{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EPFNWQJ4ACBDQXEAZWM7CJQMCK","short_pith_number":"pith:EPFNWQJ4","canonical_record":{"source":{"id":"2511.16757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-11-20T19:17:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2b9373176f8d9c4385e6cf1ed009802bd7e56ee9ca55df91f67a631f9d2adb4","abstract_canon_sha256":"0b8ac217af6bb8ab6c45dc9ff756a54eb89b40548dd88810e0124c98c3d2da41"},"schema_version":"1.0"},"canonical_sha256":"23cadb413c0082385c80cd99f1260c12978265c8393ce5183ee46447c91f554a","source":{"kind":"arxiv","id":"2511.16757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.16757","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2511.16757v2","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16757","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"EPFNWQJ4ACBD","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"EPFNWQJ4ACBDQXEA","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"EPFNWQJ4","created_at":"2026-07-01T00:17:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EPFNWQJ4ACBDQXEAZWM7CJQMCK","target":"record","payload":{"canonical_record":{"source":{"id":"2511.16757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-11-20T19:17:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2b9373176f8d9c4385e6cf1ed009802bd7e56ee9ca55df91f67a631f9d2adb4","abstract_canon_sha256":"0b8ac217af6bb8ab6c45dc9ff756a54eb89b40548dd88810e0124c98c3d2da41"},"schema_version":"1.0"},"canonical_sha256":"23cadb413c0082385c80cd99f1260c12978265c8393ce5183ee46447c91f554a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:09.289246Z","signature_b64":"zHS8NTC8FN9nFPdm6Bloeg73d1f9xP1tsIcSz2TqVAG6o3S1E7hZQ5s8uLtwBPOzCTRgpCdy2w6wAQX4iWRjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23cadb413c0082385c80cd99f1260c12978265c8393ce5183ee46447c91f554a","last_reissued_at":"2026-07-01T00:17:09.288646Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:09.288646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.16757","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":"2026-07-01T00:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfhV2R4SGPvYaWcEHWcGkcEwywi7VlVMCjHV8ZNV7kXbhr3FwoRYIyttJUNuu/j5pOv5ytlC01HaPy34aB1jAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T11:45:19.596701Z"},"content_sha256":"4669abccb94840d70752d5ecd07f35ee3b6b0a9593688c850e445bf142b63d73","schema_version":"1.0","event_id":"sha256:4669abccb94840d70752d5ecd07f35ee3b6b0a9593688c850e445bf142b63d73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EPFNWQJ4ACBDQXEAZWM7CJQMCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Dong Yu, Hao Zhang, Mingyue Huo, Wei-Cheng Tseng, Xuanru Zhou, Yiwen Shao","submitted_at":"2025-11-20T19:17:35Z","abstract_excerpt":"Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales. We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation. To fill this gap, we present the first principled empirical study of A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16757","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/2511.16757/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":"2026-07-01T00:17:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJ7FNoLOlte3t61y2f8thWWBlwyixB1wT6x4uor8KZGRWsBhM7L8KZMH7PJqYrorHSvAxOCsqOQbJphSqKYyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T11:45:19.597084Z"},"content_sha256":"d8a40f7ee287cb5ff2572656158eee72fc606c4c994cbbcc28f7a84f8b919f7f","schema_version":"1.0","event_id":"sha256:d8a40f7ee287cb5ff2572656158eee72fc606c4c994cbbcc28f7a84f8b919f7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK/bundle.json","state_url":"https://pith.science/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK/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":"2026-07-17T11:45:19Z","links":{"resolver":"https://pith.science/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK","bundle":"https://pith.science/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK/bundle.json","state":"https://pith.science/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPFNWQJ4ACBDQXEAZWM7CJQMCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EPFNWQJ4ACBDQXEAZWM7CJQMCK","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":"0b8ac217af6bb8ab6c45dc9ff756a54eb89b40548dd88810e0124c98c3d2da41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-11-20T19:17:35Z","title_canon_sha256":"e2b9373176f8d9c4385e6cf1ed009802bd7e56ee9ca55df91f67a631f9d2adb4"},"schema_version":"1.0","source":{"id":"2511.16757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.16757","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2511.16757v2","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16757","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"EPFNWQJ4ACBD","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"EPFNWQJ4ACBDQXEA","created_at":"2026-07-01T00:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"EPFNWQJ4","created_at":"2026-07-01T00:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:d8a40f7ee287cb5ff2572656158eee72fc606c4c994cbbcc28f7a84f8b919f7f","target":"graph","created_at":"2026-07-01T00:17:09Z","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/2511.16757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales. We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation. To fill this gap, we present the first principled empirical study of A","authors_text":"Dong Yu, Hao Zhang, Mingyue Huo, Wei-Cheng Tseng, Xuanru Zhou, Yiwen Shao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-11-20T19:17:35Z","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16757","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":"sha256:4669abccb94840d70752d5ecd07f35ee3b6b0a9593688c850e445bf142b63d73","target":"record","created_at":"2026-07-01T00:17:09Z","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":"0b8ac217af6bb8ab6c45dc9ff756a54eb89b40548dd88810e0124c98c3d2da41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-11-20T19:17:35Z","title_canon_sha256":"e2b9373176f8d9c4385e6cf1ed009802bd7e56ee9ca55df91f67a631f9d2adb4"},"schema_version":"1.0","source":{"id":"2511.16757","kind":"arxiv","version":2}},"canonical_sha256":"23cadb413c0082385c80cd99f1260c12978265c8393ce5183ee46447c91f554a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23cadb413c0082385c80cd99f1260c12978265c8393ce5183ee46447c91f554a","first_computed_at":"2026-07-01T00:17:09.288646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:09.288646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zHS8NTC8FN9nFPdm6Bloeg73d1f9xP1tsIcSz2TqVAG6o3S1E7hZQ5s8uLtwBPOzCTRgpCdy2w6wAQX4iWRjAA==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:09.289246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.16757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4669abccb94840d70752d5ecd07f35ee3b6b0a9593688c850e445bf142b63d73","sha256:d8a40f7ee287cb5ff2572656158eee72fc606c4c994cbbcc28f7a84f8b919f7f"],"state_sha256":"a4f167ba47f8df473a4c4749cbbb09690cae34fffd0fa4212a77ae784a348135"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MIG1+7e0zeWaO9mYG1IdL6LbgAzaZOwdg/keDgd4GVDbejaK/coYGeG+CmNzCzThcruZDoG9h1MzCLEVUKLLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T11:45:19.599663Z","bundle_sha256":"3665ffc18f2434e10f5d233226c410b329e8e955741f27bbd6c4124da3a97896"}}