{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NCIA6DL6SJ67ZIIKDJK5CT4RWS","short_pith_number":"pith:NCIA6DL6","canonical_record":{"source":{"id":"2505.14989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T00:27:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cf0249d732f7760a859b95b4688b5d03a04053d9ae26fb6c41dff2323b96e18d","abstract_canon_sha256":"59ca85f3e42c017983e11e72fd17f02a21e73eab1765bf70781d883d91bd05cc"},"schema_version":"1.0"},"canonical_sha256":"68900f0d7e927dfca10a1a55d14f91b4a52163d234ab966ebaa59aec1b0b1007","source":{"kind":"arxiv","id":"2505.14989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14989","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14989v1","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14989","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_12","alias_value":"NCIA6DL6SJ67","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_16","alias_value":"NCIA6DL6SJ67ZIIK","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_8","alias_value":"NCIA6DL6","created_at":"2026-07-05T11:06:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NCIA6DL6SJ67ZIIKDJK5CT4RWS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T00:27:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cf0249d732f7760a859b95b4688b5d03a04053d9ae26fb6c41dff2323b96e18d","abstract_canon_sha256":"59ca85f3e42c017983e11e72fd17f02a21e73eab1765bf70781d883d91bd05cc"},"schema_version":"1.0"},"canonical_sha256":"68900f0d7e927dfca10a1a55d14f91b4a52163d234ab966ebaa59aec1b0b1007","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:38.840971Z","signature_b64":"PzD+zpjbcpblUkZW+BgUKSEKecP1p2MfD3fYMUr76ogSQNhFybYZ1JtTAsdxjNcnY/SgmSZx7e2J91RjJQ5KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68900f0d7e927dfca10a1a55d14f91b4a52163d234ab966ebaa59aec1b0b1007","last_reissued_at":"2026-07-05T11:06:38.840370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:38.840370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14989","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":"2026-07-05T11:06:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDFB6LDbtECSQcv4Sarn9nq5RcE4ftyxB3CDBHY4IBerAgS3z8tWWh29to8QIIeDeCOa5gdKNtzqd9QgfsWrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:55:35.138392Z"},"content_sha256":"369b156dc1fd7efccd6cd39b54619a3819d6465ce4a920ef3ff785813618b3d3","schema_version":"1.0","event_id":"sha256:369b156dc1fd7efccd6cd39b54619a3819d6465ce4a920ef3ff785813618b3d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NCIA6DL6SJ67ZIIKDJK5CT4RWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Audio Representations for Automated Audio Captioning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoqin Sun, Jingguang Tian, Xinhui Hu, Xinkang Xu","submitted_at":"2025-05-21T00:27:38Z","abstract_excerpt":"Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to automated audio captioning (AAC) remains underexplored. This paper systematically investigates the viability of audio token-driven models for AAC through comparative analyses of various tokenization methods. Our findings reveal that audio tokenization leads to performance degradation in AAC models compared to those that directly utilize continuous audio represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14989","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/2505.14989/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":"2026-07-05T11:06:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EnTcC/fbUhTvpS4FmP9M1p+zJC8yQNJnjqgz+OZpQbn1qW2k4dC9A/F8wZBlfZNs1LquGNbGDdGiP3Xi+aPHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:55:35.138947Z"},"content_sha256":"1f9685190fb0fe52d45be77bb9087ec8198a655ec356183a8f6018a578fd041c","schema_version":"1.0","event_id":"sha256:1f9685190fb0fe52d45be77bb9087ec8198a655ec356183a8f6018a578fd041c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS/bundle.json","state_url":"https://pith.science/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS/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":"2026-08-08T02:55:35Z","links":{"resolver":"https://pith.science/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS","bundle":"https://pith.science/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS/bundle.json","state":"https://pith.science/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCIA6DL6SJ67ZIIKDJK5CT4RWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NCIA6DL6SJ67ZIIKDJK5CT4RWS","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":"59ca85f3e42c017983e11e72fd17f02a21e73eab1765bf70781d883d91bd05cc","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T00:27:38Z","title_canon_sha256":"cf0249d732f7760a859b95b4688b5d03a04053d9ae26fb6c41dff2323b96e18d"},"schema_version":"1.0","source":{"id":"2505.14989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14989","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14989v1","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14989","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_12","alias_value":"NCIA6DL6SJ67","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_16","alias_value":"NCIA6DL6SJ67ZIIK","created_at":"2026-07-05T11:06:38Z"},{"alias_kind":"pith_short_8","alias_value":"NCIA6DL6","created_at":"2026-07-05T11:06:38Z"}],"graph_snapshots":[{"event_id":"sha256:1f9685190fb0fe52d45be77bb9087ec8198a655ec356183a8f6018a578fd041c","target":"graph","created_at":"2026-07-05T11:06:38Z","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/2505.14989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous audio representations. However, their applicability to automated audio captioning (AAC) remains underexplored. This paper systematically investigates the viability of audio token-driven models for AAC through comparative analyses of various tokenization methods. Our findings reveal that audio tokenization leads to performance degradation in AAC models compared to those that directly utilize continuous audio represent","authors_text":"Haoqin Sun, Jingguang Tian, Xinhui Hu, Xinkang Xu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T00:27:38Z","title":"Discrete Audio Representations for Automated Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14989","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":"sha256:369b156dc1fd7efccd6cd39b54619a3819d6465ce4a920ef3ff785813618b3d3","target":"record","created_at":"2026-07-05T11:06:38Z","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":"59ca85f3e42c017983e11e72fd17f02a21e73eab1765bf70781d883d91bd05cc","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T00:27:38Z","title_canon_sha256":"cf0249d732f7760a859b95b4688b5d03a04053d9ae26fb6c41dff2323b96e18d"},"schema_version":"1.0","source":{"id":"2505.14989","kind":"arxiv","version":1}},"canonical_sha256":"68900f0d7e927dfca10a1a55d14f91b4a52163d234ab966ebaa59aec1b0b1007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68900f0d7e927dfca10a1a55d14f91b4a52163d234ab966ebaa59aec1b0b1007","first_computed_at":"2026-07-05T11:06:38.840370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:38.840370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PzD+zpjbcpblUkZW+BgUKSEKecP1p2MfD3fYMUr76ogSQNhFybYZ1JtTAsdxjNcnY/SgmSZx7e2J91RjJQ5KDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:38.840971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:369b156dc1fd7efccd6cd39b54619a3819d6465ce4a920ef3ff785813618b3d3","sha256:1f9685190fb0fe52d45be77bb9087ec8198a655ec356183a8f6018a578fd041c"],"state_sha256":"14beb6cc51615754db61694f2c465931ee9551dcfe58a8248bdb81142d8d9af6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66A4qxIwQacRuaBcDREQAxQ2VXaNKAM4BDUGhxv7dkpymAH/ObGt7B1anlcmtEe5Tdty/clA9ENXnZ9aEyImAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:55:35.143322Z","bundle_sha256":"04b6d805bfbb72157b1e0077e6880f7ae153e63c46df1412b91ff0bab5889920"}}