{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:G4LZFRWIDQYUBOUJTLNVQ3Q3XZ","short_pith_number":"pith:G4LZFRWI","canonical_record":{"source":{"id":"2203.16502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:39:45Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"a28a19ae83852d825c295997c070dd56e16a30e65d665f4c844bec93d8b0f7c0","abstract_canon_sha256":"2a862682ef10aa4f14499a887c4edfa33aaeb48fb2118afd5d23516de7d92b84"},"schema_version":"1.0"},"canonical_sha256":"371792c6c81c3140ba899adb586e1bbe73867b9a86369a774eb2bfb229bcaa63","source":{"kind":"arxiv","id":"2203.16502","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16502","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16502v2","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16502","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"G4LZFRWIDQYU","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"G4LZFRWIDQYUBOUJ","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"G4LZFRWI","created_at":"2026-07-05T05:18:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:G4LZFRWIDQYUBOUJTLNVQ3Q3XZ","target":"record","payload":{"canonical_record":{"source":{"id":"2203.16502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:39:45Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"a28a19ae83852d825c295997c070dd56e16a30e65d665f4c844bec93d8b0f7c0","abstract_canon_sha256":"2a862682ef10aa4f14499a887c4edfa33aaeb48fb2118afd5d23516de7d92b84"},"schema_version":"1.0"},"canonical_sha256":"371792c6c81c3140ba899adb586e1bbe73867b9a86369a774eb2bfb229bcaa63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:46.343016Z","signature_b64":"Hgftib42ZnduKKMz9GBCm1NzxBWVF3JKVecBIvtUGjRFWgddOSIByeBRF+3NtEVeQdW7Og/kd5FaXe5JdLWpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"371792c6c81c3140ba899adb586e1bbe73867b9a86369a774eb2bfb229bcaa63","last_reissued_at":"2026-07-05T05:18:46.342527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:46.342527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.16502","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":"2026-07-05T05:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTukX4hlsH5c0Lnw4bYa5wU/z6BFhcgMFZ0WFwc+ZaUoBl+nWBXIYDBJhs24oaSyZSqWj5Ae4zILCAGFwb4UBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:40:15.377089Z"},"content_sha256":"2b7f91cd53da2f37d8dcdbf0074785a3560d8583c31b037c52b9eaf100bd5ce2","schema_version":"1.0","event_id":"sha256:2b7f91cd53da2f37d8dcdbf0074785a3560d8583c31b037c52b9eaf100bd5ce2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:G4LZFRWIDQYUBOUJTLNVQ3Q3XZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Spoken Dialogue Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, Ali Elkahky, Benoit Sagot, Emmanuel Dupoux, Eugene Kharitonov, Jade Copet, Paden Tomasello, Robin Algayres, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","submitted_at":"2022-03-30T17:39:45Z","abstract_excerpt":"We introduce dGSLM, the first \"textless\" model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn-taking compared to a text-based cascaded model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16502","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/2203.16502/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":"2026-07-05T05:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BxEtPjAlCi4OK5/ex9qlfRPBUpkIV7iT34GN4Bz50+MhzlXLI5kJF7di/t7htu4rUoEa+eXyzU1+3kEDpN7bBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:40:15.377646Z"},"content_sha256":"0aa1e30696034e91398242efaa57daa0dcefe26e96fcfc7f1d9f96af609af994","schema_version":"1.0","event_id":"sha256:0aa1e30696034e91398242efaa57daa0dcefe26e96fcfc7f1d9f96af609af994"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ/bundle.json","state_url":"https://pith.science/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ/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":"2026-08-12T15:40:15Z","links":{"resolver":"https://pith.science/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ","bundle":"https://pith.science/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ/bundle.json","state":"https://pith.science/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4LZFRWIDQYUBOUJTLNVQ3Q3XZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G4LZFRWIDQYUBOUJTLNVQ3Q3XZ","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":"2a862682ef10aa4f14499a887c4edfa33aaeb48fb2118afd5d23516de7d92b84","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:39:45Z","title_canon_sha256":"a28a19ae83852d825c295997c070dd56e16a30e65d665f4c844bec93d8b0f7c0"},"schema_version":"1.0","source":{"id":"2203.16502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16502","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16502v2","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16502","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"G4LZFRWIDQYU","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"G4LZFRWIDQYUBOUJ","created_at":"2026-07-05T05:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"G4LZFRWI","created_at":"2026-07-05T05:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:0aa1e30696034e91398242efaa57daa0dcefe26e96fcfc7f1d9f96af609af994","target":"graph","created_at":"2026-07-05T05:18:46Z","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/2203.16502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce dGSLM, the first \"textless\" model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn-taking compared to a text-based cascaded model.","authors_text":"Abdelrahman Mohamed, Ali Elkahky, Benoit Sagot, Emmanuel Dupoux, Eugene Kharitonov, Jade Copet, Paden Tomasello, Robin Algayres, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:39:45Z","title":"Generative Spoken Dialogue Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16502","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":"sha256:2b7f91cd53da2f37d8dcdbf0074785a3560d8583c31b037c52b9eaf100bd5ce2","target":"record","created_at":"2026-07-05T05:18:46Z","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":"2a862682ef10aa4f14499a887c4edfa33aaeb48fb2118afd5d23516de7d92b84","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-30T17:39:45Z","title_canon_sha256":"a28a19ae83852d825c295997c070dd56e16a30e65d665f4c844bec93d8b0f7c0"},"schema_version":"1.0","source":{"id":"2203.16502","kind":"arxiv","version":2}},"canonical_sha256":"371792c6c81c3140ba899adb586e1bbe73867b9a86369a774eb2bfb229bcaa63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"371792c6c81c3140ba899adb586e1bbe73867b9a86369a774eb2bfb229bcaa63","first_computed_at":"2026-07-05T05:18:46.342527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:46.342527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hgftib42ZnduKKMz9GBCm1NzxBWVF3JKVecBIvtUGjRFWgddOSIByeBRF+3NtEVeQdW7Og/kd5FaXe5JdLWpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:46.343016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b7f91cd53da2f37d8dcdbf0074785a3560d8583c31b037c52b9eaf100bd5ce2","sha256:0aa1e30696034e91398242efaa57daa0dcefe26e96fcfc7f1d9f96af609af994"],"state_sha256":"dcf53f70b627b694f97381f0377e2fe462024f937921c304b710964181ffe090"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRQPSTny40syspoFxMwk0mL6Tn2vhfYY3qJE1a3DZqi02Ujm0JOzSSnEFT3FD76nqNshtdQrqA9phdwSVuaJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:40:15.383026Z","bundle_sha256":"248f7f3b7831f5f63a5bc7f9c05bf1ef0d9e8d341f1bb5385945fed86d12f331"}}