{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UKLKO3MQRAVWTNBGJA3D33EX3J","short_pith_number":"pith:UKLKO3MQ","canonical_record":{"source":{"id":"2406.03274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T13:52:55Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ed764ad969e1e7a9248de2bcd7cd0d2cfc3db1401fecde78b84df33bb3ec8cf0","abstract_canon_sha256":"4c9ba28276d72bf3f4565abbcf18c61818b010b99e2c846ca5cad69f2561251f"},"schema_version":"1.0"},"canonical_sha256":"a296a76d90882b69b42648363dec97da545d1cee88fe68698ac93f625a09965f","source":{"kind":"arxiv","id":"2406.03274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03274","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03274v2","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03274","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"UKLKO3MQRAVW","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"UKLKO3MQRAVWTNBG","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"UKLKO3MQ","created_at":"2026-07-05T08:30:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UKLKO3MQRAVWTNBGJA3D33EX3J","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T13:52:55Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ed764ad969e1e7a9248de2bcd7cd0d2cfc3db1401fecde78b84df33bb3ec8cf0","abstract_canon_sha256":"4c9ba28276d72bf3f4565abbcf18c61818b010b99e2c846ca5cad69f2561251f"},"schema_version":"1.0"},"canonical_sha256":"a296a76d90882b69b42648363dec97da545d1cee88fe68698ac93f625a09965f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:13.423565Z","signature_b64":"Y+2nKhKy9PTDzpyJUK4631Mlvr09tg7PLWIn4zP0RykKDxX0TahghS4KZNYBdyZVkrD8gRlnd1uQYN7AHqZrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a296a76d90882b69b42648363dec97da545d1cee88fe68698ac93f625a09965f","last_reissued_at":"2026-07-05T08:30:13.423057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:13.423057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03274","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":"2026-07-05T08:30:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wU0JymAp61YtYFtieto6iuDRGHkQsRz8SSU+fFuRIlbNKdEN+JF1oK5I8PPwehdW+6bcMFMaPLHKxkJT3EQUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:22:18.947990Z"},"content_sha256":"0f46a2433b1d32782c88ef8a793a621982dd4d9ab06b3d159f5fd0734f018a4b","schema_version":"1.0","event_id":"sha256:0f46a2433b1d32782c88ef8a793a621982dd4d9ab06b3d159f5fd0734f018a4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UKLKO3MQRAVWTNBGJA3D33EX3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing CTC-based speech recognition with diverse modeling units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Mingbin Xu, Shiyi Han, Xingyu Na, Zhen Huang, Zhihong Lei","submitted_at":"2024-06-05T13:52:55Z","abstract_excerpt":"In recent years, the evolution of end-to-end (E2E) automatic speech recognition (ASR) models has been remarkable, largely due to advances in deep learning architectures like transformer. On top of E2E systems, researchers have achieved substantial accuracy improvement by rescoring E2E model's N-best hypotheses with a phoneme-based model. This raises an interesting question about where the improvements come from other than the system combination effect. We examine the underlying mechanisms driving these gains and propose an efficient joint training approach, where E2E models are trained jointly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03274","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/2406.03274/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":"2026-07-05T08:30:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m73wlUFb9ePs2yVrVqTZ0SrmVE0L/5EHS855cgp0gdb7wNSvWgd4tb3R7t2y+udob920mQ6Nsr0iqoINizj8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:22:18.948538Z"},"content_sha256":"4c58bd1a30a4ea147251758eabc69d28aa1c3ef3bfde77abdc28e8c811a993fa","schema_version":"1.0","event_id":"sha256:4c58bd1a30a4ea147251758eabc69d28aa1c3ef3bfde77abdc28e8c811a993fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKLKO3MQRAVWTNBGJA3D33EX3J/bundle.json","state_url":"https://pith.science/pith/UKLKO