{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:C5S5PV3MUIT7SW4ZEQJ7DPZ7WM","short_pith_number":"pith:C5S5PV3M","canonical_record":{"source":{"id":"2201.03217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-10T08:55:52Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"be7cb483728cb90be43c05823c7c654a5faca5c15a8bf2a458163854af5080c2","abstract_canon_sha256":"ba47bf841f3c85e1ad16ce98880b609557da0e8d51d3a1a0a665706d45f1a85a"},"schema_version":"1.0"},"canonical_sha256":"1765d7d76ca227f95b992413f1bf3fb307972bb416eb3fe5841991704f56655e","source":{"kind":"arxiv","id":"2201.03217","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.03217","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"arxiv_version","alias_value":"2201.03217v2","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03217","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"pith_short_12","alias_value":"C5S5PV3MUIT7","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"pith_short_16","alias_value":"C5S5PV3MUIT7SW4Z","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"pith_short_8","alias_value":"C5S5PV3M","created_at":"2026-07-05T04:47:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:C5S5PV3MUIT7SW4ZEQJ7DPZ7WM","target":"record","payload":{"canonical_record":{"source":{"id":"2201.03217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-10T08:55:52Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"be7cb483728cb90be43c05823c7c654a5faca5c15a8bf2a458163854af5080c2","abstract_canon_sha256":"ba47bf841f3c85e1ad16ce98880b609557da0e8d51d3a1a0a665706d45f1a85a"},"schema_version":"1.0"},"canonical_sha256":"1765d7d76ca227f95b992413f1bf3fb307972bb416eb3fe5841991704f56655e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:11.602146Z","signature_b64":"OrpNZGxn50YlTGWeth2OiVQzHhFNasN+59JzwXmKZfLW7KXFvSxBpUNvAlu98pmwQxzp2TGurvB6gRMQzM2pDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1765d7d76ca227f95b992413f1bf3fb307972bb416eb3fe5841991704f56655e","last_reissued_at":"2026-07-05T04:47:11.601672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:11.601672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.03217","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":"2026-07-05T04:47:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIU1lDknYmNTZJMugQbLM/jvp8WproWj/5xCTwKCVIgldWMu9bAat2es0tsma00ldRyU9aodpde9SCmR4aL5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:23:20.764241Z"},"content_sha256":"6bb7c41264967ba4accb606be2aa3df1cd6f03e4cd55857d2f614adbd6090bf1","schema_version":"1.0","event_id":"sha256:6bb7c41264967ba4accb606be2aa3df1cd6f03e4cd55857d2f614adbd6090bf1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:C5S5PV3MUIT7SW4ZEQJ7DPZ7WM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Local Information Assisted Attention-free Decoder for Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Feiyang Xiao, Haiyan Lan, Jian Guan, Qiaoxi Zhu, Wenwu Wang","submitted_at":"2022-01-10T08:55:52Z","abstract_excerpt":"Automated audio captioning aims to describe audio data with captions using natural language. Existing methods often employ an encoder-decoder structure, where the attention-based decoder (e.g., Transformer decoder) is widely used and achieves state-of-the-art performance. Although this method effectively captures global information within audio data via the self-attention mechanism, it may ignore the event with short time duration, due to its limitation in capturing local information in an audio signal, leading to inaccurate prediction of captions. To address this issue, we propose a method us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03217","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/2201.03217/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":"2026-07-05T04:47:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0D+bgZHnxxumAPakskEX78ZhVCTpWlrt0X1MRdAWJ/n2EpKXgrCMgFPy5kM5vxG9qzRBXQdhDFn2ssVRCeiTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:23:20.764658Z"},"content_sha256":"bf5aa00a3c097dd2df9aac76ff3699557e87a5256ece73afb2c5f7a6a0d415b6","schema_version":"1.0","event_id":"sha256:bf5aa00a3c097dd2df9aac76ff3699557e87a5256ece73afb2c5f7a6a0d415b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM/bundle.json","state_url