{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AX56RZW6RBEAAYBE7YM4Q5IO33","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":"833afc5ca400f191ea469b2f17d658c5c13b6791a70635d462817e742ff25c09","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-06T00:05:58Z","title_canon_sha256":"cf5d07098970e27e4e1c79a8a85c42fd45ba4c943fe3c525add9f46e0b313bab"},"schema_version":"1.0","source":{"id":"2203.02838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02838","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02838v2","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02838","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"AX56RZW6RBEA","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"AX56RZW6RBEAAYBE","created_at":"2026-07-05T04:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"AX56RZW6","created_at":"2026-07-05T04:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:b2a9c6ccc59c1c5741da71f7af940602fd6b31b964810111e11b5d5c3bb8c844","target":"graph","created_at":"2026-07-05T04:09:02Z","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/2203.02838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio encoder and then a language decoder is used to generate the captions. Training an audio captioning system often encounters the problem of data scarcity. Transferring knowledge from pre-trained audio models such as Pre-trained Audio Neural Networks (PANNs) have recently emerged as a useful method to mitigate this issue. However, there is less attention on exploiti","authors_text":"Haohe Liu, Jianyuan Sun, Jinzheng Zhao, Mark D. Plumbley, Qiushi Huang, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-06T00:05:58Z","title":"Leveraging Pre-trained BERT for Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02838","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":"sha256:8b7a08fd3850f2483a044f5e24be33b890cd6639ee4e4f86912743950df36aef","target":"record","created_at":"2026-07-05T04:09:02Z","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":"833afc5ca400f191ea469b2f17d658c5c13b6791a70635d462817e742ff25c09","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-06T00:05:58Z","title_canon_sha256":"cf5d07098970e27e4e1c79a8a85c42fd45ba4c943fe3c525add9f46e0b313bab"},"schema_version":"1.0","source":{"id":"2203.02838","kind":"arxiv","version":2}},"canonical_sha256":"05fbe8e6de8848006024fe19c8750edec021e0597406391fb04e0749c79f8b34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05fbe8e6de8848006024fe19c8750edec021e0597406391fb04e0749c79f8b34","first_computed_at":"2026-07-05T04:09:02.438463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:02.438463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GnqtqfKFuivN62WR8mjzmZnknyHqoUJvxJWod5ikD3JF60gbKMOoZdrNDAvAKEqgM4x4W3564VgZy4cQ8x9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:02.438933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b7a08fd3850f2483a044f5e24be33b890cd6639ee4e4f86912743950df36aef","sha256:b2a9c6ccc59c1c5741da71f7af940602fd6b31b964810111e11b5d5c3bb8c844"],"state_sha256":"c134c4278a4a9c136e140c083cbc9b630adda27db0589d0c856de7d66c457676"}