{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NCOY2E5DBQOGU5ARRSRV6KJZJL","short_pith_number":"pith:NCOY2E5D","canonical_record":{"source":{"id":"2406.13275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-19T07:09:46Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"91c9bcdd5465ad8c460b0a5debf2cd95654e859688f37c352af99f4f5e81c8dc","abstract_canon_sha256":"e1a9f820ba7eda08d7d0874f9b406eb90f2f1cc12652ca62d4c3b2ccbee12f67"},"schema_version":"1.0"},"canonical_sha256":"689d8d13a30c1c6a74118ca35f29394ad2d2031a05352e3a01629b983d4d720c","source":{"kind":"arxiv","id":"2406.13275","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13275","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13275v2","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13275","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"NCOY2E5DBQOG","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"NCOY2E5DBQOGU5AR","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"NCOY2E5D","created_at":"2026-07-05T08:36:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NCOY2E5DBQOGU5ARRSRV6KJZJL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.13275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-19T07:09:46Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"91c9bcdd5465ad8c460b0a5debf2cd95654e859688f37c352af99f4f5e81c8dc","abstract_canon_sha256":"e1a9f820ba7eda08d7d0874f9b406eb90f2f1cc12652ca62d4c3b2ccbee12f67"},"schema_version":"1.0"},"canonical_sha256":"689d8d13a30c1c6a74118ca35f29394ad2d2031a05352e3a01629b983d4d720c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:28.679971Z","signature_b64":"ErGxPLu2qm1mIsz9nwAADy+KFBIOiwQ2vv6xgnCLNnQhoJeEK+d4njlaztN25EDeh2HVPzlD+jJKeXHfZqlZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"689d8d13a30c1c6a74118ca35f29394ad2d2031a05352e3a01629b983d4d720c","last_reissued_at":"2026-07-05T08:36:28.679513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:28.679513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.13275","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":"2026-07-05T08:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kUAJEREkFYnebtSAkFkwOv56c42w1Goe9gNu38KsBXstrriFLDXUhVFEN/1VD1MSnSFruZQgBWLmYPHEDqwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T22:00:20.079095Z"},"content_sha256":"0f7427a2d6f7966a6b7eb15c5355a451f50d1d58318626d179cf7c0703fb4b03","schema_version":"1.0","event_id":"sha256:0f7427a2d6f7966a6b7eb15c5355a451f50d1d58318626d179cf7c0703fb4b03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NCOY2E5DBQOGU5ARRSRV6KJZJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Gang Li, Heinrich Dinkel, Jizhong Liu, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2024-06-19T07:09:46Z","abstract_excerpt":"Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened up possibilities for improving AAC. Thus, we explore enhancing AAC from three aspects: 1) a pre-trained audio encoder via consistent ensemble distillation (CED) is used to improve the effectivity of acoustic tokens, with a querying transformer (Q-Former) bridging the modality gap to LLM and compress acoustic tokens; 2) we investigate the advantages of using a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13275","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/2406.13275/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":"2026-07-05T08:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eRmRU/593t5HGOwefdYGvYb7md1x6aWxTjiv0jLgkvmPfLcCHd15AhbBAEYz2BzbGn1avnRM51QgZMBUOoqDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T22:00:20.079483Z"},"content_sha256":"326d5ce1e2f0980c2aceb893780c9608aff3d11674e96de7aee9c80eb4801230","schema_version":"1.0","event_id":"sha256:326d5ce1e2f0980c2aceb893780c9608aff3d11674e96de7aee9c80eb4801230"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL/bundle.json","state_url":"https://pith.science/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL/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":"2026-07-23T22:00:20Z","links":{"resolver":"https://pith.science/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL","bundle":"https://pith.science/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL/bundle.json","state":"https://pith.science/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCOY2E5DBQOGU5ARRSRV6KJZJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCOY2E5DBQOGU5ARRSRV6KJZJL","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":"e1a9f820ba7eda08d7d0874f9b406eb90f2f1cc12652ca62d4c3b2ccbee12f67","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-19T07:09:46Z","title_canon_sha256":"91c9bcdd5465ad8c460b0a5debf2cd95654e859688f37c352af99f4f5e81c8dc"},"schema_version":"1.0","source":{"id":"2406.13275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13275","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13275v2","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13275","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"NCOY2E5DBQOG","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"NCOY2E5DBQOGU5AR","created_at":"2026-07-05T08:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"NCOY2E5D","created_at":"2026-07-05T08:36:28Z"}],"graph_snapshots":[{"event_id":"sha256:326d5ce1e2f0980c2aceb893780c9608aff3d11674e96de7aee9c80eb4801230","target":"graph","created_at":"2026-07-05T08:36:28Z","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/2406.13275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened up possibilities for improving AAC. Thus, we explore enhancing AAC from three aspects: 1) a pre-trained audio encoder via consistent ensemble distillation (CED) is used to improve the effectivity of acoustic tokens, with a querying transformer (Q-Former) bridging the modality gap to LLM and compress acoustic tokens; 2) we investigate the advantages of using a","authors_text":"Bin Wang, Gang Li, Heinrich Dinkel, Jizhong Liu, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-19T07:09:46Z","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13275","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":"sha256:0f7427a2d6f7966a6b7eb15c5355a451f50d1d58318626d179cf7c0703fb4b03","target":"record","created_at":"2026-07-05T08:36:28Z","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":"e1a9f820ba7eda08d7d0874f9b406eb90f2f1cc12652ca62d4c3b2ccbee12f67","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-19T07:09:46Z","title_canon_sha256":"91c9bcdd5465ad8c460b0a5debf2cd95654e859688f37c352af99f4f5e81c8dc"},"schema_version":"1.0","source":{"id":"2406.13275","kind":"arxiv","version":2}},"canonical_sha256":"689d8d13a30c1c6a74118ca35f29394ad2d2031a05352e3a01629b983d4d720c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"689d8d13a30c1c6a74118ca35f29394ad2d2031a05352e3a01629b983d4d720c","first_computed_at":"2026-07-05T08:36:28.679513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:28.679513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ErGxPLu2qm1mIsz9nwAADy+KFBIOiwQ2vv6xgnCLNnQhoJeEK+d4njlaztN25EDeh2HVPzlD+jJKeXHfZqlZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:28.679971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f7427a2d6f7966a6b7eb15c5355a451f50d1d58318626d179cf7c0703fb4b03","sha256:326d5ce1e2f0980c2aceb893780c9608aff3d11674e96de7aee9c80eb4801230"],"state_sha256":"797f86435e5505eee5fb8ad9fca205192649bb0e948fa7afa042609bd1598f69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N47UhvoJw0ctzLW0LFWHiJu11lm6eqnx4tv3XkPFp4FcM8sj16acJTL7l0kCu/lwUE+Fvzs5YI7y9RydKopqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T22:00:20.081983Z","bundle_sha256":"f9d10f6817f13609d1e6261bfad7df2ff44b787860e9f10eccf0ee5eef862c1a"}}