{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6W2PCU2RO4OAKOHT2MXI7D4XQC","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":"e8a870ea12bb69b54d4993a4a11371cd16b1daa8ca2885d08670f3da267ee403","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T01:13:24Z","title_canon_sha256":"c6fed1e167a68219c9e731263f510654d2b2301ec217a9f99b40a606d80b168c"},"schema_version":"1.0","source":{"id":"2606.05558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05558","created_at":"2026-06-05T01:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05558v1","created_at":"2026-06-05T01:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05558","created_at":"2026-06-05T01:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"6W2PCU2RO4OA","created_at":"2026-06-05T01:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"6W2PCU2RO4OAKOHT","created_at":"2026-06-05T01:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"6W2PCU2R","created_at":"2026-06-05T01:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:0ca15023ccd76dd40611b377deaa4c47029a235256c137997e46c7904f8b5a70","target":"graph","created_at":"2026-06-05T01:14:54Z","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/2606.05558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language model (LLM) agents in multi-turn interactive environments is expensive and risky, as it requires online environment interaction. We propose ADWM (Autoregressive Diffusion World Model), an evaluation framework that estimates the performance of a new LLM agent policy purely from pre-collected trajectories. The core idea is to learn a latent diffusion world model that simulates how the environment responds to the evaluation policy, without ever executing it in the real environment. Existing diffusion-based OPE methods guide full trajectories in a single pass by jointly d","authors_text":"Guojun Xiong, Kaixuan Liu, Shengpu Tang, Weinan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T01:13:24Z","title":"Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05558","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:ab5a9d0a0a0ad6f61748177f20acb9974d91d2b606da6e23ea3d2f18686502b6","target":"record","created_at":"2026-06-05T01:14:54Z","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":"e8a870ea12bb69b54d4993a4a11371cd16b1daa8ca2885d08670f3da267ee403","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T01:13:24Z","title_canon_sha256":"c6fed1e167a68219c9e731263f510654d2b2301ec217a9f99b40a606d80b168c"},"schema_version":"1.0","source":{"id":"2606.05558","kind":"arxiv","version":1}},"canonical_sha256":"f5b4f15351771c0538f3d32e8f8f9780aa95adde53b960d732877485150c6fd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b4f15351771c0538f3d32e8f8f9780aa95adde53b960d732877485150c6fd5","first_computed_at":"2026-06-05T01:14:54.722695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:54.722695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zSopspjgd8O3Ee1EghyPh6C9Qx33fHEZUEMnWSEBK5dR6q948B9UzLJuIDm2sXImorLke5W8ailJOssPCku/BQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:54.723130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab5a9d0a0a0ad6f61748177f20acb9974d91d2b606da6e23ea3d2f18686502b6","sha256:0ca15023ccd76dd40611b377deaa4c47029a235256c137997e46c7904f8b5a70"],"state_sha256":"0e5a4aa17d5e31deadff905e685b12066ec3384b433614504d456cf13a588886"}