{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4WFUSRLDMPV4UDI3AZYOR7V4MT","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":"51d0507ab8724516887e1db70ac7d604a2c2e88b54d38084943c2d9a6719f0d1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T08:13:59Z","title_canon_sha256":"05460de800e92f4631d15069dee08fe963de0b60415a5c6190b2b9e00c972ad4"},"schema_version":"1.0","source":{"id":"2505.17060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17060","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17060v1","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17060","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"4WFUSRLDMPV4","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"4WFUSRLDMPV4UDI3","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"4WFUSRLD","created_at":"2026-07-05T11:07:46Z"}],"graph_snapshots":[{"event_id":"sha256:c87c9ba5a2674e616988274fe0ff92c901b00b9745a74afce29f4fc8ad9ed50a","target":"graph","created_at":"2026-07-05T11:07:46Z","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/2505.17060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order to enable fluid and natural human-machine speech interaction, existing full-duplex conversational systems often adopt modular architectures with auxiliary components such as voice activity detectors, interrupters, conversation state predictors, or multiple LLMs. These systems, however, suffer from error accumulation across modules and struggle with key challenges such as context-dependent barge-in and echo cancellation. Recent approaches, most notably Moshi, simplify the pipeline by injecting audio codecs into the token space of a single LLM. However, such methods still incur signific","authors_text":"Chao Zhang, Guangzhi Sun, Jun Zhang, Lu Lu, Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Xiaoyu Yang, Yuxuan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T08:13:59Z","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17060","kind":"arxiv","version":1},"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:b14d30de8163db25e1a97020d2ed3ee4a797494a361acf9cf7cc0749e672fa3b","target":"record","created_at":"2026-07-05T11:07:46Z","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":"51d0507ab8724516887e1db70ac7d604a2c2e88b54d38084943c2d9a6719f0d1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T08:13:59Z","title_canon_sha256":"05460de800e92f4631d15069dee08fe963de0b60415a5c6190b2b9e00c972ad4"},"schema_version":"1.0","source":{"id":"2505.17060","kind":"arxiv","version":1}},"canonical_sha256":"e58b49456363ebca0d1b0670e8febc64fe6186ee2ed1aa899e00d9f2bb7e4aaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e58b49456363ebca0d1b0670e8febc64fe6186ee2ed1aa899e00d9f2bb7e4aaf","first_computed_at":"2026-07-05T11:07:46.401077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:46.401077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tTZEGggPZb2mOZPlkvoDc5YWX/yBV88c3aq+miIWXja0/i9CEz1G3q61FGsM0yQ4e0v4LZKYGErIDUO8pgfuAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:46.401604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b14d30de8163db25e1a97020d2ed3ee4a797494a361acf9cf7cc0749e672fa3b","sha256:c87c9ba5a2674e616988274fe0ff92c901b00b9745a74afce29f4fc8ad9ed50a"],"state_sha256":"f41479595152b70180761c0b4a71ed5ad7d08478a864f37b4942c4ea0a68b0eb"}