{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RZFDABDCXLCHAG2H7HUZQTHEU7","short_pith_number":"pith:RZFDABDC","canonical_record":{"source":{"id":"2406.19674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T06:22:23Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8718d05b0f83b3b8b4da13ef4c90562cf2835c5fd0e8c6946a18dd305dedb404","abstract_canon_sha256":"986506a31907518236924ec1d0a652c2feb05bc96f56fe2ec3d1c040ac3973ed"},"schema_version":"1.0"},"canonical_sha256":"8e4a300462bac4701b47f9e9984ce4a7e073d85e39fd7dd10f17fc0621505d05","source":{"kind":"arxiv","id":"2406.19674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19674","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19674v1","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19674","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"RZFDABDCXLCH","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"RZFDABDCXLCHAG2H","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"RZFDABDC","created_at":"2026-07-05T08:37:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RZFDABDCXLCHAG2H7HUZQTHEU7","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T06:22:23Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8718d05b0f83b3b8b4da13ef4c90562cf2835c5fd0e8c6946a18dd305dedb404","abstract_canon_sha256":"986506a31907518236924ec1d0a652c2feb05bc96f56fe2ec3d1c040ac3973ed"},"schema_version":"1.0"},"canonical_sha256":"8e4a300462bac4701b47f9e9984ce4a7e073d85e39fd7dd10f17fc0621505d05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:43.462355Z","signature_b64":"wpEM36zWmYFGMYoBG/7BTOIFNGcTX/jEGjZMWPkNRdweliUHXrN41ebmUX6ErtX4F/j/vewzLRDvzphdklMuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e4a300462bac4701b47f9e9984ce4a7e073d85e39fd7dd10f17fc0621505d05","last_reissued_at":"2026-07-05T08:37:43.461813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:43.461813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19674","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":"2026-07-05T08:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PReQzsLkyGxScGM0TNfp0vlIZAiI10WWkmAjJnGlIRvC3ydFDDJZ3NspHp/FrGdf9795LRTbOCQOPIdVGwSLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:29:17.781766Z"},"content_sha256":"beb15c45ff765e59290f2fac8a5c63c2d45f7007a4eb54029be2916c39fae131","schema_version":"1.0","event_id":"sha256:beb15c45ff765e59290f2fac8a5c63c2d45f7007a4eb54029be2916c39fae131"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RZFDABDCXLCHAG2H7HUZQTHEU7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More: Accurate Speech Recognition & Translation without Web-Scale Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Elena Rastorgueva, He Huang, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Nithin Rao Koluguri, Oleksii Hrinchuk, Piotr \\.Zelasko, Somshubra Majumdar, Vitaly Lavrukhin, Zhehuai Chen","submitted_at":"2024-06-28T06:22:23Z","abstract_excerpt":"Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and speech translation model, outperforms current state-of-the-art models - Whisper, OWSM, and Seamless-M4T on English, French, Spanish, and German languages, while being trained on an order of magnitude less data than these models. Three key factors enables such data-efficient model: (1) a FastConformer-based attention encoder-decoder architecture (2) training on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19674","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/2406.19674/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":"2026-07-05T08:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k9Wc3IfJzuvyZcLxBiffWpscyl0O1c+oxV1OB9ScuokHKFXHkhOXWykdFlvUQj8zxLYtITJkTg2Tkmg7CJ86CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:29:17.782170Z"},"content_sha256":"ea68080605ab7fecd63a31c9694a0640e172a883df6828fa2b7fed5113138503","schema_version":"1.0","event_id":"sha256:ea68080605ab7fecd63a31c9694a0640e172a883df6828fa2b7fed5113138503"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZFDABDCXLCHAG2H7HUZQTHEU7/bundle.json","state_url":"https://pith.science/pith/RZFDABDCXLCHAG2H7HUZQTHEU7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZFDABDCXLCHAG2H7HUZQTHEU7/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":"2026-07-06T08:29:17Z","links":{"resolver":"https://pith.science/pith/RZFDABDCXLCHAG2H7HUZQTHEU7","bundle":"https://pith.science/pith/RZFDABDCXLCHAG2H7HUZQTHEU7/bundle.json","state":"https://pith.science/pith/RZFDABDCXLCHAG2H7HUZQTHEU7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZFDABDCXLCHAG2H7HUZQTHEU7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RZFDABDCXLCHAG2H7HUZQTHEU7","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":"986506a31907518236924ec1d0a652c2feb05bc96f56fe2ec3d1c040ac3973ed","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T06:22:23Z","title_canon_sha256":"8718d05b0f83b3b8b4da13ef4c90562cf2835c5fd0e8c6946a18dd305dedb404"},"schema_version":"1.0","source":{"id":"2406.19674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19674","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19674v1","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19674","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"RZFDABDCXLCH","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"RZFDABDCXLCHAG2H","created_at":"2026-07-05T08:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"RZFDABDC","created_at":"2026-07-05T08:37:43Z"}],"graph_snapshots":[{"event_id":"sha256:ea68080605ab7fecd63a31c9694a0640e172a883df6828fa2b7fed5113138503","target":"graph","created_at":"2026-07-05T08:37:43Z","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/2406.19674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and speech translation model, outperforms current state-of-the-art models - Whisper, OWSM, and Seamless-M4T on English, French, Spanish, and German languages, while being trained on an order of magnitude less data than these models. Three key factors enables such data-efficient model: (1) a FastConformer-based attention encoder-decoder architecture (2) training on","authors_text":"Boris Ginsburg, Elena Rastorgueva, He Huang, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Nithin Rao Koluguri, Oleksii Hrinchuk, Piotr \\.Zelasko, Somshubra Majumdar, Vitaly Lavrukhin, Zhehuai Chen","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T06:22:23Z","title":"Less is More: Accurate Speech Recognition & Translation without Web-Scale Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19674","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:beb15c45ff765e59290f2fac8a5c63c2d45f7007a4eb54029be2916c39fae131","target":"record","created_at":"2026-07-05T08:37:43Z","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":"986506a31907518236924ec1d0a652c2feb05bc96f56fe2ec3d1c040ac3973ed","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T06:22:23Z","title_canon_sha256":"8718d05b0f83b3b8b4da13ef4c90562cf2835c5fd0e8c6946a18dd305dedb404"},"schema_version":"1.0","source":{"id":"2406.19674","kind":"arxiv","version":1}},"canonical_sha256":"8e4a300462bac4701b47f9e9984ce4a7e073d85e39fd7dd10f17fc0621505d05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e4a300462bac4701b47f9e9984ce4a7e073d85e39fd7dd10f17fc0621505d05","first_computed_at":"2026-07-05T08:37:43.461813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:43.461813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wpEM36zWmYFGMYoBG/7BTOIFNGcTX/jEGjZMWPkNRdweliUHXrN41ebmUX6ErtX4F/j/vewzLRDvzphdklMuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:43.462355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beb15c45ff765e59290f2fac8a5c63c2d45f7007a4eb54029be2916c39fae131","sha256:ea68080605ab7fecd63a31c9694a0640e172a883df6828fa2b7fed5113138503"],"state_sha256":"0b9abac5a527390b1eb59587e66da3fa838bde47dd9d0115431a457cab8954ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gklni9CsP/Tau7oRyDSw06n8FbcrHZHt4emWhi4/iT4FUIbL3y2aB8tNT85nTZ60p776f/T9mjp6f004kqAvCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:29:17.784198Z","bundle_sha256":"b53e91d9c84a556921d9101b12d40b9c20b9d99de682ed08527f1706be4487c0"}}