZK3KDQBACDDFTRGZ42G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FEC3TV3ZK3KDQBACDDFTRGZ42G","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":"523bcc4b399b800ed6ff9f7c9ccd7d926f438613976a0fd9ee095c691aefd213","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-05T17:34:32Z","title_canon_sha256":"73355a6ac37d99be78b0fc4c1c471a2feeb8f4de5c65d2bf273f44e411a7fed8"},"schema_version":"1.0","source":{"id":"2108.02752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02752","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02752v1","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02752","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"FEC3TV3ZK3KD","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"FEC3TV3ZK3KDQBAC","created_at":"2026-07-05T03:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"FEC3TV3Z","created_at":"2026-07-05T03:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:10c8a2e50c2a7424008b05fdbbe1dd0707f35070022196b23639916204d4bd40","target":"graph","created_at":"2026-07-05T03:03:35Z","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/2108.02752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture, where the decoder predicts words based on audio features extracted by the encoder. To improve the proposed system, transfer learning from either an upstream audio-related task or a large in-domain dataset is introduced to mitigate the problem induced by data scarcity. Besides, evaluation metrics are incorporated into the optimization of the model with reinforcement learning, which helps address the problem of ``expos","authors_text":"Gengyun Chen, H Lilian Tang, Jingqian Wu, Jinzheng Zhao, Mark D. Plumbley, Qiushi Huang, Shengchen Li, Tom Ko, Wenwu Wang, Xinhao Mei, Xi Shao, Xubo Liu, Yusong Wu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-05T17:34:32Z","title":"An Encoder-Decoder Based Audio Captioning System With Transfer and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02752","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:cf17749ce60104b210d53cd9dd60816c4d44dccf92a4f2b97d9e682baf88f31b","target":"record","created_at":"2026-07-05T03:03:35Z","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":"523bcc4b399b800ed6ff9f7c9ccd7d926f438613976a0fd9ee095c691aefd213","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-05T17:34:32Z","title_canon_sha256":"73355a6ac37d99be78b0fc4c1c471a2feeb8f4de5c65d2bf273f44e411a7fed8"},"schema_version":"1.0","source":{"id":"2108.02752","kind":"arxiv","version":1}},"canonical_sha256":"2905b9d77956d438040218cb389b3cd1a6d54d1e932b21d5e444e88573ff8aa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2905b9d77956d438040218cb389b3cd1a6d54d1e932b21d5e444e88573ff8aa1","first_computed_at":"2026-07-05T03:03:35.959708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:35.959708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pqORrMYAU4F51qIjszBMy0XXEIPnV1OIXdnXM4tbiueig5W8Fe++H0TPCkis2uH5n2ybzY+adr9uTnnbVeWgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:35.960150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf17749ce60104b210d53cd9dd60816c4d44dccf92a4f2b97d9e682baf88f31b","sha256:10c8a2e50c2a7424008b05fdbbe1dd0707f35070022196b23639916204d4bd40"],"state_sha256":"766f239ae7da168e3ec8c609aa4dbbc5fbdf4a97eaf6824e9c1ce934321f3dfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysZ1uUqqcHF2j9FM8JW6gBoIqz6blt4gymgx3OiPwiVXRPbVcxpQMF2XjfIOtVhaVWZykPpcVNejuuINKSopBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:21:02.410207Z","bundle_sha256":"c24a9239056374be09b53ef47b7afa0096554dd348ee6edb124b4b3cbb3e83e2"}}