{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HMJPEA5G37RNC746TXCM4C3NXA","short_pith_number":"pith:HMJPEA5G","canonical_record":{"source":{"id":"2205.05949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-12T08:36:35Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"71572bdd044841ae288eb8534042dffc4bfb1621f9249626f0d0e3ed267129bb","abstract_canon_sha256":"11458988c1007f375c23fba29fbdf838f8caced88444d41e6880678113890ffb"},"schema_version":"1.0"},"canonical_sha256":"3b12f203a6dfe2d17f9e9dc4ce0b6db8066d597cf1ecd463be6e96372d200d3a","source":{"kind":"arxiv","id":"2205.05949","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05949","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05949v2","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05949","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"HMJPEA5G37RN","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"HMJPEA5G37RNC746","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"HMJPEA5G","created_at":"2026-07-05T05:01:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HMJPEA5G37RNC746TXCM4C3NXA","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-12T08:36:35Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"71572bdd044841ae288eb8534042dffc4bfb1621f9249626f0d0e3ed267129bb","abstract_canon_sha256":"11458988c1007f375c23fba29fbdf838f8caced88444d41e6880678113890ffb"},"schema_version":"1.0"},"canonical_sha256":"3b12f203a6dfe2d17f9e9dc4ce0b6db8066d597cf1ecd463be6e96372d200d3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:01.861287Z","signature_b64":"lZSDMbGQOayjIjKq6ia7mqLr8xitxhe+PAkfea+eBmNSjF0btPakIxWLe1VAGak1EvggzsekDWr35oR/hpujDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b12f203a6dfe2d17f9e9dc4ce0b6db8066d597cf1ecd463be6e96372d200d3a","last_reissued_at":"2026-07-05T05:01:01.860842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:01.860842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05949","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":"2026-07-05T05:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7U/lsZgRgqsvLKxE8HXljIgiqeHIDqSPOosdRFKrsUor1rP/8nV1NiO9ZSee5IiI5Lwb2yEOAhw2E1uMrxWODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:37:06.136973Z"},"content_sha256":"c7b3f7f534746f964bbdc332c0deb62ecaf5de4d4e0efe57f10ab695ad4bb3b8","schema_version":"1.0","event_id":"sha256:c7b3f7f534746f964bbdc332c0deb62ecaf5de4d4e0efe57f10ab695ad4bb3b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HMJPEA5G37RNC746TXCM4C3NXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Mark D. Plumbley, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2022-05-12T08:36:35Z","abstract_excerpt":"Automated audio captioning is a cross-modal translation task that aims to generate natural language descriptions for given audio clips. This task has received increasing attention with the release of freely available datasets in recent years. The problem has been addressed predominantly with deep learning techniques. Numerous approaches have been proposed, such as investigating different neural network architectures, exploiting auxiliary information such as keywords or sentence information to guide caption generation, and employing different training strategies, which have greatly facilitated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05949","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/2205.05949/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":"2026-07-05T05:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qAJtygWVDJKIBcrttr5SzIDwzkgS8h8KGy0lNVetcUlkC4iBH2gxdkcYDHjhqNk8v+55siBhAXbDCYAW+O2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:37:06.137622Z"},"content_sha256":"ce108b802582b267fe5c33ecdc19a8e15d75a8fcd94ed7c1c4d4f3ae6dac434c","schema_version":"1.0","event_id":"sha256:ce108b802582b267fe5c33ecdc19a8e15d75a8fcd94ed7c1c4d4f3ae6dac434c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMJPEA5G37RNC746TXCM4C3NXA/bundle.json","state_url":"https://pith.science/pith/HMJPEA5G37RNC746TXCM4C3NXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMJPEA5G37RNC746TXCM4C3NXA/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":"2026-08-06T18:37:06Z","links":{"resolver":"https://pith.science/pith/HMJPEA5G37RNC746TXCM4C3NXA","bundle":"https://pith.science/pith/HMJPEA5G37RNC746TXCM4C3NXA/bundle.json","state":"https://pith.science/pith/HMJPEA5G37RNC746TXCM4C3NXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMJPEA5G37RNC746TXCM4C3NXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HMJPEA5G37RNC746TXCM4C3NXA","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":"11458988c1007f375c23fba29fbdf838f8caced88444d41e6880678113890ffb","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-12T08:36:35Z","title_canon_sha256":"71572bdd044841ae288eb8534042dffc4bfb1621f9249626f0d0e3ed267129bb"},"schema_version":"1.0","source":{"id":"2205.05949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05949","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05949v2","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05949","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"HMJPEA5G37RN","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"HMJPEA5G37RNC746","created_at":"2026-07-05T05:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"HMJPEA5G","created_at":"2026-07-05T05:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:ce108b802582b267fe5c33ecdc19a8e15d75a8fcd94ed7c1c4d4f3ae6dac434c","target":"graph","created_at":"2026-07-05T05:01:01Z","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/2205.05949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning is a cross-modal translation task that aims to generate natural language descriptions for given audio clips. This task has received increasing attention with the release of freely available datasets in recent years. The problem has been addressed predominantly with deep learning techniques. Numerous approaches have been proposed, such as investigating different neural network architectures, exploiting auxiliary information such as keywords or sentence information to guide caption generation, and employing different training strategies, which have greatly facilitated ","authors_text":"Mark D. Plumbley, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.AI","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-12T08:36:35Z","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05949","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:c7b3f7f534746f964bbdc332c0deb62ecaf5de4d4e0efe57f10ab695ad4bb3b8","target":"record","created_at":"2026-07-05T05:01:01Z","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":"11458988c1007f375c23fba29fbdf838f8caced88444d41e6880678113890ffb","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-05-12T08:36:35Z","title_canon_sha256":"71572bdd044841ae288eb8534042dffc4bfb1621f9249626f0d0e3ed267129bb"},"schema_version":"1.0","source":{"id":"2205.05949","kind":"arxiv","version":2}},"canonical_sha256":"3b12f203a6dfe2d17f9e9dc4ce0b6db8066d597cf1ecd463be6e96372d200d3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b12f203a6dfe2d17f9e9dc4ce0b6db8066d597cf1ecd463be6e96372d200d3a","first_computed_at":"2026-07-05T05:01:01.860842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:01:01.860842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZSDMbGQOayjIjKq6ia7mqLr8xitxhe+PAkfea+eBmNSjF0btPakIxWLe1VAGak1EvggzsekDWr35oR/hpujDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:01:01.861287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7b3f7f534746f964bbdc332c0deb62ecaf5de4d4e0efe57f10ab695ad4bb3b8","sha256:ce108b802582b267fe5c33ecdc19a8e15d75a8fcd94ed7c1c4d4f3ae6dac434c"],"state_sha256":"675af3babecaf9e46645023526e011ff377f45a43890c9ad501ae98de37abf52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+xkXbpDaD5yudEGHeQsUaL0dPG9yMb5CIJyTvshIvkLJ7n9O5Hv23Hs9an1Qx3sIn1ivU1IdATlYxge1I+aDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:37:06.148424Z","bundle_sha256":"f1b227febab62be4c83982e4fb68e00d646eda7686e3d441154e90d883760d49"}}