{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AOFTEVK7YDZQ5E57IUQPDY3C2N","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":"a8cc705bc24b78a201fa86d87078182746b01e9ff38e7f8c086dc7c7f7796170","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:48:30Z","title_canon_sha256":"a8711c4d8a2b9c9e7ff5e257f96b0c3893cba77cfcc836ae43d0077c734f758f"},"schema_version":"1.0","source":{"id":"2505.15670","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15670","created_at":"2026-07-05T11:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15670v4","created_at":"2026-07-05T11:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15670","created_at":"2026-07-05T11:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"AOFTEVK7YDZQ","created_at":"2026-07-05T11:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"AOFTEVK7YDZQ5E57","created_at":"2026-07-05T11:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"AOFTEVK7","created_at":"2026-07-05T11:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:371662bf8a6aec8f686b426a8123599363ed40a94095cb319e34f4c2ef2dfaed","target":"graph","created_at":"2026-07-05T11:43:12Z","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/2505.15670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken dialogue is an intuitive form of human-computer interaction, yet current speech language models often remain constrained to turn-based exchanges, lacking real-time adaptability such as user barge-in. We propose a novel duplex speech to speech (S2S) architecture featuring continuous user inputs and codec agent outputs with channel fusion that directly models simultaneous user and agent streams. Using a pretrained streaming encoder for user input enables the first duplex S2S model without requiring speech pretrain. Separate architectures for agent and user modeling facilitate codec fine-t","authors_text":"Boris Ginsburg, Chen Chen, Edresson Casanova, Ehsan Hosseini-Asl, Jagadeesh Balam, Jason Li, Ke Hu, Piotr \\.Zelasko, Subhankar Ghosh, Zhehuai Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:48:30Z","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15670","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":"sha256:8c01373b171bf22a02d7bd942c7ed0b3854eab7413d5d51b21141f1c1a59e08b","target":"record","created_at":"2026-07-05T11:43:12Z","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":"a8cc705bc24b78a201fa86d87078182746b01e9ff38e7f8c086dc7c7f7796170","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:48:30Z","title_canon_sha256":"a8711c4d8a2b9c9e7ff5e257f96b0c3893cba77cfcc836ae43d0077c734f758f"},"schema_version":"1.0","source":{"id":"2505.15670","kind":"arxiv","version":4}},"canonical_sha256":"038b32555fc0f30e93bf4520f1e362d37565fc8a13a0abb7b6982a656efadc35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"038b32555fc0f30e93bf4520f1e362d37565fc8a13a0abb7b6982a656efadc35","first_computed_at":"2026-07-05T11:43:12.101782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:12.101782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GLh+R+FhDN92tKeBhRaRQjpXipsRDdD2l1DzrwZVSB/6UftfeE3vssoWd1XsdnQ/s4Ddq/wWFPc/MwJTPxA0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:12.102277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15670","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c01373b171bf22a02d7bd942c7ed0b3854eab7413d5d51b21141f1c1a59e08b","sha256:371662bf8a6aec8f686b426a8123599363ed40a94095cb319e34f4c2ef2dfaed"],"state_sha256":"6363a2daade5209be27ff6ba5087657903bb992880be50d39463eebb92d50abd"}