{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QNSAHV2DOYDNQU3YXGRWCPZPNK","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":"2714a04c71769a27ff5ed62e6e2c4dc556ef149d9c28665481369a88e56c755f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T23:04:55Z","title_canon_sha256":"9028dc5c89f22ec4ba65ea7d1d662b3ef7e83419b4a975d29bee72744b661653"},"schema_version":"1.0","source":{"id":"2606.08875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08875","created_at":"2026-06-09T02:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08875v1","created_at":"2026-06-09T02:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08875","created_at":"2026-06-09T02:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"QNSAHV2DOYDN","created_at":"2026-06-09T02:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"QNSAHV2DOYDNQU3Y","created_at":"2026-06-09T02:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"QNSAHV2D","created_at":"2026-06-09T02:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:30c4a9a45c7e332316f4816129d272c074ffd0bf3e1a6cb25cd80676830f8686","target":"graph","created_at":"2026-06-09T02:07:44Z","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/2606.08875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress and resistance. In dementia care, this balance is especially difficult: trajectory level rewards are too sparse for turn level credit assignment, while external LLM-based evaluators are costly and can misread fragmented or indirect patient responses. To address this issue, we propose \\textbf{T}urn-\\textbf{T}rajectory \\textbf{G}roup \\textbf{R}elative \\textbf{P}olicy \\textbf{O}ptimization (\\textbf{T$^{2}$-GRPO}), a fram","authors_text":"Amir M. Rahmani, Honghui Xu, Jiang Wu, Nikil Dutt, Pengfei Zhang, Wenjun Huang, Yutong Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T23:04:55Z","title":"Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08875","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":"sha256:0eb083d3f1f4c6979b59e83c343c8756353a7b3c378a2043bf28713307a5d2f2","target":"record","created_at":"2026-06-09T02:07:44Z","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":"2714a04c71769a27ff5ed62e6e2c4dc556ef149d9c28665481369a88e56c755f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T23:04:55Z","title_canon_sha256":"9028dc5c89f22ec4ba65ea7d1d662b3ef7e83419b4a975d29bee72744b661653"},"schema_version":"1.0","source":{"id":"2606.08875","kind":"arxiv","version":1}},"canonical_sha256":"836403d7437606d85378b9a3613f2f6ab194fbe9668b84c932175f1fd88a7ae9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"836403d7437606d85378b9a3613f2f6ab194fbe9668b84c932175f1fd88a7ae9","first_computed_at":"2026-06-09T02:07:44.781334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:44.781334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"txa8x7q+2ec8G2L8TqRRIAL+XWVL9kTmpu4F36fyntSSrujxVzojQMPWhO1ene3JWQtmwvSQy37mBxAhHLPeCA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:44.781810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eb083d3f1f4c6979b59e83c343c8756353a7b3c378a2043bf28713307a5d2f2","sha256:30c4a9a45c7e332316f4816129d272c074ffd0bf3e1a6cb25cd80676830f8686"],"state_sha256":"8666cc22475ef17fc7ca4227770186edaeda2d9e44b4f33cf771dbb8f56aa167"}