{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YBAQQSACI3W57PZFOKT4KJT55G","short_pith_number":"pith:YBAQQSAC","canonical_record":{"source":{"id":"2509.09197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T07:12:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fda4a61f766139692a9b07d0778ddc447c0f61f15edf58fdd40e58802ec98143","abstract_canon_sha256":"c345a270c92bbe8e57e8882c638190d6ddd6029ca94152384a4043f627e7b29a"},"schema_version":"1.0"},"canonical_sha256":"c04108480246eddfbf2572a7c5267de9a2b11f99a161643cecf790ec76526185","source":{"kind":"arxiv","id":"2509.09197","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09197","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09197v1","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09197","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"YBAQQSACI3W5","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"YBAQQSACI3W57PZF","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"YBAQQSAC","created_at":"2026-07-05T12:09:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YBAQQSACI3W57PZFOKT4KJT55G","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T07:12:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fda4a61f766139692a9b07d0778ddc447c0f61f15edf58fdd40e58802ec98143","abstract_canon_sha256":"c345a270c92bbe8e57e8882c638190d6ddd6029ca94152384a4043f627e7b29a"},"schema_version":"1.0"},"canonical_sha256":"c04108480246eddfbf2572a7c5267de9a2b11f99a161643cecf790ec76526185","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:31.455995Z","signature_b64":"whjc83nWMVG7B7JZXS14jUsuuRI/RhVI3vl6FzNAO79bYP0c3jrhpNIF7uyvI0P7xhtoIO8jcWBoewqFbW67Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04108480246eddfbf2572a7c5267de9a2b11f99a161643cecf790ec76526185","last_reissued_at":"2026-07-05T12:09:31.455473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:31.455473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09197","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":"2026-07-05T12:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCuw8aJK2yI3xgq7t6JmdbFtvN0Eo4RmFPuLfIm0AkjzRr2otsvr/q16QzpUaprcrdP4FfUm6w6YoHii/wk4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:02:33.020291Z"},"content_sha256":"91d94c1629a79e337f0f1e59c8b5a8e7c6a47d5e29758328b6d9ba1663a1899e","schema_version":"1.0","event_id":"sha256:91d94c1629a79e337f0f1e59c8b5a8e7c6a47d5e29758328b6d9ba1663a1899e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YBAQQSACI3W57PZFOKT4KJT55G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chin Yuen Kwok, Eng Siong Chng, Jia Qi Yip","submitted_at":"2025-09-11T07:12:17Z","abstract_excerpt":"Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to prioritize rare words. While training the module on synthetic rare word data is more effective than using non-rare-word data, it can lead to overfitting due to artifacts in the synthetic audio. To address this, we enhance the TCPGen-based contextual biasing approach and propose a keyword-aware loss function that additionally focuses on biased words when tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09197","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/2509.09197/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":"2026-07-05T12:09:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJVjxnNV2Rdd4AthYUV2ZVReSiHARuU5DtHz5Xj7fG5LhKraXl97xMUeJ9eDw4ft1L/FUK9bAX1OibNLkLcUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:02:33.020789Z"},"content_sha256":"631316fdc1f8d8caafdf1585df08d36f5def8ad1be427b2561741d8184187083","schema_version":"1.0","event_id":"sha256:631316fdc1f8d8caafdf1585df08d36f5def8ad1be427b2561741d8184187083"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBAQQSACI3W57PZFOKT4KJT55G/bundle.json","state_url":"https://pith.science/pith/YBAQQSACI3W57PZFOKT4KJT55G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBAQQSACI3W57PZFOKT4KJT55G/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":"2026-08-15T10:02:33Z","links":{"resolver":"https://pith.science/pith/YBAQQSACI3W57PZFOKT4KJT55G","bundle":"https://pith.science/pith/YBAQQSACI3W57PZFOKT4KJT55G/bundle.json","state":"https://pith.science/pith/YBAQQSACI3W57PZFOKT4KJT55G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBAQQSACI3W57PZFOKT4KJT55G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBAQQSACI3W57PZFOKT4KJT55G","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":"c345a270c92bbe8e57e8882c638190d6ddd6029ca94152384a4043f627e7b29a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T07:12:17Z","title_canon_sha256":"fda4a61f766139692a9b07d0778ddc447c0f61f15edf58fdd40e58802ec98143"},"schema_version":"1.0","source":{"id":"2509.09197","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09197","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09197v1","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09197","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"YBAQQSACI3W5","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"YBAQQSACI3W57PZF","created_at":"2026-07-05T12:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"YBAQQSAC","created_at":"2026-07-05T12:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:631316fdc1f8d8caafdf1585df08d36f5def8ad1be427b2561741d8184187083","target":"graph","created_at":"2026-07-05T12:09:31Z","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/2509.09197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to prioritize rare words. While training the module on synthetic rare word data is more effective than using non-rare-word data, it can lead to overfitting due to artifacts in the synthetic audio. To address this, we enhance the TCPGen-based contextual biasing approach and propose a keyword-aware loss function that additionally focuses on biased words when tra","authors_text":"Chin Yuen Kwok, Eng Siong Chng, Jia Qi Yip","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T07:12:17Z","title":"Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09197","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":"sha256:91d94c1629a79e337f0f1e59c8b5a8e7c6a47d5e29758328b6d9ba1663a1899e","target":"record","created_at":"2026-07-05T12:09:31Z","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":"c345a270c92bbe8e57e8882c638190d6ddd6029ca94152384a4043f627e7b29a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T07:12:17Z","title_canon_sha256":"fda4a61f766139692a9b07d0778ddc447c0f61f15edf58fdd40e58802ec98143"},"schema_version":"1.0","source":{"id":"2509.09197","kind":"arxiv","version":1}},"canonical_sha256":"c04108480246eddfbf2572a7c5267de9a2b11f99a161643cecf790ec76526185","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c04108480246eddfbf2572a7c5267de9a2b11f99a161643cecf790ec76526185","first_computed_at":"2026-07-05T12:09:31.455473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:31.455473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"whjc83nWMVG7B7JZXS14jUsuuRI/RhVI3vl6FzNAO79bYP0c3jrhpNIF7uyvI0P7xhtoIO8jcWBoewqFbW67Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:31.455995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09197","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91d94c1629a79e337f0f1e59c8b5a8e7c6a47d5e29758328b6d9ba1663a1899e","sha256:631316fdc1f8d8caafdf1585df08d36f5def8ad1be427b2561741d8184187083"],"state_sha256":"66377c03a2bbc7ee295c7d95dc7f1b67fa85e9e7470c719c8d215baa1a7da747"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WrvFij/ErCqVlXyyR4aLpepeFrqcxMofBS1aYgZkagwYTqnxKwAorp990gVgWOrQ78WsDet3lkZsOBeYLr30AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:02:33.024602Z","bundle_sha256":"67993736fa92a23f32455fc597ea7e2c600a3e375b3f1f5a53a3aed79446803d"}}