{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IXS4NSLLGB7SMYN5KOKPR5DACB","short_pith_number":"pith:IXS4NSLL","canonical_record":{"source":{"id":"2501.05966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-10T13:49:09Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"4ac3553f3d757c6e060ccd24370fe2660ffeae64073af528f4fdebbdd948a037","abstract_canon_sha256":"bece7d6433ba4808b346096cfff2f481b4e9021d9b340ce62a9c81002d4461a3"},"schema_version":"1.0"},"canonical_sha256":"45e5c6c96b307f2661bd5394f8f460106cc1856caf299afd390bb8b29243651a","source":{"kind":"arxiv","id":"2501.05966","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05966","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05966v2","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05966","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"IXS4NSLLGB7S","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"IXS4NSLLGB7SMYN5","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"IXS4NSLL","created_at":"2026-07-05T11:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IXS4NSLLGB7SMYN5KOKPR5DACB","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05966","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-10T13:49:09Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"4ac3553f3d757c6e060ccd24370fe2660ffeae64073af528f4fdebbdd948a037","abstract_canon_sha256":"bece7d6433ba4808b346096cfff2f481b4e9021d9b340ce62a9c81002d4461a3"},"schema_version":"1.0"},"canonical_sha256":"45e5c6c96b307f2661bd5394f8f460106cc1856caf299afd390bb8b29243651a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:18.542184Z","signature_b64":"XfdH0g53AWE5LraP1Hk/+j6o1gwMhhAa2Suh/VBB1eYwimNDGhj9TSQanIkZThcWXTUPWkXal3TN8abH6T82Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e5c6c96b307f2661bd5394f8f460106cc1856caf299afd390bb8b29243651a","last_reissued_at":"2026-07-05T11:13:18.541710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:18.541710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05966","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":"2026-07-05T11:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGHt70BNHF9Mbgc68yWrSKMGlQxRJ0/Eae581QBcA8WMS4qpws7H2MeyWMpyb6EHWxx2l9duMY07ze9BFQNOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:03:51.017020Z"},"content_sha256":"c53d5ad5b5b16c46a8133d91a00c93c7fa39f65a4816024cd2e261a8ad389a4a","schema_version":"1.0","event_id":"sha256:c53d5ad5b5b16c46a8133d91a00c93c7fa39f65a4816024cd2e261a8ad389a4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IXS4NSLLGB7SMYN5KOKPR5DACB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Early Prediction of Self-Supervised Speech Model Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lucas Maison, Marco Dinarelli, Ryan Whetten, Titouan Parcollet, Yannick Est\\`eve","submitted_at":"2025-01-10T13:49:09Z","abstract_excerpt":"In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream performance. Consequently, it is often difficult to gauge the final downstream performance in a cost efficient manner during pre-training. In this work, we propose unsupervised efficient methods that give insights into the quality of the pre-training of SSL speech models, namely, measuring the cluster quality and rank of the embeddings of the SSL model. Results sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05966","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/2501.05966/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":"2026-07-05T11:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RICqKYAgf1X/ZwWmSOawpt19u3gzMldtI2nkfq3JYj107tSl0FMNmZAGbukte9xeLw5kIirdiW0W4Ctv8IogDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:03:51.017899Z"},"content_sha256":"1559679da758aee6da3073b4596b45cc0be16f8023253e9d3a144cd49eda1d58","schema_version":"1.0","event_id":"sha256:1559679da758aee6da3073b4596b45cc0be16f8023253e9d3a144cd49eda1d58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXS4NSLLGB7SMYN5KOKPR5DACB/bundle.json","state_url":"https://pith.science/pith/IXS4NSLLGB7SMYN5KOKPR5DACB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXS4NSLLGB7SMYN5KOKPR5DACB/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":"2026-08-16T09:03:51Z","links":{"resolver":"https://pith.science/pith/IXS4NSLLGB7SMYN5KOKPR5DACB","bundle":"https://pith.science/pith/IXS4NSLLGB7SMYN5KOKPR5DACB/bundle.json","state":"https://pith.science/pith/IXS4NSLLGB7SMYN5KOKPR5DACB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXS4NSLLGB7SMYN5KOKPR5DACB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IXS4NSLLGB7SMYN5KOKPR5DACB","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":"bece7d6433ba4808b346096cfff2f481b4e9021d9b340ce62a9c81002d4461a3","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-10T13:49:09Z","title_canon_sha256":"4ac3553f3d757c6e060ccd24370fe2660ffeae64073af528f4fdebbdd948a037"},"schema_version":"1.0","source":{"id":"2501.05966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05966","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05966v2","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05966","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"IXS4NSLLGB7S","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"IXS4NSLLGB7SMYN5","created_at":"2026-07-05T11:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"IXS4NSLL","created_at":"2026-07-05T11:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:1559679da758aee6da3073b4596b45cc0be16f8023253e9d3a144cd49eda1d58","target":"graph","created_at":"2026-07-05T11:13:18Z","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/2501.05966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream performance. Consequently, it is often difficult to gauge the final downstream performance in a cost efficient manner during pre-training. In this work, we propose unsupervised efficient methods that give insights into the quality of the pre-training of SSL speech models, namely, measuring the cluster quality and rank of the embeddings of the SSL model. Results sh","authors_text":"Lucas Maison, Marco Dinarelli, Ryan Whetten, Titouan Parcollet, Yannick Est\\`eve","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-10T13:49:09Z","title":"Towards Early Prediction of Self-Supervised Speech Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05966","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:c53d5ad5b5b16c46a8133d91a00c93c7fa39f65a4816024cd2e261a8ad389a4a","target":"record","created_at":"2026-07-05T11:13:18Z","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":"bece7d6433ba4808b346096cfff2f481b4e9021d9b340ce62a9c81002d4461a3","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-10T13:49:09Z","title_canon_sha256":"4ac3553f3d757c6e060ccd24370fe2660ffeae64073af528f4fdebbdd948a037"},"schema_version":"1.0","source":{"id":"2501.05966","kind":"arxiv","version":2}},"canonical_sha256":"45e5c6c96b307f2661bd5394f8f460106cc1856caf299afd390bb8b29243651a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45e5c6c96b307f2661bd5394f8f460106cc1856caf299afd390bb8b29243651a","first_computed_at":"2026-07-05T11:13:18.541710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:18.541710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XfdH0g53AWE5LraP1Hk/+j6o1gwMhhAa2Suh/VBB1eYwimNDGhj9TSQanIkZThcWXTUPWkXal3TN8abH6T82Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:18.542184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c53d5ad5b5b16c46a8133d91a00c93c7fa39f65a4816024cd2e261a8ad389a4a","sha256:1559679da758aee6da3073b4596b45cc0be16f8023253e9d3a144cd49eda1d58"],"state_sha256":"5a3253e95f56aef7aca94ed77c287731cd7c10393d9de4d39eb1e8d738a89048"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQLjxMsQXR3Apt5eclK2qYtruQ90XD7hTiKbPYJUjkaYPI3v3OH/He0yIjFja5HpP85XBpyxvgNlnB1adV+XDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T09:03:51.029570Z","bundle_sha256":"c797c84df9e53a6725e4a639fd86e926425e5f6e717146ad62bd9c5738b0bfec"}}