{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4EDL3COTOQQRVSONJ7VLQ3LVFG","short_pith_number":"pith:4EDL3COT","canonical_record":{"source":{"id":"2412.18603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T18:56:46Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9f6e02c24e813685a68df77507733b79f9fc56db915f3311d8946c12ec50d560","abstract_canon_sha256":"948884d477899976c169bab12d26de47896915a17ee6feda52a0f3c8c1664910"},"schema_version":"1.0"},"canonical_sha256":"e106bd89d374211ac9cd4feab86d7529b7448fb201fdaefb7339037669273781","source":{"kind":"arxiv","id":"2412.18603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18603","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18603v2","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18603","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"pith_short_12","alias_value":"4EDL3COTOQQR","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"pith_short_16","alias_value":"4EDL3COTOQQRVSON","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"pith_short_8","alias_value":"4EDL3COT","created_at":"2026-07-05T11:34:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4EDL3COTOQQRVSONJ7VLQ3LVFG","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T18:56:46Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9f6e02c24e813685a68df77507733b79f9fc56db915f3311d8946c12ec50d560","abstract_canon_sha256":"948884d477899976c169bab12d26de47896915a17ee6feda52a0f3c8c1664910"},"schema_version":"1.0"},"canonical_sha256":"e106bd89d374211ac9cd4feab86d7529b7448fb201fdaefb7339037669273781","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:46.201530Z","signature_b64":"JmQkS57BgG/zkgUoEvioN/6aBw+n+Wl51DSn30bo3PpU311Ms+U2Tz8qqGSxPtmaxFtl3D37fayEjcelLmjKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e106bd89d374211ac9cd4feab86d7529b7448fb201fdaefb7339037669273781","last_reissued_at":"2026-07-05T11:34:46.200997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:46.200997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18603","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":"2026-07-05T11:34:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eb3cLiiO4pDT3yYtsaxKlB4FYlmVvRNbeAQqIIYd/Ug3bb3aLgdm5daN2d4YLtA9zHHsdA1QoC3a+Z72CxeuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:16:20.393683Z"},"content_sha256":"b012baaf69f8e7fd5328097f85f45a798fbec66009d56e3679d78e7ddae13a4c","schema_version":"1.0","event_id":"sha256:b012baaf69f8e7fd5328097f85f45a798fbec66009d56e3679d78e7ddae13a4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4EDL3COTOQQRVSONJ7VLQ3LVFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long-Form Speech Generation with Spoken Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aren Jansen, Julian Salazar, Keisuke Kinoshita, RJ Skerry-Ryan, Se Jin Park, Yong Man Ro","submitted_at":"2024-12-24T18:56:46Z","abstract_excerpt":"We consider the generative modeling of speech over multiple minutes, a requirement for long-form multimedia generation and audio-native voice assistants. However, textless spoken language models struggle to generate plausible speech past tens of seconds, due to high temporal resolution of speech tokens causing loss of coherence, architectural issues with long-sequence training or extrapolation, and memory costs at inference time. From these considerations we derive SpeechSSM, the first speech language model family to learn from and sample long-form spoken audio (e.g., 16 minutes of read or ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18603","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/2412.18603/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":"2026-07-05T11:34:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIyMS8B+3sP+UUXkTWmOualfWa6W+bdv7av5NWA6ZWBgxYaAE/NXubIgaH6RoyBmXTZqBD4dhnOoD+EqRQOIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:16:20.394170Z"},"content_sha256":"d19a86d646b48ad5ae0f0ad413e914967986927cacd120ec352e13044c2fe3ec","schema_version":"1.0","event_id":"sha256:d19a86d646b48ad5ae0f0ad413e914967986927cacd120ec352e13044c2fe3ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG/bundle.json","state_url":"https://pith.science/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG/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":"2026-08-03T11:16:20Z","links":{"resolver":"https://pith.science/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG","bundle":"https://pith.science/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG/bundle.json","state":"https://pith.science/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EDL3COTOQQRVSONJ7VLQ3LVFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4EDL3COTOQQRVSONJ7VLQ3LVFG","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":"948884d477899976c169bab12d26de47896915a17ee6feda52a0f3c8c1664910","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T18:56:46Z","title_canon_sha256":"9f6e02c24e813685a68df77507733b79f9fc56db915f3311d8946c12ec50d560"},"schema_version":"1.0","source":{"id":"2412.18603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18603","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18603v2","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18603","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"pith_short_12","alias_value":"4EDL3COTOQQR","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"pith_short_16","alias_value":"4EDL3COTOQQRVSON","created_at":"2026-07-05T11:34:46Z"},{"alias_kind":"pith_short_8","alias_value":"4EDL3COT","created_at":"2026-07-05T11:34:46Z"}],"graph_snapshots":[{"event_id":"sha256:d19a86d646b48ad5ae0f0ad413e914967986927cacd120ec352e13044c2fe3ec","target":"graph","created_at":"2026-07-05T11:34:46Z","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/2412.18603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the generative modeling of speech over multiple minutes, a requirement for long-form multimedia generation and audio-native voice assistants. However, textless spoken language models struggle to generate plausible speech past tens of seconds, due to high temporal resolution of speech tokens causing loss of coherence, architectural issues with long-sequence training or extrapolation, and memory costs at inference time. From these considerations we derive SpeechSSM, the first speech language model family to learn from and sample long-form spoken audio (e.g., 16 minutes of read or ext","authors_text":"Aren Jansen, Julian Salazar, Keisuke Kinoshita, RJ Skerry-Ryan, Se Jin Park, Yong Man Ro","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T18:56:46Z","title":"Long-Form Speech Generation with Spoken Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18603","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:b012baaf69f8e7fd5328097f85f45a798fbec66009d56e3679d78e7ddae13a4c","target":"record","created_at":"2026-07-05T11:34:46Z","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":"948884d477899976c169bab12d26de47896915a17ee6feda52a0f3c8c1664910","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T18:56:46Z","title_canon_sha256":"9f6e02c24e813685a68df77507733b79f9fc56db915f3311d8946c12ec50d560"},"schema_version":"1.0","source":{"id":"2412.18603","kind":"arxiv","version":2}},"canonical_sha256":"e106bd89d374211ac9cd4feab86d7529b7448fb201fdaefb7339037669273781","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e106bd89d374211ac9cd4feab86d7529b7448fb201fdaefb7339037669273781","first_computed_at":"2026-07-05T11:34:46.200997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:46.200997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JmQkS57BgG/zkgUoEvioN/6aBw+n+Wl51DSn30bo3PpU311Ms+U2Tz8qqGSxPtmaxFtl3D37fayEjcelLmjKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:46.201530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b012baaf69f8e7fd5328097f85f45a798fbec66009d56e3679d78e7ddae13a4c","sha256:d19a86d646b48ad5ae0f0ad413e914967986927cacd120ec352e13044c2fe3ec"],"state_sha256":"100b021f53b086795c6314ef15b294158a1609c7d09945ae2eb424392487d5c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"copCGS7q5tBd379x/21OrYzX7jLPNSq7sotS3E/TXnmhRp3MkaQDteGCCih/E6boCNPDkO5Nk/+I7O6dSA61Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T11:16:20.397790Z","bundle_sha256":"2a9f09e091992107e8d5669785c4a6dc74c0ea218668d5b7d6259ef3e9407a65"}}