3MQRAVWTNBGJA3D33EX3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKLKO3MQRAVWTNBGJA3D33EX3J/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":"2026-08-15T04:22:18Z","links":{"resolver":"https://pith.science/pith/UKLKO3MQRAVWTNBGJA3D33EX3J","bundle":"https://pith.science/pith/UKLKO3MQRAVWTNBGJA3D33EX3J/bundle.json","state":"https://pith.science/pith/UKLKO3MQRAVWTNBGJA3D33EX3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKLKO3MQRAVWTNBGJA3D33EX3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UKLKO3MQRAVWTNBGJA3D33EX3J","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":"4c9ba28276d72bf3f4565abbcf18c61818b010b99e2c846ca5cad69f2561251f","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T13:52:55Z","title_canon_sha256":"ed764ad969e1e7a9248de2bcd7cd0d2cfc3db1401fecde78b84df33bb3ec8cf0"},"schema_version":"1.0","source":{"id":"2406.03274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03274","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03274v2","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03274","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"UKLKO3MQRAVW","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"UKLKO3MQRAVWTNBG","created_at":"2026-07-05T08:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"UKLKO3MQ","created_at":"2026-07-05T08:30:13Z"}],"graph_snapshots":[{"event_id":"sha256:4c58bd1a30a4ea147251758eabc69d28aa1c3ef3bfde77abdc28e8c811a993fa","target":"graph","created_at":"2026-07-05T08:30:13Z","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/2406.03274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the evolution of end-to-end (E2E) automatic speech recognition (ASR) models has been remarkable, largely due to advances in deep learning architectures like transformer. On top of E2E systems, researchers have achieved substantial accuracy improvement by rescoring E2E model's N-best hypotheses with a phoneme-based model. This raises an interesting question about where the improvements come from other than the system combination effect. We examine the underlying mechanisms driving these gains and propose an efficient joint training approach, where E2E models are trained jointly","authors_text":"Mingbin Xu, Shiyi Han, Xingyu Na, Zhen Huang, Zhihong Lei","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T13:52:55Z","title":"Enhancing CTC-based speech recognition with diverse modeling units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03274","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":"sha256:0f46a2433b1d32782c88ef8a793a621982dd4d9ab06b3d159f5fd0734f018a4b","target":"record","created_at":"2026-07-05T08:30:13Z","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":"4c9ba28276d72bf3f4565abbcf18c61818b010b99e2c846ca5cad69f2561251f","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-05T13:52:55Z","title_canon_sha256":"ed764ad969e1e7a9248de2bcd7cd0d2cfc3db1401fecde78b84df33bb3ec8cf0"},"schema_version":"1.0","source":{"id":"2406.03274","kind":"arxiv","version":2}},"canonical_sha256":"a296a76d90882b69b42648363dec97da545d1cee88fe68698ac93f625a09965f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a296a76d90882b69b42648363dec97da545d1cee88fe68698ac93f625a09965f","first_computed_at":"2026-07-05T08:30:13.423057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:13.423057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y+2nKhKy9PTDzpyJUK4631Mlvr09tg7PLWIn4zP0RykKDxX0TahghS4KZNYBdyZVkrD8gRlnd1uQYN7AHqZrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:13.423565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f46a2433b1d32782c88ef8a793a621982dd4d9ab06b3d159f5fd0734f018a4b","sha256:4c58bd1a30a4ea147251758eabc69d28aa1c3ef3bfde77abdc28e8c811a993fa"],"state_sha256":"79b6aab6e84ffb01ff7b9c81b965801322db11c659c68d711365b73f15b6e696"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TpiqIFwPrgMtJHAqQRdpHYnup7mzg8o/zPIp9t1Pksw2/lx1v/9IANay5aS77EVn5krDuLmcO0U1hLK2iVehBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:22:18.952946Z","bundle_sha256":"9dcebd1226245ab509f1d9693cbe5b5db66928d908afc7b6c5a5925d26d7c854"}}