{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FX65SURVBEKYMPLOQZ2DGVWBHC","short_pith_number":"pith:FX65SURV","canonical_record":{"source":{"id":"1909.11727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-09-25T19:37:47Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"990598ad26edac3e12d70c24d25b118f7856afb515a28d2d66e6ae97ff7e8b22","abstract_canon_sha256":"b72f2d3eb1d19b8e3b14b441221e309fe359b1525baf9800547a82841085ea73"},"schema_version":"1.0"},"canonical_sha256":"2dfdd952350915863d6e86743356c138b52a5b018aba1a08ebb55d67849a1d13","source":{"kind":"arxiv","id":"1909.11727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11727","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11727v1","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11727","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"FX65SURVBEKY","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"FX65SURVBEKYMPLO","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"FX65SURV","created_at":"2026-07-05T00:07:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FX65SURVBEKYMPLOQZ2DGVWBHC","target":"record","payload":{"canonical_record":{"source":{"id":"1909.11727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-09-25T19:37:47Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"990598ad26edac3e12d70c24d25b118f7856afb515a28d2d66e6ae97ff7e8b22","abstract_canon_sha256":"b72f2d3eb1d19b8e3b14b441221e309fe359b1525baf9800547a82841085ea73"},"schema_version":"1.0"},"canonical_sha256":"2dfdd952350915863d6e86743356c138b52a5b018aba1a08ebb55d67849a1d13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:27.333164Z","signature_b64":"6cCDoj2E+F4LCM1S5IX+lY04ayNOxkeLmBtz5VWJKcSLQ2r9fj2PfaEGlfaBI4G+Xal1+EBPhFQRilmlfbK5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dfdd952350915863d6e86743356c138b52a5b018aba1a08ebb55d67849a1d13","last_reissued_at":"2026-07-05T00:07:27.332694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:27.332694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.11727","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":"2026-07-05T00:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oPEdbLzWpHKtim2H0UxESaEjcWZo2yn83jTitxzn2Z/fGQGMwSdXVCNdO1BsHcrv3/EiZdqWLgF1WQ9cIC0CDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:30:44.239874Z"},"content_sha256":"ec1e830fc2b15b549d56ca3d07d690f7f5e8028bded15ee0ab028a7539f59270","schema_version":"1.0","event_id":"sha256:ec1e830fc2b15b549d56ca3d07d690f7f5e8028bded15ee0ab028a7539f59270"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FX65SURVBEKYMPLOQZ2DGVWBHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Alan Black, Nishant Gurunath, Sai Krishna Rallabandi","submitted_at":"2019-09-25T19:37:47Z","abstract_excerpt":"In order to build language technologies for majority of the languages, it is important to leverage the resources available in public domain on the internet - commonly referred to as `Found Data'. However, such data is characterized by the presence of non-standard, non-trivial variations. For instance, speech resources found on the internet have non-speech content, such as music. Therefore, speech recognition and speech synthesis models need to be robust to such variations. In this work, we present an analysis to show that it is important to disentangle the latent causal factors of variation in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11727","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/1909.11727/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":"2026-07-05T00:07:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o8IQopkA/T7eSu9g83+G0d5k8G1kYzx+DxBfmtU8LXtX3MD+yYvIhG28Oc5ZsOnDE/pea0GC1gjihlcJViJTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:30:44.240259Z"},"content_sha256":"42588711f4668b3a5e0f4c4b4eafb16c47b76050f10de7b56f586c7ca94f65f1","schema_version":"1.0","event_id":"sha256:42588711f4668b3a5e0f4c4b4eafb16c47b76050f10de7b56f586c7ca94f65f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FX65SURVBEKYMPLOQZ2DGVWBHC/bundle.json","state_url":"https://pith.science/pith/FX65SURVBEKYMPLOQZ2DGVWBHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FX65SURVBEKYMPLOQZ2DGVWBHC/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":"2026-07-06T23:30:44Z","links":{"resolver":"https://pith.science/pith/FX65SURVBEKYMPLOQZ2DGVWBHC","bundle":"https://pith.science/pith/FX65SURVBEKYMPLOQZ2DGVWBHC/bundle.json","state":"https://pith.science/pith/FX65SURVBEKYMPLOQZ2DGVWBHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FX65SURVBEKYMPLOQZ2DGVWBHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FX65SURVBEKYMPLOQZ2DGVWBHC","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":"b72f2d3eb1d19b8e3b14b441221e309fe359b1525baf9800547a82841085ea73","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-09-25T19:37:47Z","title_canon_sha256":"990598ad26edac3e12d70c24d25b118f7856afb515a28d2d66e6ae97ff7e8b22"},"schema_version":"1.0","source":{"id":"1909.11727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11727","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11727v1","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11727","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_12","alias_value":"FX65SURVBEKY","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_16","alias_value":"FX65SURVBEKYMPLO","created_at":"2026-07-05T00:07:27Z"},{"alias_kind":"pith_short_8","alias_value":"FX65SURV","created_at":"2026-07-05T00:07:27Z"}],"graph_snapshots":[{"event_id":"sha256:42588711f4668b3a5e0f4c4b4eafb16c47b76050f10de7b56f586c7ca94f65f1","target":"graph","created_at":"2026-07-05T00:07:27Z","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/1909.11727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order to build language technologies for majority of the languages, it is important to leverage the resources available in public domain on the internet - commonly referred to as `Found Data'. However, such data is characterized by the presence of non-standard, non-trivial variations. For instance, speech resources found on the internet have non-speech content, such as music. Therefore, speech recognition and speech synthesis models need to be robust to such variations. In this work, we present an analysis to show that it is important to disentangle the latent causal factors of variation in","authors_text":"Alan Black, Nishant Gurunath, Sai Krishna Rallabandi","cross_cats":["cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-09-25T19:37:47Z","title":"Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11727","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:ec1e830fc2b15b549d56ca3d07d690f7f5e8028bded15ee0ab028a7539f59270","target":"record","created_at":"2026-07-05T00:07:27Z","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":"b72f2d3eb1d19b8e3b14b441221e309fe359b1525baf9800547a82841085ea73","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-09-25T19:37:47Z","title_canon_sha256":"990598ad26edac3e12d70c24d25b118f7856afb515a28d2d66e6ae97ff7e8b22"},"schema_version":"1.0","source":{"id":"1909.11727","kind":"arxiv","version":1}},"canonical_sha256":"2dfdd952350915863d6e86743356c138b52a5b018aba1a08ebb55d67849a1d13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dfdd952350915863d6e86743356c138b52a5b018aba1a08ebb55d67849a1d13","first_computed_at":"2026-07-05T00:07:27.332694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:27.332694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6cCDoj2E+F4LCM1S5IX+lY04ayNOxkeLmBtz5VWJKcSLQ2r9fj2PfaEGlfaBI4G+Xal1+EBPhFQRilmlfbK5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:27.333164Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec1e830fc2b15b549d56ca3d07d690f7f5e8028bded15ee0ab028a7539f59270","sha256:42588711f4668b3a5e0f4c4b4eafb16c47b76050f10de7b56f586c7ca94f65f1"],"state_sha256":"bcc40fbd13e2b7d5109ab38966da1757c52ddacccf421fcedc78d70781a547ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNaq0Tqfdsl2uNiMBkZgVmdne8EPT+k50MnFNK6AZMUVNiXsUGZVpB/HSdDgGLDZ26In79fYVbX/x/lkmcYUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:30:44.243409Z","bundle_sha256":"5137101f0a2fa539d219b84b5f2abf2ccd63758247cc146ac58f9bd891d2b64f"}}