{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IDGGIM66CW5GDBLQRINKSVJ2L3","short_pith_number":"pith:IDGGIM66","canonical_record":{"source":{"id":"2306.01942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T22:56:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d519e85f57ba7d11bcaf295a5158e9122ee5123352d2e6aa8bee332dc6d0bd38","abstract_canon_sha256":"fb5e4dbcfed23d3c9172be4905628febf12dbca1971273a02b7106b6e9c0830c"},"schema_version":"1.0"},"canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","source":{"kind":"arxiv","id":"2306.01942","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01942","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01942v1","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01942","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"IDGGIM66CW5G","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"IDGGIM66CW5GDBLQ","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"IDGGIM66","created_at":"2026-07-05T06:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IDGGIM66CW5GDBLQRINKSVJ2L3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.01942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T22:56:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d519e85f57ba7d11bcaf295a5158e9122ee5123352d2e6aa8bee332dc6d0bd38","abstract_canon_sha256":"fb5e4dbcfed23d3c9172be4905628febf12dbca1971273a02b7106b6e9c0830c"},"schema_version":"1.0"},"canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:11.262264Z","signature_b64":"PQtF7BLVEa8FGJVbgmROOwBG3Er3Rpr7pCJjmmjf/n/bKBHfJIGkihF6lt45xuBXqDnALHh9HYPqRIoWMvYXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","last_reissued_at":"2026-07-05T06:17:11.261826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:11.261826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.01942","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":"2026-07-05T06:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c/YCoQjTSfl2fQxJyjvKCpU7DhOw9Pv0/BiA1casUrlxSxq0YOIM+BFPQGrqA4hYgwwnBSZ7gi5O53g8T9b8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:51:49.656047Z"},"content_sha256":"499c0d67b0eca71b76588e09bead25b9af2e2ac395469060d82002f940680fe6","schema_version":"1.0","event_id":"sha256:499c0d67b0eca71b76588e09bead25b9af2e2ac395469060d82002f940680fe6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IDGGIM66CW5GDBLQRINKSVJ2L3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Guangzhi Sun, Philip C. Woodland, Xianrui Zheng","submitted_at":"2023-06-02T22:56:01Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent content words that occur in a particular task may still exhibit poor ASR performance, with contextual biasing a possible remedy. This paper investigates the effectiveness of neural contextual biasing for Whisper combined with GPT-2. Specifically, this paper proposes integrating an adapted tree-constrained pointer generator (TCPGen) component for Whisper and a dedicated training s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01942","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/2306.01942/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":"2026-07-05T06:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gdCLGFbfaxfC1HtqF7ypEwpo/N4mgeFtKuAg3JMv7r0igS6/SugAtfFpSyxvj6vKRM/zJsgnBBWwt2FaHRcgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:51:49.656439Z"},"content_sha256":"78b7be704f14769e214fee26e38ae7228374a1c55977a68c06d7503df085dc54","schema_version":"1.0","event_id":"sha256:78b7be704f14769e214fee26e38ae7228374a1c55977a68c06d7503df085dc54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/bundle.json","state_url":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/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":"2026-08-07T23:51:49Z","links":{"resolver":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3","bundle":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/bundle.json","state":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IDGGIM66CW5GDBLQRINKSVJ2L3","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":"fb5e4dbcfed23d3c9172be4905628febf12dbca1971273a02b7106b6e9c0830c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T22:56:01Z","title_canon_sha256":"d519e85f57ba7d11bcaf295a5158e9122ee5123352d2e6aa8bee332dc6d0bd38"},"schema_version":"1.0","source":{"id":"2306.01942","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01942","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01942v1","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01942","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"IDGGIM66CW5G","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"IDGGIM66CW5GDBLQ","created_at":"2026-07-05T06:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"IDGGIM66","created_at":"2026-07-05T06:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:78b7be704f14769e214fee26e38ae7228374a1c55977a68c06d7503df085dc54","target":"graph","created_at":"2026-07-05T06:17:11Z","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/2306.01942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent content words that occur in a particular task may still exhibit poor ASR performance, with contextual biasing a possible remedy. This paper investigates the effectiveness of neural contextual biasing for Whisper combined with GPT-2. Specifically, this paper proposes integrating an adapted tree-constrained pointer generator (TCPGen) component for Whisper and a dedicated training s","authors_text":"Chao Zhang, Guangzhi Sun, Philip C. Woodland, Xianrui Zheng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T22:56:01Z","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01942","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":"sha256:499c0d67b0eca71b76588e09bead25b9af2e2ac395469060d82002f940680fe6","target":"record","created_at":"2026-07-05T06:17:11Z","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":"fb5e4dbcfed23d3c9172be4905628febf12dbca1971273a02b7106b6e9c0830c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T22:56:01Z","title_canon_sha256":"d519e85f57ba7d11bcaf295a5158e9122ee5123352d2e6aa8bee332dc6d0bd38"},"schema_version":"1.0","source":{"id":"2306.01942","kind":"arxiv","version":1}},"canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","first_computed_at":"2026-07-05T06:17:11.261826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:11.261826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PQtF7BLVEa8FGJVbgmROOwBG3Er3Rpr7pCJjmmjf/n/bKBHfJIGkihF6lt45xuBXqDnALHh9HYPqRIoWMvYXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:11.262264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01942","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:499c0d67b0eca71b76588e09bead25b9af2e2ac395469060d82002f940680fe6","sha256:78b7be704f14769e214fee26e38ae7228374a1c55977a68c06d7503df085dc54"],"state_sha256":"3f004bf3aae081aff898bba527e424a264ba5ef15517b93ce4b2d6eb97c6edc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8b+Cf2AzIjZ68bEI43fyL3j/P6p6IZ6MI4kmb5XcL/JD52cZsRW072kzoF8bKoyZXk0fsoxFJimGHITa6me+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:51:49.659340Z","bundle_sha256":"6cc14c8e9e56b1c39d4d95056b55620cdcc4ba90eb4eb12c33543aa775206096"}}