{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WTP5FDQGFYYJE3RTXSPHGQUE3X","short_pith_number":"pith:WTP5FDQG","canonical_record":{"source":{"id":"2110.05354","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T23:03:29Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"761261fe40e8786c072a0485b7fc3d3dec034b456328f71c9eb7386c6a37aab2","abstract_canon_sha256":"cce5473377ba7b395accb694be339788fad6f5261eb7383db67d0667e75565e0"},"schema_version":"1.0"},"canonical_sha256":"b4dfd28e062e30926e33bc9e734284ddcf7d7b1e4f72fff5c2fb4a0e4257171b","source":{"kind":"arxiv","id":"2110.05354","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05354","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05354v5","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05354","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"WTP5FDQGFYYJ","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"WTP5FDQGFYYJE3RT","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"WTP5FDQG","created_at":"2026-07-05T05:11:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WTP5FDQGFYYJE3RTXSPHGQUE3X","target":"record","payload":{"canonical_record":{"source":{"id":"2110.05354","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T23:03:29Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"761261fe40e8786c072a0485b7fc3d3dec034b456328f71c9eb7386c6a37aab2","abstract_canon_sha256":"cce5473377ba7b395accb694be339788fad6f5261eb7383db67d0667e75565e0"},"schema_version":"1.0"},"canonical_sha256":"b4dfd28e062e30926e33bc9e734284ddcf7d7b1e4f72fff5c2fb4a0e4257171b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:35.244177Z","signature_b64":"MR8DJurMM7ZGrV6LYc/Wc2BYqmIbQuwtTwH86GWTjRPwYQN0IFlC6k8l486OhMZ29WOcNSmJA+UU9wgvKuajAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4dfd28e062e30926e33bc9e734284ddcf7d7b1e4f72fff5c2fb4a0e4257171b","last_reissued_at":"2026-07-05T05:11:35.243689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:35.243689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.05354","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0DH7a9P043XJpJF5m8hCd78VotbXWK2VrVcWUj14wZWtVfjrCcz8kHTktvwi4gvOzajlTcOtOsYCxTab61xJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:30.904731Z"},"content_sha256":"eaaad819099dc07ade3fee3438a366066ab384517248ac02781d023c4437fba7","schema_version":"1.0","event_id":"sha256:eaaad819099dc07ade3fee3438a366066ab384517248ac02781d023c4437fba7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WTP5FDQGFYYJE3RTXSPHGQUE3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jinyu Li, Naoyuki Kanda, Xie Chen, Yashesh Gaur, Yifan Gong, Yu Wu, Zhong Meng","submitted_at":"2021-10-06T23:03:29Z","abstract_excerpt":"Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an additional external LM during inference, significantly increasing the computation cost. To overcome this, we propose an internal LM adaptation (ILMA) of the E2E model using text-only data. Trained with audio-transcript pairs, an E2E model implicitly learns an internal LM that characterizes the token sequence probability which is approximated by the E2E model output after zeroing out the encoder contribution. During ILMA, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05354","kind":"arxiv","version":5},"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/2110.05354/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":"2026-07-05T05:11:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFYNR0HEV2UTKMQEOVmgYT9dRcfDe4xnJbOLprEjTey3kN40uuA6eQ/aCLeucEwvlVfunzdtnBWno+fg6NnACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:49:30.905263Z"},"content_sha256":"6f6e7b1c7e3c5959f15a79be935fdd7c9c5ea1bca6cd74857860d06717fd673d","schema_version":"1.0","event_id":"sha256:6f6e7b1c7e3c5959f15a79be935fdd7c9c5ea1bca6cd74857860d06717fd673d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X/bundle.json","state_url":"https://pith.science/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X/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":"2026-08-06T10:49:30Z","links":{"resolver":"https://pith.science/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X","bundle":"https://pith.science/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X/bundle.json","state":"https://pith.science/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTP5FDQGFYYJE3RTXSPHGQUE3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WTP5FDQGFYYJE3RTXSPHGQUE3X","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":"cce5473377ba7b395accb694be339788fad6f5261eb7383db67d0667e75565e0","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T23:03:29Z","title_canon_sha256":"761261fe40e8786c072a0485b7fc3d3dec034b456328f71c9eb7386c6a37aab2"},"schema_version":"1.0","source":{"id":"2110.05354","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05354","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05354v5","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05354","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"WTP5FDQGFYYJ","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"WTP5FDQGFYYJE3RT","created_at":"2026-07-05T05:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"WTP5FDQG","created_at":"2026-07-05T05:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:6f6e7b1c7e3c5959f15a79be935fdd7c9c5ea1bca6cd74857860d06717fd673d","target":"graph","created_at":"2026-07-05T05:11:35Z","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/2110.05354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an additional external LM during inference, significantly increasing the computation cost. To overcome this, we propose an internal LM adaptation (ILMA) of the E2E model using text-only data. Trained with audio-transcript pairs, an E2E model implicitly learns an internal LM that characterizes the token sequence probability which is approximated by the E2E model output after zeroing out the encoder contribution. During ILMA, we ","authors_text":"Jinyu Li, Naoyuki Kanda, Xie Chen, Yashesh Gaur, Yifan Gong, Yu Wu, Zhong Meng","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T23:03:29Z","title":"Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05354","kind":"arxiv","version":5},"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:eaaad819099dc07ade3fee3438a366066ab384517248ac02781d023c4437fba7","target":"record","created_at":"2026-07-05T05:11:35Z","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":"cce5473377ba7b395accb694be339788fad6f5261eb7383db67d0667e75565e0","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-06T23:03:29Z","title_canon_sha256":"761261fe40e8786c072a0485b7fc3d3dec034b456328f71c9eb7386c6a37aab2"},"schema_version":"1.0","source":{"id":"2110.05354","kind":"arxiv","version":5}},"canonical_sha256":"b4dfd28e062e30926e33bc9e734284ddcf7d7b1e4f72fff5c2fb4a0e4257171b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4dfd28e062e30926e33bc9e734284ddcf7d7b1e4f72fff5c2fb4a0e4257171b","first_computed_at":"2026-07-05T05:11:35.243689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:35.243689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MR8DJurMM7ZGrV6LYc/Wc2BYqmIbQuwtTwH86GWTjRPwYQN0IFlC6k8l486OhMZ29WOcNSmJA+UU9wgvKuajAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:35.244177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05354","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaaad819099dc07ade3fee3438a366066ab384517248ac02781d023c4437fba7","sha256:6f6e7b1c7e3c5959f15a79be935fdd7c9c5ea1bca6cd74857860d06717fd673d"],"state_sha256":"8b5715cb3d65872df8c459ff1a8b1e9951384bd26e61743fcf68a37c72e2660c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbuehzCBMgGleycZ9yL3aKKTRUpJVRDSOoWluPfx6eeFVJMyg1GR/jwszuZu74UZUXEGnuI2U+BmemDkrXpRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:49:30.912029Z","bundle_sha256":"458df140f73661ca6e2bba0c95e194ec32c891c56d01921fe02e3b9921cc4872"}}