{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A4B7K4S5TKWZEWYFPH5JAHZPJE","short_pith_number":"pith:A4B7K4S5","canonical_record":{"source":{"id":"2607.27756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-30T06:53:15Z","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"7ae98cf1e2d1ea4f1a33b67e575770c12514391bd2a24297105dea00ee610fae","abstract_canon_sha256":"22909dffbca32d53043ea05199d81635c30be2e70dcc3d7818c72a0d600b0fe5"},"schema_version":"1.0"},"canonical_sha256":"0703f5725d9aad925b0579fa901f2f4931b138f56751dc5b10ad8a6464440cab","source":{"kind":"arxiv","id":"2607.27756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27756","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27756v1","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27756","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"A4B7K4S5TKWZ","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"A4B7K4S5TKWZEWYF","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"A4B7K4S5","created_at":"2026-07-31T01:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A4B7K4S5TKWZEWYFPH5JAHZPJE","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-30T06:53:15Z","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"7ae98cf1e2d1ea4f1a33b67e575770c12514391bd2a24297105dea00ee610fae","abstract_canon_sha256":"22909dffbca32d53043ea05199d81635c30be2e70dcc3d7818c72a0d600b0fe5"},"schema_version":"1.0"},"canonical_sha256":"0703f5725d9aad925b0579fa901f2f4931b138f56751dc5b10ad8a6464440cab","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0703f5725d9aad925b0579fa901f2f4931b138f56751dc5b10ad8a6464440cab","last_reissued_at":"2026-07-31T01:30:29.441189Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:30:29.441189Z"},"source_kind":"arxiv","source_id":"2607.27756","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EapJp09CV/at3jBC+QZ4xK0K1RupXEVYQtb6T0YKkyTpBofRWttVx6NuYFWV23J5zPN4TdDbQ3DFS62h3lK4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:49:35.076260Z"},"content_sha256":"1f81be9d35a5a6d4b8727751595638789aab37c44476c2f3234fde633b5c13ef","schema_version":"1.0","event_id":"sha256:1f81be9d35a5a6d4b8727751595638789aab37c44476c2f3234fde633b5c13ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A4B7K4S5TKWZEWYFPH5JAHZPJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junkai Wu, Nima Mesgarani, Riki Shimizu, Sukru Samet Dindar, Xilin Jiang, Zhongweiyang Xu","submitted_at":"2026-07-30T06:53:15Z","abstract_excerpt":"Spoken dialog systems are typically designed for clean, dyadic interactions in which a single user and an assistant take turns speaking. Real-world social conversations, however, are often more ambiguous: multiple speakers may participate in the same conversation amid irrelevant speech and background noise. Each utterance may be directed to the assistant, addressed to another speaker, or completely irrelevant. In such settings, the assistant must decide not only what to say, but also whether to speak at all. In this paper, we introduce Cocktail-Talker, a speech LLM framework for multi-speaker "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27756","kind":"arxiv","version":1},"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/2607.27756/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":"2026-07-31T01:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBXXr8KPKfPavUpAFZcUaFifjdVyBPnNfGl5RuoUIEZgZkVH248ssmA884F9Cjo6RAb4y9rcnyqJ0iqwPyb3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:49:35.076749Z"},"content_sha256":"2cd0b3acabfd56ff80e467a16594e1802649d08824b22129ab72b9adf2f55f6e","schema_version":"1.0","event_id":"sha256:2cd0b3acabfd56ff80e467a16594e1802649d08824b22129ab72b9adf2f55f6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE/bundle.json","state_url":"https://pith.science/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE/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":"2026-08-06T17:49:35Z","links":{"resolver":"https://pith.science/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE","bundle":"https://pith.science/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE/bundle.json","state":"https://pith.science/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4B7K4S5TKWZEWYFPH5JAHZPJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A4B7K4S5TKWZEWYFPH5JAHZPJE","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":"22909dffbca32d53043ea05199d81635c30be2e70dcc3d7818c72a0d600b0fe5","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-30T06:53:15Z","title_canon_sha256":"7ae98cf1e2d1ea4f1a33b67e575770c12514391bd2a24297105dea00ee610fae"},"schema_version":"1.0","source":{"id":"2607.27756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27756","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27756v1","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27756","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"A4B7K4S5TKWZ","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"A4B7K4S5TKWZEWYF","created_at":"2026-07-31T01:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"A4B7K4S5","created_at":"2026-07-31T01:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:2cd0b3acabfd56ff80e467a16594e1802649d08824b22129ab72b9adf2f55f6e","target":"graph","created_at":"2026-07-31T01:30:29Z","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/2607.27756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken dialog systems are typically designed for clean, dyadic interactions in which a single user and an assistant take turns speaking. Real-world social conversations, however, are often more ambiguous: multiple speakers may participate in the same conversation amid irrelevant speech and background noise. Each utterance may be directed to the assistant, addressed to another speaker, or completely irrelevant. In such settings, the assistant must decide not only what to say, but also whether to speak at all. In this paper, we introduce Cocktail-Talker, a speech LLM framework for multi-speaker ","authors_text":"Junkai Wu, Nima Mesgarani, Riki Shimizu, Sukru Samet Dindar, Xilin Jiang, Zhongweiyang Xu","cross_cats":["cs.CL","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-30T06:53:15Z","title":"Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27756","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":"sha256:1f81be9d35a5a6d4b8727751595638789aab37c44476c2f3234fde633b5c13ef","target":"record","created_at":"2026-07-31T01:30:29Z","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":"22909dffbca32d53043ea05199d81635c30be2e70dcc3d7818c72a0d600b0fe5","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-30T06:53:15Z","title_canon_sha256":"7ae98cf1e2d1ea4f1a33b67e575770c12514391bd2a24297105dea00ee610fae"},"schema_version":"1.0","source":{"id":"2607.27756","kind":"arxiv","version":1}},"canonical_sha256":"0703f5725d9aad925b0579fa901f2f4931b138f56751dc5b10ad8a6464440cab","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0703f5725d9aad925b0579fa901f2f4931b138f56751dc5b10ad8a6464440cab","first_computed_at":"2026-07-31T01:30:29.441189Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:30:29.441189Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f81be9d35a5a6d4b8727751595638789aab37c44476c2f3234fde633b5c13ef","sha256:2cd0b3acabfd56ff80e467a16594e1802649d08824b22129ab72b9adf2f55f6e"],"state_sha256":"ffb9f9062c76fcdc15538c1e47745dc62491d411f0ed6ae1ee0978f7b44c43de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EWvM9TAesI7sU+Xg5x8kQj7r+VtiQw05skcyO+yyhJuDxK0pt+vNT2I4ENQ/LvAlD80/C6jkHFYYLimRRxLKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:49:35.080004Z","bundle_sha256":"a41d2058e58ee203eea772f8a1b5e1003676f2d61388367b843db5432d0ba272"}}