{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UDAYDFYRT4FKEVSGT774S2L5IE","short_pith_number":"pith:UDAYDFYR","canonical_record":{"source":{"id":"1907.01302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T11:33:52Z","cross_cats_sorted":[],"title_canon_sha256":"c4df225362d715588a3da2a128b3be9ccf59472638d1c7daa00473ff9f776a94","abstract_canon_sha256":"4292466b9e849e222ce1f42bebbcfe81fa2f6f64d72b557fc162e35c83c38225"},"schema_version":"1.0"},"canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","source":{"kind":"arxiv","id":"1907.01302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01302","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01302v1","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01302","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"UDAYDFYRT4FK","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UDAYDFYRT4FKEVSG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UDAYDFYR","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UDAYDFYRT4FKEVSGT774S2L5IE","target":"record","payload":{"canonical_record":{"source":{"id":"1907.01302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T11:33:52Z","cross_cats_sorted":[],"title_canon_sha256":"c4df225362d715588a3da2a128b3be9ccf59472638d1c7daa00473ff9f776a94","abstract_canon_sha256":"4292466b9e849e222ce1f42bebbcfe81fa2f6f64d72b557fc162e35c83c38225"},"schema_version":"1.0"},"canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:40.719466Z","signature_b64":"jgjNCRj+djdJ9llvT3j3lmMYsRZ7AgGlINOhCs3NvYmtiBACssbHWfKkrfW8euuXTzefATO3clWNDyzfvlYdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","last_reissued_at":"2026-05-17T23:41:40.718949Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:40.718949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.01302","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":"2026-05-17T23:41:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NC3piRmBj7lELz+Pb3/H+a4KL5p9s9PximRgFU5yBa+VDyviZwsz+s9FrkafK7lylwVuhC8idKdBkK4FPEnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:40:24.311605Z"},"content_sha256":"d2c3fa265943796a3161d59ae26948eda31de1015675b425c73658c08542fe3a","schema_version":"1.0","event_id":"sha256:d2c3fa265943796a3161d59ae26948eda31de1015675b425c73658c08542fe3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UDAYDFYRT4FKEVSGT774S2L5IE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mortaza (Morrie) Doulaty, Thomas Hain","submitted_at":"2019-07-02T11:33:52Z","abstract_excerpt":"Selecting in-domain data from a large pool of diverse and out-of-domain data is a non-trivial problem. In most cases simply using all of the available data will lead to sub-optimal and in some cases even worse performance compared to carefully selecting a matching set. This is true even for data-inefficient neural models. Acoustic Latent Dirichlet Allocation (aLDA) is shown to be useful in a variety of speech technology related tasks, including domain adaptation of acoustic models for automatic speech recognition and entity labeling for information retrieval. In this paper we propose to use aL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01302","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":""},"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":"2026-05-17T23:41:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CnTw9h5F484QS8cVinom4HDIk6VN7nMeI7JNKWzghCaCX/QItUr5HHy9uoQSoCHawW5dQvFbDfWwZ3yOpTPHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:40:24.311972Z"},"content_sha256":"ebc50042b03a93c1693568f99f24a9dc24adb6ac29eb891785c164e33d04c2f1","schema_version":"1.0","event_id":"sha256:ebc50042b03a93c1693568f99f24a9dc24adb6ac29eb891785c164e33d04c2f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/bundle.json","state_url":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDAYDFYRT4FKEVSGT774S2L5IE/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":"2026-06-28T13:40:24Z","links":{"resolver":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE","bundle":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/bundle.json","state":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDAYDFYRT4FKEVSGT774S2L5IE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UDAYDFYRT4FKEVSGT774S2L5IE","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":"4292466b9e849e222ce1f42bebbcfe81fa2f6f64d72b557fc162e35c83c38225","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T11:33:52Z","title_canon_sha256":"c4df225362d715588a3da2a128b3be9ccf59472638d1c7daa00473ff9f776a94"},"schema_version":"1.0","source":{"id":"1907.01302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.01302","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"1907.01302v1","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01302","created_at":"2026-05-17T23:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"UDAYDFYRT4FK","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UDAYDFYRT4FKEVSG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UDAYDFYR","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:ebc50042b03a93c1693568f99f24a9dc24adb6ac29eb891785c164e33d04c2f1","target":"graph","created_at":"2026-05-17T23:41:40Z","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"},"paper":{"abstract_excerpt":"Selecting in-domain data from a large pool of diverse and out-of-domain data is a non-trivial problem. In most cases simply using all of the available data will lead to sub-optimal and in some cases even worse performance compared to carefully selecting a matching set. This is true even for data-inefficient neural models. Acoustic Latent Dirichlet Allocation (aLDA) is shown to be useful in a variety of speech technology related tasks, including domain adaptation of acoustic models for automatic speech recognition and entity labeling for information retrieval. In this paper we propose to use aL","authors_text":"Mortaza (Morrie) Doulaty, Thomas Hain","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T11:33:52Z","title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01302","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:d2c3fa265943796a3161d59ae26948eda31de1015675b425c73658c08542fe3a","target":"record","created_at":"2026-05-17T23:41:40Z","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":"4292466b9e849e222ce1f42bebbcfe81fa2f6f64d72b557fc162e35c83c38225","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T11:33:52Z","title_canon_sha256":"c4df225362d715588a3da2a128b3be9ccf59472638d1c7daa00473ff9f776a94"},"schema_version":"1.0","source":{"id":"1907.01302","kind":"arxiv","version":1}},"canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","first_computed_at":"2026-05-17T23:41:40.718949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:40.718949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jgjNCRj+djdJ9llvT3j3lmMYsRZ7AgGlINOhCs3NvYmtiBACssbHWfKkrfW8euuXTzefATO3clWNDyzfvlYdCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:40.719466Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.01302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2c3fa265943796a3161d59ae26948eda31de1015675b425c73658c08542fe3a","sha256:ebc50042b03a93c1693568f99f24a9dc24adb6ac29eb891785c164e33d04c2f1"],"state_sha256":"9fbfa36aba698288c5b791e65d7cd8eab93fa84b46c0bd43bcb4c68d4aa33196"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iK9K39m4lyRjKvjXFElkqCvfXZp/Olq+YABNgWG2+cdpPck1gFiKkI/pDVS4hdtPZyyDlu5fO9TOzPeRWdUyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T13:40:24.314003Z","bundle_sha256":"6f1258bd06cb460bc64221272a1b4d173cf084e6943d18fe79743c3f4a2caf0c"}}