{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TDTP2VQESTI54RHTJLTX4CKYNG","short_pith_number":"pith:TDTP2VQE","canonical_record":{"source":{"id":"2102.01192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-01T21:41:40Z","cross_cats_sorted":[],"title_canon_sha256":"c40b879189175e510355546864ead8c976dacdd548fdad96789c2f32998c69a8","abstract_canon_sha256":"ff72b678067d954a8a12b6c5297430f07d79e578ad7546381ba90f8437ab29f8"},"schema_version":"1.0"},"canonical_sha256":"98e6fd560494d1de44f34ae77e095869bdae332db89f92f7c6486ed4b28e9050","source":{"kind":"arxiv","id":"2102.01192","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01192","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01192v2","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01192","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"TDTP2VQESTI5","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"TDTP2VQESTI54RHT","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"TDTP2VQE","created_at":"2026-07-05T03:13:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TDTP2VQESTI54RHTJLTX4CKYNG","target":"record","payload":{"canonical_record":{"source":{"id":"2102.01192","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-01T21:41:40Z","cross_cats_sorted":[],"title_canon_sha256":"c40b879189175e510355546864ead8c976dacdd548fdad96789c2f32998c69a8","abstract_canon_sha256":"ff72b678067d954a8a12b6c5297430f07d79e578ad7546381ba90f8437ab29f8"},"schema_version":"1.0"},"canonical_sha256":"98e6fd560494d1de44f34ae77e095869bdae332db89f92f7c6486ed4b28e9050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:02.017906Z","signature_b64":"dtKQBAwCJ6Om9sb6X2hM3RPN9zynPVqaVqG9NsT5imuGUuL9LNZhlXPipJf5IBXMaPw1wMwV+DL6uyQb8i1jCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98e6fd560494d1de44f34ae77e095869bdae332db89f92f7c6486ed4b28e9050","last_reissued_at":"2026-07-05T03:13:02.017449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:02.017449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.01192","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":"2026-07-05T03:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yAAp/EDebcJqPOL49KRFNdORPmfM6zH2r6FYyltWCF4q4LlFm919sFA8gZfjEIpXEqmozDNgJhxAA/YsduE6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:55:24.299652Z"},"content_sha256":"977899a371460bef5162b040169434ce99d03a8b667f89f91ae22bc67809fac5","schema_version":"1.0","event_id":"sha256:977899a371460bef5162b040169434ce99d03a8b667f89f91ae22bc67809fac5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TDTP2VQESTI54RHTJLTX4CKYNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Spoken Language Modeling from Raw Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Polyak, Adelrahman Mohamed, Alexei Baevski, Benjamin Bolte, Emmanuel Dupoux, Evgeny Kharitonov, Jade Copet, Kushal Lakhotia, Tu-Anh Nguyen, Wei-Ning Hsu, Yossi Adi","submitted_at":"2021-02-01T21:41:40Z","abstract_excerpt":"We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations at acoustic and linguistic levels for both encoding and generation. We set up baseline systems consisting of a discrete speech encoder (returning pseudo-text units), a generative language model (trained on pseudo-text), and a speech decoder (generating a waveform from pseudo-text) all trained without supervision and validate the proposed metrics with human "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01192","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/2102.01192/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":"2026-07-05T03:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YYhFwK6ZdBmdr9dcSBxMoT0UVRr9QBaD13JdDaOGHBuON7M22+kwKawyFUbbiNUO8sFvrg2bwQBCAIBh4FlEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:55:24.300200Z"},"content_sha256":"acc19b4fc8f101f7c88b83f75244b2e5e3117a5d17cee70fe9a229485d5067c3","schema_version":"1.0","event_id":"sha256:acc19b4fc8f101f7c88b83f75244b2e5e3117a5d17cee70fe9a229485d5067c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDTP2VQESTI54RHTJLTX4CKYNG/bundle.json","state_url":"https://pith.science/pith/TDTP2VQESTI54RHTJLTX4CKYNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDTP2VQESTI54RHTJLTX4CKYNG/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":"2026-08-08T14:55:24Z","links":{"resolver":"https://pith.science/pith/TDTP2VQESTI54RHTJLTX4CKYNG","bundle":"https://pith.science/pith/TDTP2VQESTI54RHTJLTX4CKYNG/bundle.json","state":"https://pith.science/pith/TDTP2VQESTI54RHTJLTX4CKYNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDTP2VQESTI54RHTJLTX4CKYNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TDTP2VQESTI54RHTJLTX4CKYNG","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":"ff72b678067d954a8a12b6c5297430f07d79e578ad7546381ba90f8437ab29f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-01T21:41:40Z","title_canon_sha256":"c40b879189175e510355546864ead8c976dacdd548fdad96789c2f32998c69a8"},"schema_version":"1.0","source":{"id":"2102.01192","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01192","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01192v2","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01192","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"TDTP2VQESTI5","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"TDTP2VQESTI54RHT","created_at":"2026-07-05T03:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"TDTP2VQE","created_at":"2026-07-05T03:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:acc19b4fc8f101f7c88b83f75244b2e5e3117a5d17cee70fe9a229485d5067c3","target":"graph","created_at":"2026-07-05T03:13:02Z","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/2102.01192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations at acoustic and linguistic levels for both encoding and generation. We set up baseline systems consisting of a discrete speech encoder (returning pseudo-text units), a generative language model (trained on pseudo-text), and a speech decoder (generating a waveform from pseudo-text) all trained without supervision and validate the proposed metrics with human ","authors_text":"Adam Polyak, Adelrahman Mohamed, Alexei Baevski, Benjamin Bolte, Emmanuel Dupoux, Evgeny Kharitonov, Jade Copet, Kushal Lakhotia, Tu-Anh Nguyen, Wei-Ning Hsu, Yossi Adi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-01T21:41:40Z","title":"Generative Spoken Language Modeling from Raw Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01192","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":"sha256:977899a371460bef5162b040169434ce99d03a8b667f89f91ae22bc67809fac5","target":"record","created_at":"2026-07-05T03:13:02Z","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":"ff72b678067d954a8a12b6c5297430f07d79e578ad7546381ba90f8437ab29f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-01T21:41:40Z","title_canon_sha256":"c40b879189175e510355546864ead8c976dacdd548fdad96789c2f32998c69a8"},"schema_version":"1.0","source":{"id":"2102.01192","kind":"arxiv","version":2}},"canonical_sha256":"98e6fd560494d1de44f34ae77e095869bdae332db89f92f7c6486ed4b28e9050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98e6fd560494d1de44f34ae77e095869bdae332db89f92f7c6486ed4b28e9050","first_computed_at":"2026-07-05T03:13:02.017449Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:02.017449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dtKQBAwCJ6Om9sb6X2hM3RPN9zynPVqaVqG9NsT5imuGUuL9LNZhlXPipJf5IBXMaPw1wMwV+DL6uyQb8i1jCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:02.017906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01192","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:977899a371460bef5162b040169434ce99d03a8b667f89f91ae22bc67809fac5","sha256:acc19b4fc8f101f7c88b83f75244b2e5e3117a5d17cee70fe9a229485d5067c3"],"state_sha256":"2e27e032dc89f5a2359a543eb1fffab935f415a708be571ec33b18cbaf734cdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8WMmqgysOGxb2MxNLJ89DEHVHAdk+cIghQifhUxMj3eZPs+ygsiYjRJSZ2vR2XuCDbBUY08otjKTcovNliXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:55:24.304139Z","bundle_sha256":"b347e2972c3e0f5127eb7de68d81e1f133ecb237e52f2de724274ad68045bf3d"}}