{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T42VE62WITC6M6SGATY5RXVYVR","short_pith_number":"pith:T42VE62W","canonical_record":{"source":{"id":"2309.05472","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T14:13:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"9d8a9f8c05d1414267f0897ae0228a3191137856ea68830d104043e7081e7a01","abstract_canon_sha256":"30887a5701adba17e13421be6b549b341ab55b75049dda88ac8051a2cf32e84f"},"schema_version":"1.0"},"canonical_sha256":"9f35527b5644c5e67a4604f1d8deb8ac52315ad297362b00f218b341fd3d308b","source":{"kind":"arxiv","id":"2309.05472","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05472","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05472v2","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05472","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"T42VE62WITC6","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"T42VE62WITC6M6SG","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"T42VE62W","created_at":"2026-07-05T07:56:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T42VE62WITC6M6SGATY5RXVYVR","target":"record","payload":{"canonical_record":{"source":{"id":"2309.05472","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T14:13:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"9d8a9f8c05d1414267f0897ae0228a3191137856ea68830d104043e7081e7a01","abstract_canon_sha256":"30887a5701adba17e13421be6b549b341ab55b75049dda88ac8051a2cf32e84f"},"schema_version":"1.0"},"canonical_sha256":"9f35527b5644c5e67a4604f1d8deb8ac52315ad297362b00f218b341fd3d308b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:52.120433Z","signature_b64":"Ws+nlmC9R/9N07/rK48yyAWTKdpn1xz/rVCzkdLmDE8l8DT6Vq+dS5ixwrFqFWsbQyWPBK42mx41NLgwno8wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f35527b5644c5e67a4604f1d8deb8ac52315ad297362b00f218b341fd3d308b","last_reissued_at":"2026-07-05T07:56:52.119949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:52.119949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.05472","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":"2026-07-05T07:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uf9tNZ0xtxz5GRck3Rd6QqDBShHmfVVlDejpKAd57b5fHNcXmpsM/oDjyhGVe3NPE3nqLj+Z1LaXv8QG86TDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:39.129514Z"},"content_sha256":"002bda1f504057c7cebe400047713ad596b7d743ffb868774c8830a48fd7b6ac","schema_version":"1.0","event_id":"sha256:002bda1f504057c7cebe400047713ad596b7d743ffb868774c8830a48fd7b6ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T42VE62WITC6M6SGATY5RXVYVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adrien Pupier, Alexandre Allauzen, Benjamin Lecouteux, Didier Schwab, Fabien Ringeval, Francois Portet, Hang Le, Ha Nguyen, Jerome Goulian, Laurent Besacier, Marcely Zanon Boito, Marco Dinarelli, Maximin Coavoux, Mickael Rouvier, Natalia Tomashenko, Salima Mdhaffar, Shucong Zhang, Sina Alisamir, Solange Rossato, Solene Evain, Titouan Parcollet, Yannick Esteve","submitted_at":"2023-09-11T14:13:09Z","abstract_excerpt":"Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most of the current domain-related tasks are now being approached with pre-trained models. This work introduces LeBenchmark 2.0 an open-source framework for assessing and building SSL-equipped French speech technologies. It includes documented, large-scale and heterogeneous corpora with up to 14,000 hours of heterogeneous speech, ten pre-trained SSL wav2vec 2.0 models containing fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05472","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/2309.05472/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":"2026-07-05T07:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ERFElRInam8aKbme1EbqHfrgcXvWvXg6FqEYay60L/P7OwtXlZmjfe4wpvh+nj1Af79Hag3Klx4RziVN1msBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:23:39.130270Z"},"content_sha256":"e00d99847ebe983461bb8435a24c71d3e708959f2341f8347bed8bf1ce344667","schema_version":"1.0","event_id":"sha256:e00d99847ebe983461bb8435a24c71d3e708959f2341f8347bed8bf1ce344667"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T42VE62WITC6M6SGATY5RXVYVR/bundle.json","state_