{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MNKK5GIMYSI3PA6WFOZOQTOV2S","short_pith_number":"pith:MNKK5GIM","canonical_record":{"source":{"id":"2104.01721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T00:16:27Z","cross_cats_sorted":[],"title_canon_sha256":"dd92314e3bab764a1f7d4911db76d4ef70d498055d227a655079120c2cc032e6","abstract_canon_sha256":"f237efe809e0ea52584dfa92aceab3ba9a4a73ba043a7d97dacdaf702f29c162"},"schema_version":"1.0"},"canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","source":{"kind":"arxiv","id":"2104.01721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01721","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01721v1","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01721","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"MNKK5GIMYSI3","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"MNKK5GIMYSI3PA6W","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"MNKK5GIM","created_at":"2026-07-05T02:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MNKK5GIMYSI3PA6WFOZOQTOV2S","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T00:16:27Z","cross_cats_sorted":[],"title_canon_sha256":"dd92314e3bab764a1f7d4911db76d4ef70d498055d227a655079120c2cc032e6","abstract_canon_sha256":"f237efe809e0ea52584dfa92aceab3ba9a4a73ba043a7d97dacdaf702f29c162"},"schema_version":"1.0"},"canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:02.890429Z","signature_b64":"yMXDxZ9VOIFwM7QR/Pq3b+/MrBTkdgXLwfVIrMhDcPG47iwAuQeJZ9gUxZmBqh79b84wmEC8NlojKTERyioNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","last_reissued_at":"2026-07-05T02:29:02.890049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:02.890049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01721","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":"2026-07-05T02:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rIZA6O1ysrtjTl61lIvG7jQ7j4UM+vEIVbBnbr5nU+hJ7raEUi182aymTmpFTAM96bDsAChLtgM1GP3t98DCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:31:31.572176Z"},"content_sha256":"25d5fd3d6898915b8e7fbacd1f8e9f206681146efc19bcc0db618794c0bc7537","schema_version":"1.0","event_id":"sha256:25d5fd3d6898915b8e7fbacd1f8e9f206681146efc19bcc0db618794c0bc7537"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MNKK5GIMYSI3PA6WFOZOQTOV2S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Jagadeesh Balam, Oleksii Hrinchuk, Somshubra Majumdar, Vahid Noroozi, Vitaly Lavrukhin","submitted_at":"2021-04-05T00:16:27Z","abstract_excerpt":"We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01721","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/2104.01721/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":"2026-07-05T02:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3y35Dkq++GFWMZq80Z3z7/C+l8LuyJBWG2vRM7U/ti2UXn6ql4xK3XQwQRvLKWvUbxk1B89wr/VpmRhUBFRxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:31:31.572560Z"},"content_sha256":"4631394145791fe9d9aea3bdb4141138f97244fd7c97fc42a2fea78416616b4b","schema_version":"1.0","event_id":"sha256:4631394145791fe9d9aea3bdb4141138f97244fd7c97fc42a2fea78416616b4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/bundle.json","state_url":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/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":"2026-07-06T08:31:31Z","links":{"resolver":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S","bundle":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/bundle.json","state":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MNKK5GIMYSI3PA6WFOZOQTOV2S","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":"f237efe809e0ea52584dfa92aceab3ba9a4a73ba043a7d97dacdaf702f29c162","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T00:16:27Z","title_canon_sha256":"dd92314e3bab764a1f7d4911db76d4ef70d498055d227a655079120c2cc032e6"},"schema_version":"1.0","source":{"id":"2104.01721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01721","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01721v1","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01721","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"MNKK5GIMYSI3","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"MNKK5GIMYSI3PA6W","created_at":"2026-07-05T02:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"MNKK5GIM","created_at":"2026-07-05T02:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:4631394145791fe9d9aea3bdb4141138f97244fd7c97fc42a2fea78416616b4b","target":"graph","created_at":"2026-07-05T02:29:02Z","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/2104.01721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best","authors_text":"Boris Ginsburg, Jagadeesh Balam, Oleksii Hrinchuk, Somshubra Majumdar, Vahid Noroozi, Vitaly Lavrukhin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T00:16:27Z","title":"Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01721","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":"sha256:25d5fd3d6898915b8e7fbacd1f8e9f206681146efc19bcc0db618794c0bc7537","target":"record","created_at":"2026-07-05T02:29:02Z","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":"f237efe809e0ea52584dfa92aceab3ba9a4a73ba043a7d97dacdaf702f29c162","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T00:16:27Z","title_canon_sha256":"dd92314e3bab764a1f7d4911db76d4ef70d498055d227a655079120c2cc032e6"},"schema_version":"1.0","source":{"id":"2104.01721","kind":"arxiv","version":1}},"canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","first_computed_at":"2026-07-05T02:29:02.890049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:02.890049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yMXDxZ9VOIFwM7QR/Pq3b+/MrBTkdgXLwfVIrMhDcPG47iwAuQeJZ9gUxZmBqh79b84wmEC8NlojKTERyioNAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:02.890429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25d5fd3d6898915b8e7fbacd1f8e9f206681146efc19bcc0db618794c0bc7537","sha256:4631394145791fe9d9aea3bdb4141138f97244fd7c97fc42a2fea78416616b4b"],"state_sha256":"65ec6c65c20c8c929addc8a1df74c6b5f34e28b24061558ea3230fbd982cb111"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2CoGPjCTwLIXEoDi1hwkO3PX5WvdYmD0uNPYwpaGIFTk9dBbZt8b3DJOiC5DaGexh4w+VBhZixu6VJYdLGMjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:31:31.575232Z","bundle_sha256":"f68d5b37d28ae0df760c0243d8778bb1b38ec71506778b7853e2c7860f81e227"}}