{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YY4LKWMLELTOO32K6E5EYRWYPZ","short_pith_number":"pith:YY4LKWML","canonical_record":{"source":{"id":"2604.03924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T01:32:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca97ae67cb17aa05f3f2575f3ee4c22fff1b0d871727900615a0d699886ecbe7","abstract_canon_sha256":"b8c1c918647b15637e63342383a8e9e1322c6fdec33e161ee639068e418580c1"},"schema_version":"1.0"},"canonical_sha256":"c638b5598b22e6e76f4af13a4c46d87e534e939b0ef8fe1ad137f51463d70b6f","source":{"kind":"arxiv","id":"2604.03924","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03924","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03924v2","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03924","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"YY4LKWMLELTO","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"YY4LKWMLELTOO32K","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"YY4LKWML","created_at":"2026-08-13T00:21:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YY4LKWMLELTOO32K6E5EYRWYPZ","target":"record","payload":{"canonical_record":{"source":{"id":"2604.03924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T01:32:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca97ae67cb17aa05f3f2575f3ee4c22fff1b0d871727900615a0d699886ecbe7","abstract_canon_sha256":"b8c1c918647b15637e63342383a8e9e1322c6fdec33e161ee639068e418580c1"},"schema_version":"1.0"},"canonical_sha256":"c638b5598b22e6e76f4af13a4c46d87e534e939b0ef8fe1ad137f51463d70b6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:21:21.205692Z","signature_b64":"TugrO6jrO4ZqGNh4pI6RNK5eb2MKN8X5twCHorV4lbC8RrjnfEp0O6rTe/xW/u71rcIK7pqpmznBoZHqBxuOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c638b5598b22e6e76f4af13a4c46d87e534e939b0ef8fe1ad137f51463d70b6f","last_reissued_at":"2026-08-13T00:21:21.204131Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:21:21.204131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.03924","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":"2026-08-13T00:21:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uc+iHSY/UYp6Su/Qxyf7tzzgk6tFLvAdRK2eL+RLEuF0SN25Rf63QFsy6pOH/7Wcdw6IlkSOrsIutpUwHxI0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:01:59.358294Z"},"content_sha256":"8279cf4d7d41f44d2bd33cf7a81f55b6a3e63d5cc2d930f878ec14759571863d","schema_version":"1.0","event_id":"sha256:8279cf4d7d41f44d2bd33cf7a81f55b6a3e63d5cc2d930f878ec14759571863d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YY4LKWMLELTOO32K6E5EYRWYPZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Uncertainty about a user's intent is a planning signal that lets conversational systems succeed more often with fewer turns.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Reza Averly, Xia Ning, Xinyi Ling, Ye Liu","submitted_at":"2026-04-05T01:32:00Z","abstract_excerpt":"Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's intent, where the algorithm must balance information acquisition and target commitment over multiple turns. Existing approaches address this challenge from different perspectives: structured methods enable multi-step planning but rely on predefined schemas, while LLM-based approaches support flexible interactions but lack long-horizon decision making, resulting in poor coordination between information acquisition and target commitment. To address this limitation, we formulate goal-orient"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CUP “consistently improves success rates while requiring fewer interaction turns” across Beauty, Fashion, Home and Inspired and three LLM backbones (Table 2), with the largest gains on the high-ambiguity Inspired set (e.g., Qwen3-4B: 89.80 % SR / 3.93 turns vs. 67.35 % / 4.30 for MISQ-HF).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an LLM user simulator (Llama-3.2-3B) plus a deterministic attribute-lookup rollout model inside MCTS faithfully approximate real multi-turn user responses and the true expected information gain of each action (Implementation Details §4.1 and Appendix A). If the simulator is systematically easier or more consistent than humans, the reported success-rate and turn reductions overstate real-world gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Uncertainty-guided MCTS over LLM-proposed ask/commit actions raises goal-oriented dialogue success while cutting turns across four benchmarks and three LLM backbones.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Uncertainty about a user's intent is a planning signal that lets conversational systems succeed more often with fewer turns.