{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VO67JS32XCSZ2IM53PNMCLCKQM","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":"989aa2f953757a344dfba66d98ab62090366a13b1c3d130ee193d70a30f2775e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-22T05:56:46Z","title_canon_sha256":"24258c4c6208f2b94e71e7ab86201a7a7cc718586c073ac4767ca79076fd42ab"},"schema_version":"1.0","source":{"id":"2507.16252","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16252","created_at":"2026-07-05T11:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16252v1","created_at":"2026-07-05T11:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16252","created_at":"2026-07-05T11:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"VO67JS32XCSZ","created_at":"2026-07-05T11:41:06Z"},{"alias_kind":"pith_short_16","alias_value":"VO67JS32XCSZ2IM5","created_at":"2026-07-05T11:41:06Z"},{"alias_kind":"pith_short_8","alias_value":"VO67JS32","created_at":"2026-07-05T11:41:06Z"}],"graph_snapshots":[{"event_id":"sha256:749c35b2f2784079a11863bbd237914c01caced0b3167049a06963632c565230","target":"graph","created_at":"2026-07-05T11:41:06Z","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/2507.16252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) built on existing reinforcement learning with human feedback (RLHF) frameworks typically optimize responses based on immediate turn-level human preferences. However, this approach falls short in multi-turn dialogue settings, such as online math tutoring. We propose a method to enhance LLM-based tutors by representing the dialogue history with a lower-dimensional latent state representation of a student and optimizing a long-term policy to determine high-level actions based on the latent state. The goal is to better align the tutor's behavior with the long-term obje","authors_text":"Amy Zhang, Dean Foster, Emma Brunskill, Hyunji Nam, Lyle Ungar, Omer Gottesman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-22T05:56:46Z","title":"Efficient RL for optimizing conversation level outcomes with an LLM-based tutor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16252","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:ce32265093f2ccbc6f31cd53a4a24375240bfd34a67df980310abf54dc855cc5","target":"record","created_at":"2026-07-05T11:41:06Z","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":"989aa2f953757a344dfba66d98ab62090366a13b1c3d130ee193d70a30f2775e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-22T05:56:46Z","title_canon_sha256":"24258c4c6208f2b94e71e7ab86201a7a7cc718586c073ac4767ca79076fd42ab"},"schema_version":"1.0","source":{"id":"2507.16252","kind":"arxiv","version":1}},"canonical_sha256":"abbdf4cb7ab8a59d219ddbdac12c4a83093520d3bfcdbc38fb9a5bdeefae1f9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abbdf4cb7ab8a59d219ddbdac12c4a83093520d3bfcdbc38fb9a5bdeefae1f9e","first_computed_at":"2026-07-05T11:41:06.457827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:06.457827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GD8VwKqizqU3ezCx9xDahoJ/TauJSvaAiUw/3O2vmaPYEEfZXBSTWD4uw/o5PFSfmawbaXOw/Q9Gbyr3ByCCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:06.458257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16252","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce32265093f2ccbc6f31cd53a4a24375240bfd34a67df980310abf54dc855cc5","sha256:749c35b2f2784079a11863bbd237914c01caced0b3167049a06963632c565230"],"state_sha256":"4347b9b006ff6ccebaa12fbfa6064795d1aa01bc28666fd894bbe984c9ccb8a2"}