{"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"}