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"604c951202721d9192f080d92e854fb72b3a44e05df180b959826ef2596b7ef0"},"source":{"id":"2604.03924","kind":"arxiv","version":2},"verdict":{"id":"b5a89295-8677-4066-9bbd-d2cb30a6852f","model_set":{"reader":"grok-4.5"},"created_at":"2026-07-13T11:57:50.180180Z","strongest_claim":"CUP “consistently improves success rates while requiring fewer interaction turns” across Beauty, Fashion, Home and Inspired and three LLM backbones (Table 2), with the largest gains on the high-ambiguity Inspired set (e.g., Qwen3-4B: 89.80 % SR / 3.93 turns vs. 67.35 % / 4.30 for MISQ-HF).","one_line_summary":"Uncertainty-guided MCTS over LLM-proposed ask/commit actions raises goal-oriented dialogue success while cutting turns across four benchmarks and three LLM backbones.","pipeline_version":"pith-pipeline@v1.1.0-grok45","weakest_assumption":"That an LLM user simulator (Llama-3.2-3B) plus a deterministic attribute-lookup rollout model inside MCTS faithfully approximate real multi-turn user responses and the true expected information gain of each action (Implementation Details §4.1 and Appendix A). If the simulator is systematically easier or more consistent than humans, the reported success-rate and turn reductions overstate real-world gains.","pith_extraction_headline":"Uncertainty about a user's intent is a planning signal that lets conversational systems succeed more often with fewer turns."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03924/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":"b5a89295-8677-4066-9bbd-d2cb30a6852f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-13T00:21:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qk8nXTdVZy5s5EIo+ZDyiJQxaDkC/gQRHFwrTnCYCtxA9tV4YwGZl+xS6PdzuQYF9Ch1Y/Jptr5fiuSjTowcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:01:59.359111Z"},"content_sha256":"1dc35810ea646920237317a21a815ccde44c553e197662b2b7f11635b7787737","schema_version":"1.0","event_id":"sha256:1dc35810ea646920237317a21a815ccde44c553e197662b2b7f11635b7787737"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YY4LKWMLELTOO32K6E5EYRWYPZ/bundle.json","state_url":"https://pith.science/pith/YY4LKWMLELTOO32K6E5EYRWYPZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YY4LKWMLELTOO32K6E5EYRWYPZ/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":"2026-08-13T08:01:59Z","links":{"resolver":"https://pith.science/pith/YY4LKWMLELTOO32K6E5EYRWYPZ","bundle":"https://pith.science/pith/YY4LKWMLELTOO32K6E5EYRWYPZ/bundle.json","state":"https://pith.science/pith/YY4LKWMLELTOO32K6E5EYRWYPZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YY4LKWMLELTOO32K6E5EYRWYPZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YY4LKWMLELTOO32K6E5EYRWYPZ","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":"b8c1c918647b15637e63342383a8e9e1322c6fdec33e161ee639068e418580c1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T01:32:00Z","title_canon_sha256":"ca97ae67cb17aa05f3f2575f3ee4c22fff1b0d871727900615a0d699886ecbe7"},"schema_version":"1.0","source":{"id":"2604.03924","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03924","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03924v2","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03924","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"YY4LKWMLELTO","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"YY4LKWMLELTOO32K","created_at":"2026-08-13T00:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"YY4LKWML","created_at":"2026-08-13T00:21:21Z"}],"graph_snapshots":[{"event_id":"sha256:1dc35810ea646920237317a21a815ccde44c553e197662b2b7f11635b7787737","target":"graph","created_at":"2026-08-13T00:21:21Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CUP “consistently improves success rates while requiring fewer interaction turns” across Beauty, Fashion, Home and Inspired and three LLM backbones (Table 2), with the largest gains on the high-ambiguity Inspired set (e.g., Qwen3-4B: 89.80 % SR / 3.93 turns vs. 67.35 % / 4.30 for MISQ-HF)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That an LLM user simulator (Llama-3.2-3B) plus a deterministic attribute-lookup rollout model inside MCTS faithfully approximate real multi-turn user responses and the true expected information gain of each action (Implementation Details §4.1 and Appendix A). If the simulator is systematically easier or more consistent than humans, the reported success-rate and turn reductions overstate real-world gains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Uncertainty-guided MCTS over LLM-proposed ask/commit actions raises goal-oriented dialogue success while cutting turns across four benchmarks and three LLM backbones."