{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SHWOJI5PR2YAAGMMPXEVMX5XG6","short_pith_number":"pith:SHWOJI5P","canonical_record":{"source":{"id":"2306.02317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T10:00:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"eb28849afcea0ad93286ae903deff6243543d0972f41fa6e2ff78f014e36b965","abstract_canon_sha256":"845ba4de203139d852a8156279f729550dc3d24cc0507fa886687b2e9ae5f409"},"schema_version":"1.0"},"canonical_sha256":"91ece4a3af8eb000198c7dc9565fb7378f3b9f7de7047acc7db600356bf076f6","source":{"kind":"arxiv","id":"2306.02317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02317","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02317v1","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02317","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"SHWOJI5PR2YA","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"SHWOJI5PR2YAAGMM","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"SHWOJI5P","created_at":"2026-07-05T06:17:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SHWOJI5PR2YAAGMMPXEVMX5XG6","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T10:00:12Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"eb28849afcea0ad93286ae903deff6243543d0972f41fa6e2ff78f014e36b965","abstract_canon_sha256":"845ba4de203139d852a8156279f729550dc3d24cc0507fa886687b2e9ae5f409"},"schema_version":"1.0"},"canonical_sha256":"91ece4a3af8eb000198c7dc9565fb7378f3b9f7de7047acc7db600356bf076f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:15.689024Z","signature_b64":"Wxd0IJE5iod1M56JqEZgXAiJFTAm4t2UfjKnWp89NAhL/VxIpe5lBnOJAyugJkvCVN4v5ri2yzklZQuTbTqtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91ece4a3af8eb000198c7dc9565fb7378f3b9f7de7047acc7db600356bf076f6","last_reissued_at":"2026-07-05T06:17:15.688553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:15.688553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02317","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":"2026-07-05T06:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4JhZIJW5h8vUwnywzSl9f8alxY/LB6wknKVGg0lIna/xwOn2ASG/Eak1rlQslrUdS7NmWfEOxPdq4+u4CbgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:03:16.293790Z"},"content_sha256":"c9e5c35211f0cacb217ea254350bb7609085742d618235020ccdbe5bfa1a02f9","schema_version":"1.0","event_id":"sha256:c9e5c35211f0cacb217ea254350bb7609085742d618235020ccdbe5bfa1a02f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SHWOJI5PR2YAAGMMPXEVMX5XG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexandra Antonova, Boris Ginsburg, Evelina Bakhturina","submitted_at":"2023-06-04T10:00:12Z","abstract_excerpt":"Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval mechanisms, usually based on minimum edit distance between fragments of ASR hypothesis and user phrases. However, the edit-distance approach is slow, non-trainable, and may have low recall as it relies only on common letters. We propose: 1) a novel algorithm for candidate retrieval, based on misspelled n-gram mappings, which gives up to 90% recall with just t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02317","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/2306.02317/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":"2026-07-05T06:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9H94ykEmixwy5VO9dIBf2lbgrjVT0Bx2k1CUmuSK53ML/x6VFWl3cVgWkO83wwjB9A8G26nR2JsWVyCxKTNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:03:16.294314Z"},"content_sha256":"45021fb80244272e4e9bd61df4db6c8abcef67ef993c5784bb3375c287f94432","schema_version":"1.0","event_id":"sha256:45021fb80244272e4e9bd61df4db6c8abcef67ef993c5784bb3375c287f94432"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6/bundle.json","state_url":"https://pith.science/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6/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":"2026-08-06T03:03:16Z","links":{"resolver":"https://pith.science/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6","bundle":"https://pith.science/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6/bundle.json","state":"https://pith.science/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHWOJI5PR2YAAGMMPXEVMX5XG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SHWOJI5PR2YAAGMMPXEVMX5XG6","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":"845ba4de203139d852a8156279f729550dc3d24cc0507fa886687b2e9ae5f409","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T10:00:12Z","title_canon_sha256":"eb28849afcea0ad93286ae903deff6243543d0972f41fa6e2ff78f014e36b965"},"schema_version":"1.0","source":{"id":"2306.02317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02317","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02317v1","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02317","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"SHWOJI5PR2YA","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"SHWOJI5PR2YAAGMM","created_at":"2026-07-05T06:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"SHWOJI5P","created_at":"2026-07-05T06:17:15Z"}],"graph_snapshots":[{"event_id":"sha256:45021fb80244272e4e9bd61df4db6c8abcef67ef993c5784bb3375c287f94432","target":"graph","created_at":"2026-07-05T06:17:15Z","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/2306.02317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval mechanisms, usually based on minimum edit distance between fragments of ASR hypothesis and user phrases. However, the edit-distance approach is slow, non-trainable, and may have low recall as it relies only on common letters. We propose: 1) a novel algorithm for candidate retrieval, based on misspelled n-gram mappings, which gives up to 90% recall with just t","authors_text":"Alexandra Antonova, Boris Ginsburg, Evelina Bakhturina","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T10:00:12Z","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02317","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:c9e5c35211f0cacb217ea254350bb7609085742d618235020ccdbe5bfa1a02f9","target":"record","created_at":"2026-07-05T06:17:15Z","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":"845ba4de203139d852a8156279f729550dc3d24cc0507fa886687b2e9ae5f409","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T10:00:12Z","title_canon_sha256":"eb28849afcea0ad93286ae903deff6243543d0972f41fa6e2ff78f014e36b965"},"schema_version":"1.0","source":{"id":"2306.02317","kind":"arxiv","version":1}},"canonical_sha256":"91ece4a3af8eb000198c7dc9565fb7378f3b9f7de7047acc7db600356bf076f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91ece4a3af8eb000198c7dc9565fb7378f3b9f7de7047acc7db600356bf076f6","first_computed_at":"2026-07-05T06:17:15.688553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:15.688553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wxd0IJE5iod1M56JqEZgXAiJFTAm4t2UfjKnWp89NAhL/VxIpe5lBnOJAyugJkvCVN4v5ri2yzklZQuTbTqtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:15.689024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9e5c35211f0cacb217ea254350bb7609085742d618235020ccdbe5bfa1a02f9","sha256:45021fb80244272e4e9bd61df4db6c8abcef67ef993c5784bb3375c287f94432"],"state_sha256":"fe2c93b651ac50fbc498b55170ac5019fea170b717fe7c1716ab3468ee1c4aff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xdj3j7paYHFH1gpnBk4FK4jXwLlwfKKL7mYfmtRq7TsDulTJHHrC94oYZxoRqVLNWPCCUuzuNKLilw0KQmcuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:03:16.297697Z","bundle_sha256":"7324cb9bd885bcb1bd511d68c5b8a27035cbcbb198cb580c65362270520821f8"}}