{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2JJB4VDSC4SXMM4I7DLKHFDFZH","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":"2124fdcd33bb04884b10ed44c371043864b59a29071de12b2e4731f262386d96","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T10:45:07Z","title_canon_sha256":"79277c7caa0c326664d70c7447e47089866decac7fb9e9ecd66264f9f457a2bf"},"schema_version":"1.0","source":{"id":"2311.00430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00430","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00430v1","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00430","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"2JJB4VDSC4SX","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"2JJB4VDSC4SXMM4I","created_at":"2026-07-05T07:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"2JJB4VDS","created_at":"2026-07-05T07:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:8d0f00c97cfd968ad8586319b7c7956cb607049090bce3f0f949c16d725dca1d","target":"graph","created_at":"2026-07-05T07:07:57Z","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/2311.00430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the size of pre-trained speech recognition models increases, running these large models in low-latency or resource-constrained environments becomes challenging. In this work, we leverage pseudo-labelling to assemble a large-scale open-source dataset which we use to distill the Whisper model into a smaller variant, called Distil-Whisper. Using a simple word error rate (WER) heuristic, we select only the highest quality pseudo-labels for training. The distilled model is 5.8 times faster with 51% fewer parameters, while performing to within 1% WER on out-of-distribution test data in a zero-sho","authors_text":"Alexander M. Rush, Patrick von Platen, Sanchit Gandhi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T10:45:07Z","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00430","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":"sha256:259212c6e0a998076c1fd7501105f595b7999f4042d51b2927f831c2ab853df3","target":"record","created_at":"2026-07-05T07:07:57Z","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":"2124fdcd33bb04884b10ed44c371043864b59a29071de12b2e4731f262386d96","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T10:45:07Z","title_canon_sha256":"79277c7caa0c326664d70c7447e47089866decac7fb9e9ecd66264f9f457a2bf"},"schema_version":"1.0","source":{"id":"2311.00430","kind":"arxiv","version":1}},"canonical_sha256":"d2521e54721725763388f8d6a39465c9e548fd25868e25797f4a08fa5cef220e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2521e54721725763388f8d6a39465c9e548fd25868e25797f4a08fa5cef220e","first_computed_at":"2026-07-05T07:07:57.625851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:57.625851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mj9X/nQH82P+bydPOWVJWbVpDODhYLvW9es3uwWSGYlurpGRdL4MFaRfjecNP8e97lDE/Gwgkau66+xtZIsMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:57.626434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:259212c6e0a998076c1fd7501105f595b7999f4042d51b2927f831c2ab853df3","sha256:8d0f00c97cfd968ad8586319b7c7956cb607049090bce3f0f949c16d725dca1d"],"state_sha256":"c8ef4569c6cbaed1d81899322d2008b72309dbabcdf3d0851f966b022cc9444b"}