{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VQXW4LS5SOEKZBBJWETMNVL4LY","short_pith_number":"pith:VQXW4LS5","canonical_record":{"source":{"id":"2104.01393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:00:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"605365e512d08a35868d3a32146768159fa50c142242df7fa7a93d2d8fae428c","abstract_canon_sha256":"75278d240397d70957b4d58304eeb031eefa4aa7547a28e4c6fa37ab9d32ddab"},"schema_version":"1.0"},"canonical_sha256":"ac2f6e2e5d9388ac8429b126c6d57c5e22dba379f26c9c68659fcc1ce3fa2f03","source":{"kind":"arxiv","id":"2104.01393","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01393","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01393v2","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01393","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"pith_short_12","alias_value":"VQXW4LS5SOEK","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"pith_short_16","alias_value":"VQXW4LS5SOEKZBBJ","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"pith_short_8","alias_value":"VQXW4LS5","created_at":"2026-07-05T06:19:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VQXW4LS5SOEKZBBJWETMNVL4LY","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:00:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"605365e512d08a35868d3a32146768159fa50c142242df7fa7a93d2d8fae428c","abstract_canon_sha256":"75278d240397d70957b4d58304eeb031eefa4aa7547a28e4c6fa37ab9d32ddab"},"schema_version":"1.0"},"canonical_sha256":"ac2f6e2e5d9388ac8429b126c6d57c5e22dba379f26c9c68659fcc1ce3fa2f03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:33.002697Z","signature_b64":"Xaa0QCCoJGa3FiacFZWgMZ5GzFAholb4X07u/UQJW3pf9ukMmxbGfzJCqrXGZ2phWwDlOAOxDQ1fduPOivdFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2f6e2e5d9388ac8429b126c6d57c5e22dba379f26c9c68659fcc1ce3fa2f03","last_reissued_at":"2026-07-05T06:19:33.002293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:33.002293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01393","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":"2026-07-05T06:19:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wePwB1PyfSGJJIAdIasMygZEQ0tswEQR6h+QQra/EFYkAukzER1U6DHk4/eZxsJqretkvwJAvcqkmaOBTpRyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:56:29.341888Z"},"content_sha256":"88557b2871913649d4934245331250bb096578f197ba1ac6936e2332c44a4a25","schema_version":"1.0","event_id":"sha256:88557b2871913649d4934245331250bb096578f197ba1ac6936e2332c44a4a25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VQXW4LS5SOEKZBBJWETMNVL4LY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Mayumi Ohta, Shigehiko Schamoni, Stefan Riezler, Tsz Kin Lam","submitted_at":"2021-04-03T13:00:00Z","abstract_excerpt":"We propose an on-the-fly data augmentation method for automatic speech recognition (ASR) that uses alignment information to generate effective training samples. Our method, called Aligned Data Augmentation (ADA) for ASR, replaces transcribed tokens and the speech representations in an aligned manner to generate previously unseen training pairs. The speech representations are sampled from an audio dictionary that has been extracted from the training corpus and inject speaker variations into the training examples. The transcribed tokens are either predicted by a language model such that the augm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01393","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/2104.01393/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":"2026-07-05T06:19:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydVVYQGW9BUS5HFPYCWJeIhlFgRhlDzg+P9ZqR+Pmo5tYL5LUPQDOWN4NYkFR3RphSDXBE72C0pktRpo8jTBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:56:29.342453Z"},"content_sha256":"5f01c7af1e4271f3c016c7a445b571578b9307f33fa6b3330a2c92116665818a","schema_version":"1.0","event_id":"sha256:5f01c7af1e4271f3c016c7a445b571578b9307f33fa6b3330a2c92116665818a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQXW4LS5SOEKZBBJWETMNVL4LY/bundle.json","state_url":"https://pith.science/pith/VQXW4LS5SOEKZBBJWETMNVL4LY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQXW4LS5SOEKZBBJWETMNVL4LY/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":"2026-08-15T22:56:29Z","links":{"resolver":"https://pith.science/pith/VQXW4LS5SOEKZBBJWETMNVL4LY","bundle":"https://pith.science/pith/VQXW4LS5SOEKZBBJWETMNVL4LY/bundle.json","state":"https://pith.science/pith/VQXW4LS5SOEKZBBJWETMNVL4LY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQXW4LS5SOEKZBBJWETMNVL4LY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VQXW4LS5SOEKZBBJWETMNVL4LY","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":"75278d240397d70957b4d58304eeb031eefa4aa7547a28e4c6fa37ab9d32ddab","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:00:00Z","title_canon_sha256":"605365e512d08a35868d3a32146768159fa50c142242df7fa7a93d2d8fae428c"},"schema_version":"1.0","source":{"id":"2104.01393","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01393","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01393v2","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01393","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"pith_short_12","alias_value":"VQXW4LS5SOEK","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"pith_short_16","alias_value":"VQXW4LS5SOEKZBBJ","created_at":"2026-07-05T06:19:33Z"},{"alias_kind":"pith_short_8","alias_value":"VQXW4LS5","created_at":"2026-07-05T06:19:33Z"}],"graph_snapshots":[{"event_id":"sha256:5f01c7af1e4271f3c016c7a445b571578b9307f33fa6b3330a2c92116665818a","target":"graph","created_at":"2026-07-05T06:19:33Z","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/2104.01393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an on-the-fly data augmentation method for automatic speech recognition (ASR) that uses alignment information to generate effective training samples. Our method, called Aligned Data Augmentation (ADA) for ASR, replaces transcribed tokens and the speech representations in an aligned manner to generate previously unseen training pairs. The speech representations are sampled from an audio dictionary that has been extracted from the training corpus and inject speaker variations into the training examples. The transcribed tokens are either predicted by a language model such that the augm","authors_text":"Mayumi Ohta, Shigehiko Schamoni, Stefan Riezler, Tsz Kin Lam","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:00:00Z","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01393","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":"sha256:88557b2871913649d4934245331250bb096578f197ba1ac6936e2332c44a4a25","target":"record","created_at":"2026-07-05T06:19:33Z","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":"75278d240397d70957b4d58304eeb031eefa4aa7547a28e4c6fa37ab9d32ddab","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:00:00Z","title_canon_sha256":"605365e512d08a35868d3a32146768159fa50c142242df7fa7a93d2d8fae428c"},"schema_version":"1.0","source":{"id":"2104.01393","kind":"arxiv","version":2}},"canonical_sha256":"ac2f6e2e5d9388ac8429b126c6d57c5e22dba379f26c9c68659fcc1ce3fa2f03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac2f6e2e5d9388ac8429b126c6d57c5e22dba379f26c9c68659fcc1ce3fa2f03","first_computed_at":"2026-07-05T06:19:33.002293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:33.002293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xaa0QCCoJGa3FiacFZWgMZ5GzFAholb4X07u/UQJW3pf9ukMmxbGfzJCqrXGZ2phWwDlOAOxDQ1fduPOivdFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:33.002697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01393","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88557b2871913649d4934245331250bb096578f197ba1ac6936e2332c44a4a25","sha256:5f01c7af1e4271f3c016c7a445b571578b9307f33fa6b3330a2c92116665818a"],"state_sha256":"21d8a6137b275c17c5704cd6d422ac7fd4f4faafd6f2cfc43ff36385c29c63b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KnQYbF7izwD63lkNwCNzNyc52l2TnSxpm0Td/1fAMMfDOlIckf6nOvRovrhit327xENFGgUc+NCWLGmDrPtcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:56:29.349131Z","bundle_sha256":"d71fe714c03dbc6e1b313024f68553abc35524491d0af4f51f632736e341b800"}}