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Uncertainty about a user's intent is a planning signal that lets conversational systems succeed more often with fewer turns."}],"snapshot_sha256":"604c951202721d9192f080d92e854fb72b3a44e05df180b959826ef2596b7ef0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.03924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Goal-oriented conversational systems require making sequential decisions under uncertainty about the user's intent, where the algorithm must balance information acquisition and target commitment over multiple turns. Existing approaches address this challenge from different perspectives: structured methods enable multi-step planning but rely on predefined schemas, while LLM-based approaches support flexible interactions but lack long-horizon decision making, resulting in poor coordination between information acquisition and target commitment. To address this limitation, we formulate goal-orient","authors_text":"Reza Averly, Xia Ning, Xinyi Ling, Ye Liu","cross_cats":["cs.AI"],"headline":"Uncertainty about a user's intent is a planning signal that lets conversational systems succeed more often with fewer turns.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T01:32:00Z","title":"Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.03924","kind":"arxiv","version":2},"verdict":{"created_at":"2026-07-13T11:57:50.180180Z","id":"b5a89295-8677-4066-9bbd-d2cb30a6852f","model_set":{"reader":"grok-4.5"},"one_line_summary":"Uncertainty-guided MCTS over LLM-proposed ask/commit actions raises goal-oriented dialogue success while cutting turns across four benchmarks and three LLM backbones.","pipeline_version":"pith-pipeline@v1.1.0-grok45","pith_extraction_headline":"Uncertainty about a user's intent is a planning signal that lets conversational systems succeed more often with fewer turns.","strongest_claim":"CUP “consistently improves success rates while requiring fewer interaction turns” across Beauty, Fashion, Home and Inspired and three LLM backbones (Table 2), with the largest gains on the high-ambiguity Inspired set (e.g., Qwen3-4B: 89.80 % SR / 3.93 turns vs. 67.35 % / 4.30 for MISQ-HF).","weakest_assumption":"That an LLM user simulator (Llama-3.2-3B) plus a deterministic attribute-lookup rollout model inside MCTS faithfully approximate real multi-turn user responses and the true expected information gain of each action (Implementation Details §4.1 and Appendix A). If the simulator is systematically easier or more consistent than humans, the reported success-rate and turn reductions overstate real-world gains."}},"verdict_id":"b5a89295-8677-4066-9bbd-d2cb30a6852f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8279cf4d7d41f44d2bd33cf7a81f55b6a3e63d5cc2d930f878ec14759571863d","target":"record","created_at":"2026-08-13T00:21:21Z","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":"b8c1c918647b15637e63342383a8e9e1322c6fdec33e161ee639068e418580c1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T01:32:00Z","title_canon_sha256":"ca97ae67cb17aa05f3f2575f3ee4c22fff1b0d871727900615a0d699886ecbe7"},"schema_version":"1.0","source":{"id":"2604.03924","kind":"arxiv","version":2}},"canonical_sha256":"c638b5598b22e6e76f4af13a4c46d87e534e939b0ef8fe1ad137f51463d70b6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c638b5598b22e6e76f4af13a4c46d87e534e939b0ef8fe1ad137f51463d70b6f","first_computed_at":"2026-08-13T00:21:21.204131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:21:21.204131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TugrO6jrO4ZqGNh4pI6RNK5eb2MKN8X5twCHorV4lbC8RrjnfEp0O6rTe/xW/u71rcIK7pqpmznBoZHqBxuOCQ==","signature_status":"signed_v1","signed_at":"2026-08-13T00:21:21.205692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.03924","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8279cf4d7d41f44d2bd33cf7a81f55b6a3e63d5cc2d930f878ec14759571863d","sha256:1dc35810ea646920237317a21a815ccde44c553e197662b2b7f11635b7787737"],"state_sha256":"3d7efa60753c63b732bdac5a5d52cf5841fd3221133a942d0ecf5df946c0b90a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PT+bG5wvZvnGWy7Pt2C9M9KIN6ACUBy+zPXp5tfVrp0Wm+iaROCnPC+RkGCj/aL2hH8syU8XFUAR5EVLTXFNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:01:59.363371Z","bundle_sha256":"c69c8d06b6a8988bc5ff6a02036869d5f8931fbebb4edbc2511dded30a26956a"}}