{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3BTEVUEPXFQECOWLDJGM35N3IE","short_pith_number":"pith:3BTEVUEP","canonical_record":{"source":{"id":"2506.07659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T11:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"5f3a7ebc103398400918fe4b1116f338aaf57b687ef276db42436ff7aa8508bb","abstract_canon_sha256":"9aab0a4082d5cc21eb29f0cd8a64dbc7ca3122f5fd9be07753d85478e9a6be82"},"schema_version":"1.0"},"canonical_sha256":"d8664ad08fb960413acb1a4ccdf5bb41211a3bc0255a3cb7a1befd23148bc1b0","source":{"kind":"arxiv","id":"2506.07659","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07659","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07659v1","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07659","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"3BTEVUEPXFQE","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"3BTEVUEPXFQECOWL","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"3BTEVUEP","created_at":"2026-07-05T11:18:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3BTEVUEPXFQECOWLDJGM35N3IE","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T11:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"5f3a7ebc103398400918fe4b1116f338aaf57b687ef276db42436ff7aa8508bb","abstract_canon_sha256":"9aab0a4082d5cc21eb29f0cd8a64dbc7ca3122f5fd9be07753d85478e9a6be82"},"schema_version":"1.0"},"canonical_sha256":"d8664ad08fb960413acb1a4ccdf5bb41211a3bc0255a3cb7a1befd23148bc1b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:31.123159Z","signature_b64":"AiTZt45sUnUZM+E74A8UZrhDg+X6Bp3n88mP/xElimgkgprGz/SUva1zcBBlkrBrHVu9ZktwKXzcl28hs474Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8664ad08fb960413acb1a4ccdf5bb41211a3bc0255a3cb7a1befd23148bc1b0","last_reissued_at":"2026-07-05T11:18:31.122666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:31.122666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07659","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":"2026-07-05T11:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SQvb4NmjLeDa44nVAUfa8n6wGRP1OSFV3OC9aTduMqx/tUqGsbsOhhCDOiGvj9ASQ3KQqw14C9NYMfIgEbGZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:17:21.526801Z"},"content_sha256":"650d12d7b256e4ece84eedccd3b447b38254d830c92a7d1bc78169cfeb35c71e","schema_version":"1.0","event_id":"sha256:650d12d7b256e4ece84eedccd3b447b38254d830c92a7d1bc78169cfeb35c71e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3BTEVUEPXFQECOWLDJGM35N3IE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Semi-Supervised Pipeline for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andrei Andrusenko, Ante Jukic, Nikolay Karpov, Nune Tadevosyan, Vitaly Lavrukhin","submitted_at":"2025-06-09T11:31:24Z","abstract_excerpt":"Automatic Speech Recognition has been a longstanding research area, with substantial efforts dedicated to integrating semi-supervised learning due to the scarcity of labeled datasets. However, most prior work has focused on improving learning algorithms using existing datasets, without providing a complete public framework for large-scale semi-supervised training across new datasets or languages. In this work, we introduce a fully open-source semi-supervised training framework encompassing the entire pipeline: from unlabeled data collection to pseudo-labeling and model training. Our approach e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07659","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/2506.07659/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":"2026-07-05T11:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aV46xEv+LE/p4Fifk5rWRWjA1GIZUmexZH0jkh7Lq/aQgtucidY5OJ461QBz/PCK5R7VFmC/ygLcUT9hAbfZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:17:21.527866Z"},"content_sha256":"3fb71b6453c27c68a939dee3dbf04547baf8a6aec25a9f33dd4508c72abfcfca","schema_version":"1.0","event_id":"sha256:3fb71b6453c27c68a939dee3dbf04547baf8a6aec25a9f33dd4508c72abfcfca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BTEVUEPXFQECOWLDJGM35N3IE/bundle.json","state_url":"https://pith.science/pith/3BTEVUEPXFQECOWLDJGM35N3IE