{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EC43MMLBWXKGVUW6JVSCLIJ72M","short_pith_number":"pith:EC43MMLB","canonical_record":{"source":{"id":"2505.20606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T00:55:32Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"35a4a8ed63bc737ba503a347a2236491f712618e78a282c66f60d17fcfba4b79","abstract_canon_sha256":"ddbbda95e90fc51cd2e749d51fd7b8e103861e6ed8f87e740c3369e9d9dcad72"},"schema_version":"1.0"},"canonical_sha256":"20b9b63161b5d46ad2de4d6425a13fd3355f866b928a01dd0ad4d82e7c6c70fa","source":{"kind":"arxiv","id":"2505.20606","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20606","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20606v1","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20606","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"EC43MMLBWXKG","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"EC43MMLBWXKGVUW6","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"EC43MMLB","created_at":"2026-07-05T11:10:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EC43MMLBWXKGVUW6JVSCLIJ72M","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T00:55:32Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"35a4a8ed63bc737ba503a347a2236491f712618e78a282c66f60d17fcfba4b79","abstract_canon_sha256":"ddbbda95e90fc51cd2e749d51fd7b8e103861e6ed8f87e740c3369e9d9dcad72"},"schema_version":"1.0"},"canonical_sha256":"20b9b63161b5d46ad2de4d6425a13fd3355f866b928a01dd0ad4d82e7c6c70fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:15.326294Z","signature_b64":"MSfP3sCkAvArMyh4IkyuJeHAJrBLQ1LuqLRUmQn2BAzW15v2hJXf8gRr9dMsuP6SewmfuJT55dfWShuRKoK4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b9b63161b5d46ad2de4d6425a13fd3355f866b928a01dd0ad4d82e7c6c70fa","last_reissued_at":"2026-07-05T11:10:15.325791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:15.325791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20606","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":"2026-07-05T11:10:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"byQbdIwgnJ9SokW9IZnfj422+skUAxrsJ9v7tM+2Vo7atoEvxhVMkXhWvnCCsS6RiPWqDr60MO+O46DqZjgJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:02:09.986908Z"},"content_sha256":"86fb4a249f261c0308fc9541ea2623d7c299025fa4102e18c11a18ac8fc7a6e7","schema_version":"1.0","event_id":"sha256:86fb4a249f261c0308fc9541ea2623d7c299025fa4102e18c11a18ac8fc7a6e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EC43MMLBWXKGVUW6JVSCLIJ72M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CL","authors_text":"Amir Nassereldine, Chenhui Xu, Dancheng Liu, Jinjun Xiong","submitted_at":"2025-05-27T00:55:32Z","abstract_excerpt":"Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in training data affect the robustness of the ASR model and reveal that transcription generalization is primarily driven by acoustic variation rather than linguistic richness. We find that targeted acoustic augmentation methods could significantly improve the generalization ability of ASR models, reducing word-error rates by up to 19.24 percent on unseen datasets wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20606","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/2505.20606/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":"2026-07-05T11:10:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"42KgjXIXPgsHB2s5XS+BOhd0Btg+uJ8VZ0a32eXFCVw4hE32RcHBVuR20Lw9Gd3rWQwaDVxYrhwVJKq7ikZpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:02:09.987407Z"},"content_sha256":"234c678f7f7632904c84c6332134b9aa724198cd7ddb430d844f757fdf2bc706","schema_version":"1.0","event_id":"sha256:234c678f7f7632904c84c6332134b9aa724198cd7ddb430d844f757fdf2bc706"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EC43MMLBWXKGVUW6JVSCLIJ72M/bundle.json","state_url":"https://pith.science/pith/EC43MMLBWXKGVUW6JVSCLIJ72M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EC43MMLBWXKGVUW6JVSCLIJ72M/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":"2026-08-08T18:02:09Z","links":{"resolver":"https://pith.science/pith/EC43MMLBWXKGVUW6JVSCLIJ72M","bundle":"https://pith.science/pith/EC43MMLBWXKGVUW6JVSCLIJ72M/bundle.json","state":"https://pith.science/pith/EC43MMLBWXKGVUW6JVSCLIJ72M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EC43MMLBWXKGVUW6JVSCLIJ72M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EC43MMLBWXKGVUW6JVSCLIJ72M","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":"ddbbda95e90fc51cd2e749d51fd7b8e103861e6ed8f87e740c3369e9d9dcad72","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T00:55:32Z","title_canon_sha256":"35a4a8ed63bc737ba503a347a2236491f712618e78a282c66f60d17fcfba4b79"},"schema_version":"1.0","source":{"id":"2505.20606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20606","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20606v1","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20606","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"EC43MMLBWXKG","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"EC43MMLBWXKGVUW6","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"EC43MMLB","created_at":"2026-07-05T11:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:234c678f7f7632904c84c6332134b9aa724198cd7ddb430d844f757fdf2bc706","target":"graph","created_at":"2026-07-05T11:10:15Z","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/2505.20606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in training data affect the robustness of the ASR model and reveal that transcription generalization is primarily driven by acoustic variation rather than linguistic richness. We find that targeted acoustic augmentation methods could significantly improve the generalization ability of ASR models, reducing word-error rates by up to 19.24 percent on unseen datasets wh","authors_text":"Amir Nassereldine, Chenhui Xu, Dancheng Liu, Jinjun Xiong","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T00:55:32Z","title":"Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20606","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":"sha256:86fb4a249f261c0308fc9541ea2623d7c299025fa4102e18c11a18ac8fc7a6e7","target":"record","created_at":"2026-07-05T11:10:15Z","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":"ddbbda95e90fc51cd2e749d51fd7b8e103861e6ed8f87e740c3369e9d9dcad72","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T00:55:32Z","title_canon_sha256":"35a4a8ed63bc737ba503a347a2236491f712618e78a282c66f60d17fcfba4b79"},"schema_version":"1.0","source":{"id":"2505.20606","kind":"arxiv","version":1}},"canonical_sha256":"20b9b63161b5d46ad2de4d6425a13fd3355f866b928a01dd0ad4d82e7c6c70fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20b9b63161b5d46ad2de4d6425a13fd3355f866b928a01dd0ad4d82e7c6c70fa","first_computed_at":"2026-07-05T11:10:15.325791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:15.325791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MSfP3sCkAvArMyh4IkyuJeHAJrBLQ1LuqLRUmQn2BAzW15v2hJXf8gRr9dMsuP6SewmfuJT55dfWShuRKoK4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:15.326294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86fb4a249f261c0308fc9541ea2623d7c299025fa4102e18c11a18ac8fc7a6e7","sha256:234c678f7f7632904c84c6332134b9aa724198cd7ddb430d844f757fdf2bc706"],"state_sha256":"d8a1ce92a01b0846373a5af1d2be44d6f0c9e5f46c74059d6b9dbbbf4ec90632"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yTwSKgSrXKrhvW2xlIajP2Jkq1hz6016QHjFB84rS0y94bvilut2iREgFE1pfMLFcLXIx4j58NM2OHn7FuyxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:02:09.993415Z","bundle_sha256":"30af31c4ed8ae8f015313ef0fc571e7b028af85d58ce10eeec7a91049d55e95a"}}