{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IVR67UUESOIMSK6F2J2S45HSAM","short_pith_number":"pith:IVR67UUE","canonical_record":{"source":{"id":"2110.10329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:59:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"92c18158d149107937080494917c92cf09be8fcb26ce5781223114327ae58e01","abstract_canon_sha256":"10ac4e68cbc764720573c308c0ae46d97f5fac73aabb691d63dd3b80733a90d4"},"schema_version":"1.0"},"canonical_sha256":"4563efd2849390c92bc5d2752e74f20311839e686f863c23324e61f7b55a6f58","source":{"kind":"arxiv","id":"2110.10329","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10329","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10329v1","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10329","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"IVR67UUESOIM","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"IVR67UUESOIMSK6F","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"IVR67UUE","created_at":"2026-07-05T03:24:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IVR67UUESOIMSK6F2J2S45HSAM","target":"record","payload":{"canonical_record":{"source":{"id":"2110.10329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:59:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"92c18158d149107937080494917c92cf09be8fcb26ce5781223114327ae58e01","abstract_canon_sha256":"10ac4e68cbc764720573c308c0ae46d97f5fac73aabb691d63dd3b80733a90d4"},"schema_version":"1.0"},"canonical_sha256":"4563efd2849390c92bc5d2752e74f20311839e686f863c23324e61f7b55a6f58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:15.998167Z","signature_b64":"Fvul4evX+QmZcr2upv4NMH91t+qxLTdySwckojDxLn15kTIu+62d1AIjuRg26Umy9di/4DyyWSkCRWDQYyFxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4563efd2849390c92bc5d2752e74f20311839e686f863c23324e61f7b55a6f58","last_reissued_at":"2026-07-05T03:24:15.997746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:15.997746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.10329","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":"2026-07-05T03:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G7on8lrQsPWIHDs1wcrZfTGTE18YAtKZpA6/WnyHypzfYfHRCJ9Wo0VJHp6nlbJyFt+HlPfpOj0iwcV1JeOOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T09:45:07.288345Z"},"content_sha256":"eb59673db888a6957bd95874fbf5686f8f814c9c419c05264c492fca4343c9f4","schema_version":"1.0","event_id":"sha256:eb59673db888a6957bd95874fbf5686f8f814c9c419c05264c492fca4343c9f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IVR67UUESOIMSK6F2J2S45HSAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Ankur Bapna, Anmol Gulati, Jason Riesa, Jonathan H. Clark, Melvin Johnson, Nan Wu, Ye Jia, Yu-An Chung, Yu Zhang","submitted_at":"2021-10-20T00:59:36Z","abstract_excerpt":"Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a variety of domains and languages. This paper takes the universality of unsupervised language pre-training one step further, by unifying speech and text pre-training within a single model. We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. To further align our model representations acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10329","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/2110.10329/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":"2026-07-05T03:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Q5DDmyjOrp5dyhH00J1HEJT2CZbpc2XsecXBh8+UM3bBDK49dgIfm82PIT41Rm0THJiSpgAWpb2EFocENNjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T09:45:07.288734Z"},"content_sha256":"8aefd6eabc230196a9e45465c2f6bbff6a9fe9d0b5a3c9ca8cf223acf2fc03b2","schema_version":"1.0","event_id":"sha256:8aefd6eabc230196a9e45465c2f6bbff6a9fe9d0b5a3c9ca8cf223acf2fc03b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVR67UUESOIMSK6F2J2S45HSAM/bundle.json","state_url":"https://pith.science/pith/IVR67UUESOIMSK6F2J2S45HSAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVR67UUESOIMSK6F2J2S45HSAM/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":"2026-07-11T09:45:07Z","links":{"resolver":"https://pith.science/pith/IVR67UUESOIMSK6F2J2S45HSAM","bundle":"https://pith.science/pith/IVR67UUESOIMSK6F2J2S45HSAM/bundle.json","state":"https://pith.science/pith/IVR67UUESOIMSK6F2J2S45HSAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVR67UUESOIMSK6F2J2S45HSAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IVR67UUESOIMSK6F2J2S45HSAM","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":"10ac4e68cbc764720573c308c0ae46d97f5fac73aabb691d63dd3b80733a90d4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:59:36Z","title_canon_sha256":"92c18158d149107937080494917c92cf09be8fcb26ce5781223114327ae58e01"},"schema_version":"1.0","source":{"id":"2110.10329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10329","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10329v1","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10329","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"IVR67UUESOIM","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"IVR67UUESOIMSK6F","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"IVR67UUE","created_at":"2026-07-05T03:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:8aefd6eabc230196a9e45465c2f6bbff6a9fe9d0b5a3c9ca8cf223acf2fc03b2","target":"graph","created_at":"2026-07-05T03:24:15Z","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/2110.10329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised pre-training is now the predominant approach for both text and speech understanding. Self-attention models pre-trained on large amounts of unannotated data have been hugely successful when fine-tuned on downstream tasks from a variety of domains and languages. This paper takes the universality of unsupervised language pre-training one step further, by unifying speech and text pre-training within a single model. We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. To further align our model representations acr","authors_text":"Alexis Conneau, Ankur Bapna, Anmol Gulati, Jason Riesa, Jonathan H. Clark, Melvin Johnson, Nan Wu, Ye Jia, Yu-An Chung, Yu Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:59:36Z","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10329","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:eb59673db888a6957bd95874fbf5686f8f814c9c419c05264c492fca4343c9f4","target":"record","created_at":"2026-07-05T03:24:15Z","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":"10ac4e68cbc764720573c308c0ae46d97f5fac73aabb691d63dd3b80733a90d4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-20T00:59:36Z","title_canon_sha256":"92c18158d149107937080494917c92cf09be8fcb26ce5781223114327ae58e01"},"schema_version":"1.0","source":{"id":"2110.10329","kind":"arxiv","version":1}},"canonical_sha256":"4563efd2849390c92bc5d2752e74f20311839e686f863c23324e61f7b55a6f58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4563efd2849390c92bc5d2752e74f20311839e686f863c23324e61f7b55a6f58","first_computed_at":"2026-07-05T03:24:15.997746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:15.997746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fvul4evX+QmZcr2upv4NMH91t+qxLTdySwckojDxLn15kTIu+62d1AIjuRg26Umy9di/4DyyWSkCRWDQYyFxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:15.998167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb59673db888a6957bd95874fbf5686f8f814c9c419c05264c492fca4343c9f4","sha256:8aefd6eabc230196a9e45465c2f6bbff6a9fe9d0b5a3c9ca8cf223acf2fc03b2"],"state_sha256":"4623dacc11fa4c659887a7e8526f50d77679b554e22d23b9f62eed3818f2763a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7ja13s+cfD1kNSH7C0E0Ts0LGAUULZptsI7gNff7bAUZMD/a8KGNe57GQlIcPvYPtZAGdl68Y9gwlXiCYWWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T09:45:07.291163Z","bundle_sha256":"5be66b07f4b64ed1201a4b39c0ce9da6cbf773ebd284de84709fcba04624ab05"}}