{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UUDUOAYAKWPB6IEZDATAW2AIRQ","short_pith_number":"pith:UUDUOAYA","canonical_record":{"source":{"id":"2305.07677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-11T22:44:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c615b4befa464353f79631550e5fcbfb5e3afe0d34281c8d444bd6d946b5e688","abstract_canon_sha256":"fb0b900145f574c889faec78d906eaf1e316be0cd5eb54d33ba4233245c89ec1"},"schema_version":"1.0"},"canonical_sha256":"a507470300559e1f209918260b68088c1920a5a5571d5d973873f8fbdbbd9dfa","source":{"kind":"arxiv","id":"2305.07677","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07677","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07677v2","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07677","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"UUDUOAYAKWPB","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"UUDUOAYAKWPB6IEZ","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"UUDUOAYA","created_at":"2026-07-05T06:13:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UUDUOAYAKWPB6IEZDATAW2AIRQ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.07677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-11T22:44:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c615b4befa464353f79631550e5fcbfb5e3afe0d34281c8d444bd6d946b5e688","abstract_canon_sha256":"fb0b900145f574c889faec78d906eaf1e316be0cd5eb54d33ba4233245c89ec1"},"schema_version":"1.0"},"canonical_sha256":"a507470300559e1f209918260b68088c1920a5a5571d5d973873f8fbdbbd9dfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:39.483301Z","signature_b64":"/HBqzvQcO0gINieR3t+iiePunJnltasiITSgdKKD8QdssXSATqqQGr+DH/EyzojwsiQFKaws6s6SMJn8FVZ0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a507470300559e1f209918260b68088c1920a5a5571d5d973873f8fbdbbd9dfa","last_reissued_at":"2026-07-05T06:13:39.482762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:39.482762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.07677","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"paM9zqX5j+shoKZ69xtl/HO0qDzXPYez+Xuvbvj64im99kFPMR6a30QtvYl+bf23SS025M3Ezz19wj0qjbM7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:01:47.307221Z"},"content_sha256":"e6ecf1e20d838894a4e3197160bf27119389a823b9acbe40c647813ff1581482","schema_version":"1.0","event_id":"sha256:e6ecf1e20d838894a4e3197160bf27119389a823b9acbe40c647813ff1581482"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UUDUOAYAKWPB6IEZDATAW2AIRQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Audio Text Encoders are Effective Multi-Modal Rescorers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Anshu Bhatia, Jinglun Cai, Monica Sunkara, Sravan Bodapati, Xiao Pan, Xilai Li","submitted_at":"2023-05-11T22:44:43Z","abstract_excerpt":"Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which incorporates acoustic representations into the input space of MLM. We adopt contrastive learning for effectively aligning the modalities by learning shared representations. We show that using a multi-modal rescorer is beneficial for domain generalization of the ASR system when target domain data is unavailable. MATE reduces word error rate (WER) by 4%-16% o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07677","kind":"arxiv","version":2},"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/2305.07677/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":"2026-07-05T06:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BkbaoNvqVWD7WUhI6PPSKK9EkejBjlYgu3r43rwgbyNA63d+Hw9AI6J5a3d5N7U+hpWenUoKZp7z7F5dYnBYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:01:47.307708Z"},"content_sha256":"d43b48881576bd5215af2de2d1f26f1f56a67ce21b86e2b52377816c9b09bde7","schema_version":"1.0","event_id":"sha256:d43b48881576bd5215af2de2d1f26f1f56a67ce21b86e2b52377816c9b09bde7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ/bundle.json","state_url":"https://pith.science/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ/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":"2026-08-15T15:01:47Z","links":{"resolver":"https://pith.science/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ","bundle":"https://pith.science/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ/bundle.json","state":"https://pith.science/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUDUOAYAKWPB6IEZDATAW2AIRQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UUDUOAYAKWPB6IEZDATAW2AIRQ","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":"fb0b900145f574c889faec78d906eaf1e316be0cd5eb54d33ba4233245c89ec1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-11T22:44:43Z","title_canon_sha256":"c615b4befa464353f79631550e5fcbfb5e3afe0d34281c8d444bd6d946b5e688"},"schema_version":"1.0","source":{"id":"2305.07677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07677","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07677v2","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07677","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"UUDUOAYAKWPB","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"UUDUOAYAKWPB6IEZ","created_at":"2026-07-05T06:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"UUDUOAYA","created_at":"2026-07-05T06:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:d43b48881576bd5215af2de2d1f26f1f56a67ce21b86e2b52377816c9b09bde7","target":"graph","created_at":"2026-07-05T06:13:39Z","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/2305.07677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which incorporates acoustic representations into the input space of MLM. We adopt contrastive learning for effectively aligning the modalities by learning shared representations. We show that using a multi-modal rescorer is beneficial for domain generalization of the ASR system when target domain data is unavailable. MATE reduces word error rate (WER) by 4%-16% o","authors_text":"Anshu Bhatia, Jinglun Cai, Monica Sunkara, Sravan Bodapati, Xiao Pan, Xilai Li","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-11T22:44:43Z","title":"Masked Audio Text Encoders are Effective Multi-Modal Rescorers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07677","kind":"arxiv","version":2},"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:e6ecf1e20d838894a4e3197160bf27119389a823b9acbe40c647813ff1581482","target":"record","created_at":"2026-07-05T06:13:39Z","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":"fb0b900145f574c889faec78d906eaf1e316be0cd5eb54d33ba4233245c89ec1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-11T22:44:43Z","title_canon_sha256":"c615b4befa464353f79631550e5fcbfb5e3afe0d34281c8d444bd6d946b5e688"},"schema_version":"1.0","source":{"id":"2305.07677","kind":"arxiv","version":2}},"canonical_sha256":"a507470300559e1f209918260b68088c1920a5a5571d5d973873f8fbdbbd9dfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a507470300559e1f209918260b68088c1920a5a5571d5d973873f8fbdbbd9dfa","first_computed_at":"2026-07-05T06:13:39.482762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:39.482762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HBqzvQcO0gINieR3t+iiePunJnltasiITSgdKKD8QdssXSATqqQGr+DH/EyzojwsiQFKaws6s6SMJn8FVZ0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:39.483301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6ecf1e20d838894a4e3197160bf27119389a823b9acbe40c647813ff1581482","sha256:d43b48881576bd5215af2de2d1f26f1f56a67ce21b86e2b52377816c9b09bde7"],"state_sha256":"a8525d9b5a1079b52f4f4f2422464f864bbc2b9ab1f194efc04f006d64634fa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYAGv0SomRDZTHJ5acfnbFFkTtJ6xJRk0xSL65VpDqTrZUry4o9aenqiMqaweBLpZciF6sNwfhuWUg8NCihmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:01:47.310846Z","bundle_sha256":"5b6a6c098a5131068430a816b3d77243cc8debd6bc7f429fd6336a2d6704612c"}}