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BTEVUEPXFQECOWLDJGM35N3IE/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":"2026-08-06T14:17:21Z","links":{"resolver":"https://pith.science/pith/3BTEVUEPXFQECOWLDJGM35N3IE","bundle":"https://pith.science/pith/3BTEVUEPXFQECOWLDJGM35N3IE/bundle.json","state":"https://pith.science/pith/3BTEVUEPXFQECOWLDJGM35N3IE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BTEVUEPXFQECOWLDJGM35N3IE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3BTEVUEPXFQECOWLDJGM35N3IE","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":"9aab0a4082d5cc21eb29f0cd8a64dbc7ca3122f5fd9be07753d85478e9a6be82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T11:31:24Z","title_canon_sha256":"5f3a7ebc103398400918fe4b1116f338aaf57b687ef276db42436ff7aa8508bb"},"schema_version":"1.0","source":{"id":"2506.07659","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07659","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07659v1","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07659","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"3BTEVUEPXFQE","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"3BTEVUEPXFQECOWL","created_at":"2026-07-05T11:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"3BTEVUEP","created_at":"2026-07-05T11:18:31Z"}],"graph_snapshots":[{"event_id":"sha256:3fb71b6453c27c68a939dee3dbf04547baf8a6aec25a9f33dd4508c72abfcfca","target":"graph","created_at":"2026-07-05T11:18:31Z","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/2506.07659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Speech Recognition has been a longstanding research area, with substantial efforts dedicated to integrating semi-supervised learning due to the scarcity of labeled datasets. However, most prior work has focused on improving learning algorithms using existing datasets, without providing a complete public framework for large-scale semi-supervised training across new datasets or languages. In this work, we introduce a fully open-source semi-supervised training framework encompassing the entire pipeline: from unlabeled data collection to pseudo-labeling and model training. Our approach e","authors_text":"Andrei Andrusenko, Ante Jukic, Nikolay Karpov, Nune Tadevosyan, Vitaly Lavrukhin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T11:31:24Z","title":"Unified Semi-Supervised Pipeline for Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07659","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":"sha256:650d12d7b256e4ece84eedccd3b447b38254d830c92a7d1bc78169cfeb35c71e","target":"record","created_at":"2026-07-05T11:18:31Z","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":"9aab0a4082d5cc21eb29f0cd8a64dbc7ca3122f5fd9be07753d85478e9a6be82","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T11:31:24Z","title_canon_sha256":"5f3a7ebc103398400918fe4b1116f338aaf57b687ef276db42436ff7aa8508bb"},"schema_version":"1.0","source":{"id":"2506.07659","kind":"arxiv","version":1}},"canonical_sha256":"d8664ad08fb960413acb1a4ccdf5bb41211a3bc0255a3cb7a1befd23148bc1b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8664ad08fb960413acb1a4ccdf5bb41211a3bc0255a3cb7a1befd23148bc1b0","first_computed_at":"2026-07-05T11:18:31.122666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:31.122666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AiTZt45sUnUZM+E74A8UZrhDg+X6Bp3n88mP/xElimgkgprGz/SUva1zcBBlkrBrHVu9ZktwKXzcl28hs474Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:31.123159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07659","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:650d12d7b256e4ece84eedccd3b447b38254d830c92a7d1bc78169cfeb35c71e","sha256:3fb71b6453c27c68a939dee3dbf04547baf8a6aec25a9f33dd4508c72abfcfca"],"state_sha256":"05590ca2914c9218b908cb504ce2f021813386419c3b5d8d145445e42104fd2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sa4jmbNAjBTDXTZLpcBG1HyGOmVTkKdAWdFxmFRIm2ZUBlgTSfYh6Sot5FEOtIcEzYjzaU3sw/BAu5mloplwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:17:21.536078Z","bundle_sha256":"1f732eb6f32415774e4f9737d96b84c1b2c6849c06278175aa8f75862d929c4b"}}