":"https://pith.science/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM/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":"2026-07-08T16:23:20Z","links":{"resolver":"https://pith.science/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM","bundle":"https://pith.science/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM/bundle.json","state":"https://pith.science/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5S5PV3MUIT7SW4ZEQJ7DPZ7WM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:C5S5PV3MUIT7SW4ZEQJ7DPZ7WM","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":"ba47bf841f3c85e1ad16ce98880b609557da0e8d51d3a1a0a665706d45f1a85a","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-10T08:55:52Z","title_canon_sha256":"be7cb483728cb90be43c05823c7c654a5faca5c15a8bf2a458163854af5080c2"},"schema_version":"1.0","source":{"id":"2201.03217","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.03217","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"arxiv_version","alias_value":"2201.03217v2","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03217","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"pith_short_12","alias_value":"C5S5PV3MUIT7","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"pith_short_16","alias_value":"C5S5PV3MUIT7SW4Z","created_at":"2026-07-05T04:47:11Z"},{"alias_kind":"pith_short_8","alias_value":"C5S5PV3M","created_at":"2026-07-05T04:47:11Z"}],"graph_snapshots":[{"event_id":"sha256:bf5aa00a3c097dd2df9aac76ff3699557e87a5256ece73afb2c5f7a6a0d415b6","target":"graph","created_at":"2026-07-05T04:47:11Z","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/2201.03217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning aims to describe audio data with captions using natural language. Existing methods often employ an encoder-decoder structure, where the attention-based decoder (e.g., Transformer decoder) is widely used and achieves state-of-the-art performance. Although this method effectively captures global information within audio data via the self-attention mechanism, it may ignore the event with short time duration, due to its limitation in capturing local information in an audio signal, leading to inaccurate prediction of captions. To address this issue, we propose a method us","authors_text":"Feiyang Xiao, Haiyan Lan, Jian Guan, Qiaoxi Zhu, Wenwu Wang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-10T08:55:52Z","title":"Local Information Assisted Attention-free Decoder for Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03217","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":"sha256:6bb7c41264967ba4accb606be2aa3df1cd6f03e4cd55857d2f614adbd6090bf1","target":"record","created_at":"2026-07-05T04:47:11Z","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":"ba47bf841f3c85e1ad16ce98880b609557da0e8d51d3a1a0a665706d45f1a85a","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-10T08:55:52Z","title_canon_sha256":"be7cb483728cb90be43c05823c7c654a5faca5c15a8bf2a458163854af5080c2"},"schema_version":"1.0","source":{"id":"2201.03217","kind":"arxiv","version":2}},"canonical_sha256":"1765d7d76ca227f95b992413f1bf3fb307972bb416eb3fe5841991704f56655e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1765d7d76ca227f95b992413f1bf3fb307972bb416eb3fe5841991704f56655e","first_computed_at":"2026-07-05T04:47:11.601672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:47:11.601672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OrpNZGxn50YlTGWeth2OiVQzHhFNasN+59JzwXmKZfLW7KXFvSxBpUNvAlu98pmwQxzp2TGurvB6gRMQzM2pDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:47:11.602146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.03217","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bb7c41264967ba4accb606be2aa3df1cd6f03e4cd55857d2f614adbd6090bf1","sha256:bf5aa00a3c097dd2df9aac76ff3699557e87a5256ece73afb2c5f7a6a0d415b6"],"state_sha256":"c19aac123837aac3d3e00f93d2e1047ebbc2ed1f961910cdb93d3b78d3ec48c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/7fsRBWKR5HuAES4cB+kRTIPieBbVSC4oxvqVDeyneHU3LPyeBZoD/3no8syJ0ObvjR6Yc8DcHvIaMwByGgAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:23:20.766831Z","bundle_sha256":"e1b25c3a83ec394ce8c276e72245a3d21077093de98c8134ed1c851d86ee8c17"}}