{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YQZ4W6TUQEKODHE7ZCNTMF6ST4","short_pith_number":"pith:YQZ4W6TU","canonical_record":{"source":{"id":"2106.07716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T19:25:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"52895d8c8e483f912d00992c18df29ffb7b56409cefb12f60d61bef18fe86d4e","abstract_canon_sha256":"9b27c34c904bf5e0b7bd7466b344e48184670c355112319a1bb08ef987c19340"},"schema_version":"1.0"},"canonical_sha256":"c433cb7a748114e19c9fc89b3617d29f33ee5156ebde96d025fbcf4595b1e870","source":{"kind":"arxiv","id":"2106.07716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07716","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07716v1","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07716","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"YQZ4W6TUQEKO","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"YQZ4W6TUQEKODHE7","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"YQZ4W6TU","created_at":"2026-07-05T02:49:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YQZ4W6TUQEKODHE7ZCNTMF6ST4","target":"record","payload":{"canonical_record":{"source":{"id":"2106.07716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T19:25:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"52895d8c8e483f912d00992c18df29ffb7b56409cefb12f60d61bef18fe86d4e","abstract_canon_sha256":"9b27c34c904bf5e0b7bd7466b344e48184670c355112319a1bb08ef987c19340"},"schema_version":"1.0"},"canonical_sha256":"c433cb7a748114e19c9fc89b3617d29f33ee5156ebde96d025fbcf4595b1e870","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:33.141093Z","signature_b64":"ei3DHCNHQRXp3A7lGINGobILpzagpVEq3WWIvoNdmYzTJjzFnK6G+0zaOMi5t6qQ4bTc1Rj423Kz5Vn+DPbhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c433cb7a748114e19c9fc89b3617d29f33ee5156ebde96d025fbcf4595b1e870","last_reissued_at":"2026-07-05T02:49:33.140618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:33.140618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.07716","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":"2026-07-05T02:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1UusB1cuLZ1CvI9c+D/MdSdyZByghmN+TTKNKCwmX2hPPBVKuiLdQhxxGLadreCUHjzCzqp6XtlPQBP4AGraDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:16:06.964844Z"},"content_sha256":"43de1c8217f942cd10256e691b09b4e8fab2487e172c974565f7299e5d1f35d8","schema_version":"1.0","event_id":"sha256:43de1c8217f942cd10256e691b09b4e8fab2487e172c974565f7299e5d1f35d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YQZ4W6TUQEKODHE7ZCNTMF6ST4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chak-Fai Li, Francis Keith, Matthew Snover, Owen Kimball, William Hartmann","submitted_at":"2021-06-14T19:25:57Z","abstract_excerpt":"Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for seq2seq models than their hybrid counterparts. We examine corpora of five languages from the IARPA MATERIAL program where the transcribed data is conversational telephone speech (CTS) and evaluation data is broadcast news (BN). We show that there is a sizable initial gap in such a data condition between hybrid and seq2seq models, and the hybrid model is able "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07716","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/2106.07716/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":"2026-07-05T02:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8E6QbO4dPngBQCBNwCYKvF8loD1s7vsKFefnNRQjSn93465hRV8jTIT0MHi6r3V+0Xal9BtkrkFv7ZTi3AU4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:16:06.965420Z"},"content_sha256":"eca325052344a0640be4ff2d21ad87dca74eadb607a9d7b7c46afe276b3dab63","schema_version":"1.0","event_id":"sha256:eca325052344a0640be4ff2d21ad87dca74eadb607a9d7b7c46afe276b3dab63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4/bundle.json","state_url":"https://pith.science/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4/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":"2026-08-15T17:16:06Z","links":{"resolver":"https://pith.science/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4","bundle":"https://pith.science/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4/bundle.json","state":"https://pith.science/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQZ4W6TUQEKODHE7ZCNTMF6ST4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YQZ4W6TUQEKODHE7ZCNTMF6ST4","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":"9b27c34c904bf5e0b7bd7466b344e48184670c355112319a1bb08ef987c19340","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T19:25:57Z","title_canon_sha256":"52895d8c8e483f912d00992c18df29ffb7b56409cefb12f60d61bef18fe86d4e"},"schema_version":"1.0","source":{"id":"2106.07716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07716","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07716v1","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07716","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"YQZ4W6TUQEKO","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_16","alias_value":"YQZ4W6TUQEKODHE7","created_at":"2026-07-05T02:49:33Z"},{"alias_kind":"pith_short_8","alias_value":"YQZ4W6TU","created_at":"2026-07-05T02:49:33Z"}],"graph_snapshots":[{"event_id":"sha256:eca325052344a0640be4ff2d21ad87dca74eadb607a9d7b7c46afe276b3dab63","target":"graph","created_at":"2026-07-05T02:49:33Z","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/2106.07716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for seq2seq models than their hybrid counterparts. We examine corpora of five languages from the IARPA MATERIAL program where the transcribed data is conversational telephone speech (CTS) and evaluation data is broadcast news (BN). We show that there is a sizable initial gap in such a data condition between hybrid and seq2seq models, and the hybrid model is able ","authors_text":"Chak-Fai Li, Francis Keith, Matthew Snover, Owen Kimball, William Hartmann","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T19:25:57Z","title":"Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscripts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07716","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":"sha256:43de1c8217f942cd10256e691b09b4e8fab2487e172c974565f7299e5d1f35d8","target":"record","created_at":"2026-07-05T02:49:33Z","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":"9b27c34c904bf5e0b7bd7466b344e48184670c355112319a1bb08ef987c19340","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T19:25:57Z","title_canon_sha256":"52895d8c8e483f912d00992c18df29ffb7b56409cefb12f60d61bef18fe86d4e"},"schema_version":"1.0","source":{"id":"2106.07716","kind":"arxiv","version":1}},"canonical_sha256":"c433cb7a748114e19c9fc89b3617d29f33ee5156ebde96d025fbcf4595b1e870","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c433cb7a748114e19c9fc89b3617d29f33ee5156ebde96d025fbcf4595b1e870","first_computed_at":"2026-07-05T02:49:33.140618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:33.140618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ei3DHCNHQRXp3A7lGINGobILpzagpVEq3WWIvoNdmYzTJjzFnK6G+0zaOMi5t6qQ4bTc1Rj423Kz5Vn+DPbhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:33.141093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43de1c8217f942cd10256e691b09b4e8fab2487e172c974565f7299e5d1f35d8","sha256:eca325052344a0640be4ff2d21ad87dca74eadb607a9d7b7c46afe276b3dab63"],"state_sha256":"9cac6de464773e2a446db28909949c61ddaf8eb5a0e06fed0250bda7ae389b76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqqnCtyvjobZI+fz/Jsm0hbceSQnRyqqMyPWkJHlS/R8B9RAtFR/NQaBOCk/9mvo9vGdUrX/3LdFbSG2XkpNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:16:06.969315Z","bundle_sha256":"5a541537e6bb18f51616e85709c37408a3b82d46b6172e6e4d9048151ac7b132"}}