{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BPJO2KFD6XGYBJLW6XBU6YGN3G","short_pith_number":"pith:BPJO2KFD","canonical_record":{"source":{"id":"2506.00800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T03:01:16Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"daf703d928c7687be4b8355f798a6a83a7082e4319de7a1d2240ff2452550c97","abstract_canon_sha256":"abad321ee7ce93e81d6cc47020ef08e863fdb53442661da08c33c38baf195f8e"},"schema_version":"1.0"},"canonical_sha256":"0bd2ed28a3f5cd80a576f5c34f60cdd9b42eea8a61c6a61d6e64fb04b618a3fe","source":{"kind":"arxiv","id":"2506.00800","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00800","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00800v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00800","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"BPJO2KFD6XGY","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"BPJO2KFD6XGYBJLW","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"BPJO2KFD","created_at":"2026-07-05T11:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BPJO2KFD6XGYBJLW6XBU6YGN3G","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T03:01:16Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"daf703d928c7687be4b8355f798a6a83a7082e4319de7a1d2240ff2452550c97","abstract_canon_sha256":"abad321ee7ce93e81d6cc47020ef08e863fdb53442661da08c33c38baf195f8e"},"schema_version":"1.0"},"canonical_sha256":"0bd2ed28a3f5cd80a576f5c34f60cdd9b42eea8a61c6a61d6e64fb04b618a3fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:40.672855Z","signature_b64":"ZTiEAM3dX1SVsn+v5VMpgfI2UkkRqv+JASjfTScyfcAyeo1kl0ivOBFxfaA6E6hYD9Qa1GZpKVGiyykRxklRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bd2ed28a3f5cd80a576f5c34f60cdd9b42eea8a61c6a61d6e64fb04b618a3fe","last_reissued_at":"2026-07-05T11:13:40.672246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:40.672246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00800","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":"2026-07-05T11:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqHYAicd5QW2xwwTwMVP3a6TP50CfagPhoD5G8z6C80qeS4/72EQedud4oW/b10v3hrlpkJi4GZ4wTXG3mZjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:13:39.413956Z"},"content_sha256":"ccde93fcdc27977d078bb5f72a802481267485df57f6c867332f89c4b713e9c8","schema_version":"1.0","event_id":"sha256:ccde93fcdc27977d078bb5f72a802481267485df57f6c867332f89c4b713e9c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BPJO2KFD6XGYBJLW6XBU6YGN3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Binh Thien Nguyen, Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Noboru Harada, Yasunori Ohishi","submitted_at":"2025-06-01T03:01:16Z","abstract_excerpt":"Automated Audio Captioning (AAC) aims to describe the semantic contexts of general sounds, including acoustic events and scenes, by leveraging effective acoustic features. To enhance performance, an AAC method, EnCLAP, employed discrete tokens from EnCodec as an effective input for fine-tuning a language model BART. However, EnCodec is designed to reconstruct waveforms rather than capture the semantic contexts of general sounds, which AAC should describe. To address this issue, we propose CLAP-ART, an AAC method that utilizes ``semantic-rich and discrete'' tokens as input. CLAP-ART computes se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00800","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/2506.00800/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":"2026-07-05T11:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/v8PGrfArnXo6hXTUJJfjiZoucvuBdQkewEnAZrTS8zjmxgpCplqNzzhMuvE4T/StKhQBj60nKFhRXDVfDtCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:13:39.414523Z"},"content_sha256":"e7d34e8cba23353313afb3f5873e3a5281decc3ee75b3dbe4544a7f97bf13c62","schema_version":"1.0","event_id":"sha256:e7d34e8cba23353313afb3f5873e3a5281decc3ee75b3dbe4544a7f97bf13c62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G/bundle.json","state_url":"https://pith.science/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G/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":"2026-08-09T13:13:39Z","links":{"resolver":"https://pith.science/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G","bundle":"https://pith.science/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G/bundle.json","state":"https://pith.science/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPJO2KFD6XGYBJLW6XBU6YGN3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BPJO2KFD6XGYBJLW6XBU6YGN3G","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":"abad321ee7ce93e81d6cc47020ef08e863fdb53442661da08c33c38baf195f8e","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T03:01:16Z","title_canon_sha256":"daf703d928c7687be4b8355f798a6a83a7082e4319de7a1d2240ff2452550c97"},"schema_version":"1.0","source":{"id":"2506.00800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00800","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00800v1","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00800","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"BPJO2KFD6XGY","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"BPJO2KFD6XGYBJLW","created_at":"2026-07-05T11:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"BPJO2KFD","created_at":"2026-07-05T11:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:e7d34e8cba23353313afb3f5873e3a5281decc3ee75b3dbe4544a7f97bf13c62","target":"graph","created_at":"2026-07-05T11:13:40Z","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/2506.00800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated Audio Captioning (AAC) aims to describe the semantic contexts of general sounds, including acoustic events and scenes, by leveraging effective acoustic features. To enhance performance, an AAC method, EnCLAP, employed discrete tokens from EnCodec as an effective input for fine-tuning a language model BART. However, EnCodec is designed to reconstruct waveforms rather than capture the semantic contexts of general sounds, which AAC should describe. To address this issue, we propose CLAP-ART, an AAC method that utilizes ``semantic-rich and discrete'' tokens as input. CLAP-ART computes se","authors_text":"Binh Thien Nguyen, Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Noboru Harada, Yasunori Ohishi","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T03:01:16Z","title":"CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00800","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:ccde93fcdc27977d078bb5f72a802481267485df57f6c867332f89c4b713e9c8","target":"record","created_at":"2026-07-05T11:13:40Z","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":"abad321ee7ce93e81d6cc47020ef08e863fdb53442661da08c33c38baf195f8e","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T03:01:16Z","title_canon_sha256":"daf703d928c7687be4b8355f798a6a83a7082e4319de7a1d2240ff2452550c97"},"schema_version":"1.0","source":{"id":"2506.00800","kind":"arxiv","version":1}},"canonical_sha256":"0bd2ed28a3f5cd80a576f5c34f60cdd9b42eea8a61c6a61d6e64fb04b618a3fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bd2ed28a3f5cd80a576f5c34f60cdd9b42eea8a61c6a61d6e64fb04b618a3fe","first_computed_at":"2026-07-05T11:13:40.672246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:40.672246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZTiEAM3dX1SVsn+v5VMpgfI2UkkRqv+JASjfTScyfcAyeo1kl0ivOBFxfaA6E6hYD9Qa1GZpKVGiyykRxklRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:40.672855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccde93fcdc27977d078bb5f72a802481267485df57f6c867332f89c4b713e9c8","sha256:e7d34e8cba23353313afb3f5873e3a5281decc3ee75b3dbe4544a7f97bf13c62"],"state_sha256":"1af7bdfe7918dbf39f6c248b2dc0299e4f45e4e2a7e1512ebd1d2ee115741e8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C71JINI+NY15Q9NE128hnhbev9N6DYKc6yEDmlKscDkkIcP9MlDm48rOpTfZcrxsUzN9ktQ+TmaM0Zb4VQo7AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:13:39.418489Z","bundle_sha256":"6bd8b48caf51d7eab815e0ffad2855d7e3c227d6ebd7e538352a027debc80c34"}}