url":"https://pith.science/pith/T42VE62WITC6M6SGATY5RXVYVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T42VE62WITC6M6SGATY5RXVYVR/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":"2026-08-10T06:23:39Z","links":{"resolver":"https://pith.science/pith/T42VE62WITC6M6SGATY5RXVYVR","bundle":"https://pith.science/pith/T42VE62WITC6M6SGATY5RXVYVR/bundle.json","state":"https://pith.science/pith/T42VE62WITC6M6SGATY5RXVYVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T42VE62WITC6M6SGATY5RXVYVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T42VE62WITC6M6SGATY5RXVYVR","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":"30887a5701adba17e13421be6b549b341ab55b75049dda88ac8051a2cf32e84f","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T14:13:09Z","title_canon_sha256":"9d8a9f8c05d1414267f0897ae0228a3191137856ea68830d104043e7081e7a01"},"schema_version":"1.0","source":{"id":"2309.05472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05472","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05472v2","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05472","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"T42VE62WITC6","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"T42VE62WITC6M6SG","created_at":"2026-07-05T07:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"T42VE62W","created_at":"2026-07-05T07:56:52Z"}],"graph_snapshots":[{"event_id":"sha256:e00d99847ebe983461bb8435a24c71d3e708959f2341f8347bed8bf1ce344667","target":"graph","created_at":"2026-07-05T07:56:52Z","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/2309.05472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most of the current domain-related tasks are now being approached with pre-trained models. This work introduces LeBenchmark 2.0 an open-source framework for assessing and building SSL-equipped French speech technologies. It includes documented, large-scale and heterogeneous corpora with up to 14,000 hours of heterogeneous speech, ten pre-trained SSL wav2vec 2.0 models containing fr","authors_text":"Adrien Pupier, Alexandre Allauzen, Benjamin Lecouteux, Didier Schwab, Fabien Ringeval, Francois Portet, Hang Le, Ha Nguyen, Jerome Goulian, Laurent Besacier, Marcely Zanon Boito, Marco Dinarelli, Maximin Coavoux, Mickael Rouvier, Natalia Tomashenko, Salima Mdhaffar, Shucong Zhang, Sina Alisamir, Solange Rossato, Solene Evain, Titouan Parcollet, Yannick Esteve","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T14:13:09Z","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05472","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":"sha256:002bda1f504057c7cebe400047713ad596b7d743ffb868774c8830a48fd7b6ac","target":"record","created_at":"2026-07-05T07:56:52Z","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":"30887a5701adba17e13421be6b549b341ab55b75049dda88ac8051a2cf32e84f","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T14:13:09Z","title_canon_sha256":"9d8a9f8c05d1414267f0897ae0228a3191137856ea68830d104043e7081e7a01"},"schema_version":"1.0","source":{"id":"2309.05472","kind":"arxiv","version":2}},"canonical_sha256":"9f35527b5644c5e67a4604f1d8deb8ac52315ad297362b00f218b341fd3d308b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f35527b5644c5e67a4604f1d8deb8ac52315ad297362b00f218b341fd3d308b","first_computed_at":"2026-07-05T07:56:52.119949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:52.119949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ws+nlmC9R/9N07/rK48yyAWTKdpn1xz/rVCzkdLmDE8l8DT6Vq+dS5ixwrFqFWsbQyWPBK42mx41NLgwno8wCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:52.120433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:002bda1f504057c7cebe400047713ad596b7d743ffb868774c8830a48fd7b6ac","sha256:e00d99847ebe983461bb8435a24c71d3e708959f2341f8347bed8bf1ce344667"],"state_sha256":"642f2dd3d01fa174dd9dba6b3b601d54c7467439b49f6d4d7e4eecf5fa864bb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/ChaVj5vKRs4JvSigx5SgWfKIlFRj2Hlj0lFKUwqn61SzooyP0FY4/Agjyi7wca6RMZDWf3cp/3KMAJxxIGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:23:39.136073Z","bundle_sha256":"942974ad440b3e6dd93129ae9d79cce0e39557afc6fde924f032d274e5c09fbc"}}