{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O4YLKYQBXW4XGKFLL37JIEE6NK","short_pith_number":"pith:O4YLKYQB","canonical_record":{"source":{"id":"2506.00975","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:01:40Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2d26737f16b184f0d5b2cdc90b3dd8ec1654efec0e28bb615313a7155cbfa667","abstract_canon_sha256":"6b20f80c20c4b1d5351a84e2d24a28dd204ca10f72356a56f6cc27a58f276865"},"schema_version":"1.0"},"canonical_sha256":"7730b56201bdb97328ab5efe94109e6aa331a0603c18990cb921b30c0ce9c684","source":{"kind":"arxiv","id":"2506.00975","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00975","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00975v4","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00975","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"O4YLKYQBXW4X","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"O4YLKYQBXW4XGKFL","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"O4YLKYQB","created_at":"2026-07-05T11:19:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O4YLKYQBXW4XGKFLL37JIEE6NK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00975","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:01:40Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2d26737f16b184f0d5b2cdc90b3dd8ec1654efec0e28bb615313a7155cbfa667","abstract_canon_sha256":"6b20f80c20c4b1d5351a84e2d24a28dd204ca10f72356a56f6cc27a58f276865"},"schema_version":"1.0"},"canonical_sha256":"7730b56201bdb97328ab5efe94109e6aa331a0603c18990cb921b30c0ce9c684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:27.779066Z","signature_b64":"+SzOkRkt4OoLJsBfoy3XlyqsrdqRqL8qGaH+MsTbgZTlo/8DWjv7QEPeDYCEQASN7kLppH1Ae/m9gxGcom37Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7730b56201bdb97328ab5efe94109e6aa331a0603c18990cb921b30c0ce9c684","last_reissued_at":"2026-07-05T11:19:27.778576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:27.778576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00975","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gh4uJmzLtQ44o6SSefI0k8XvRKuLcEOYwr1S8QbUF99ThMIEhSye4ayJKOkJs2g7mfuR9qRL3vyWxew6Eb+eDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:48:50.861553Z"},"content_sha256":"fe899ca9592daef116f8f4ebaba820fd4106612d6466283686f11f0608a45467","schema_version":"1.0","event_id":"sha256:fe899ca9592daef116f8f4ebaba820fd4106612d6466283686f11f0608a45467"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O4YLKYQBXW4XGKFLL37JIEE6NK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bingzhe Wu, Irwin King, Liang Chen, Peilin Zhao, Pengcheng Wu, Qichao Wang, Wenqian Cui, Yifei Zhang, Ziqiao Meng","submitted_at":"2025-06-01T12:01:40Z","abstract_excerpt":"Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several SLMs that demonstrate promising results in this area. However, current approaches have yet to fully exploit dual-channel speech data, which inherently captures the structure and dynamics of human conversation. In this work, we systematically explore the use of dual-channel speech data in the context of modern large language models, and introduce a novel gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00975","kind":"arxiv","version":4},"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/2506.00975/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":"2026-07-05T11:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/RBfH6VtSxqujF44T912B84tP2j7dvZp6o1XZnXQdB3HYKXDOk3nybVzjNYRxbU11ThsYWMj/478xJgRiUoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:48:50.862083Z"},"content_sha256":"730a51b72b3b7f4ee0485eb2294b476504b2a386aedfc9453036584c04b5f6ea","schema_version":"1.0","event_id":"sha256:730a51b72b3b7f4ee0485eb2294b476504b2a386aedfc9453036584c04b5f6ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4YLKYQBXW4XGKFLL37JIEE6NK/bundle.json","state_url":"https://pith.science/pith/O4YLKYQBXW4XGKFLL37JIEE6NK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4YLKYQBXW4XGKFLL37JIEE6NK/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":"2026-08-04T04:48:50Z","links":{"resolver":"https://pith.science/pith/O4YLKYQBXW4XGKFLL37JIEE6NK","bundle":"https://pith.science/pith/O4YLKYQBXW4XGKFLL37JIEE6NK/bundle.json","state":"https://pith.science/pith/O4YLKYQBXW4XGKFLL37JIEE6NK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4YLKYQBXW4XGKFLL37JIEE6NK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O4YLKYQBXW4XGKFLL37JIEE6NK","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":"6b20f80c20c4b1d5351a84e2d24a28dd204ca10f72356a56f6cc27a58f276865","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:01:40Z","title_canon_sha256":"2d26737f16b184f0d5b2cdc90b3dd8ec1654efec0e28bb615313a7155cbfa667"},"schema_version":"1.0","source":{"id":"2506.00975","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00975","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00975v4","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00975","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"O4YLKYQBXW4X","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"O4YLKYQBXW4XGKFL","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"O4YLKYQB","created_at":"2026-07-05T11:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:730a51b72b3b7f4ee0485eb2294b476504b2a386aedfc9453036584c04b5f6ea","target":"graph","created_at":"2026-07-05T11:19:27Z","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/2506.00975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several SLMs that demonstrate promising results in this area. However, current approaches have yet to fully exploit dual-channel speech data, which inherently captures the structure and dynamics of human conversation. In this work, we systematically explore the use of dual-channel speech data in the context of modern large language models, and introduce a novel gener","authors_text":"Bingzhe Wu, Irwin King, Liang Chen, Peilin Zhao, Pengcheng Wu, Qichao Wang, Wenqian Cui, Yifei Zhang, Ziqiao Meng","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:01:40Z","title":"NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00975","kind":"arxiv","version":4},"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:fe899ca9592daef116f8f4ebaba820fd4106612d6466283686f11f0608a45467","target":"record","created_at":"2026-07-05T11:19:27Z","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":"6b20f80c20c4b1d5351a84e2d24a28dd204ca10f72356a56f6cc27a58f276865","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:01:40Z","title_canon_sha256":"2d26737f16b184f0d5b2cdc90b3dd8ec1654efec0e28bb615313a7155cbfa667"},"schema_version":"1.0","source":{"id":"2506.00975","kind":"arxiv","version":4}},"canonical_sha256":"7730b56201bdb97328ab5efe94109e6aa331a0603c18990cb921b30c0ce9c684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7730b56201bdb97328ab5efe94109e6aa331a0603c18990cb921b30c0ce9c684","first_computed_at":"2026-07-05T11:19:27.778576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:27.778576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+SzOkRkt4OoLJsBfoy3XlyqsrdqRqL8qGaH+MsTbgZTlo/8DWjv7QEPeDYCEQASN7kLppH1Ae/m9gxGcom37Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:27.779066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00975","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe899ca9592daef116f8f4ebaba820fd4106612d6466283686f11f0608a45467","sha256:730a51b72b3b7f4ee0485eb2294b476504b2a386aedfc9453036584c04b5f6ea"],"state_sha256":"3d9409a7b41bd3746e52a13f9ff6cdb0a5dac1da0f4743f39fb84d745a1f98ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1DKFqfSTgUyzGIE8+J3uUqvXLuPS9VRFIGIAUcraca2nfOXdqGQTMFlmwHDSZWS1TAH3mGuC7S6Enf9Fknr5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:48:50.867062Z","bundle_sha256":"de8dfa25ed5cd6e535ecb2d1cdf75bc60a383360812987c2207ea72f5ec543de"}}