{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3XOLTHNIEYEWIMDTDOUI53CP7K","short_pith_number":"pith:3XOLTHNI","schema_version":"1.0","canonical_sha256":"dddcb99da826096430731ba88eec4ffa814d338e702ef5631366be6c83e32e52","source":{"kind":"arxiv","id":"2606.27806","version":1},"attestation_state":"computed","paper":{"title":"Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xinyuan Song, Zekun Cai","submitted_at":"2026-06-26T07:45:15Z","abstract_excerpt":"World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated state changes that are hard to score with ordinary regression losses. A parameterized world model is a trained transition predictor; its errors are easier to measure with quantities such as NodeMSE, delta accuracy, and validity accuracy, but it is usually weaker as a standalone planner. We compare these two families on four graph-structured planning benchmarks and introduce operational hallucination metrics for the agent-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.27806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T07:45:15Z","cross_cats_sorted":[],"title_canon_sha256":"01df55ee43622243491b3028d330dca2d4726696fd5d3836cfb9d4bc5e06ef8a","abstract_canon_sha256":"4a5015bcb85053b1aa533c4977a3e8aea99c9f7a823f3fa0073d8bb264748c13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:49.039966Z","signature_b64":"j2+qNB0NsIGFxTH1q1rl4JIiD6+ujrbXtLGeGYlvMyGAuHo6qf73GvF68gyVcfENgZHa+v2J8C66NXrs+mD/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dddcb99da826096430731ba88eec4ffa814d338e702ef5631366be6c83e32e52","last_reissued_at":"2026-06-29T01:14:49.039576Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:49.039576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xinyuan Song, Zekun Cai","submitted_at":"2026-06-26T07:45:15Z","abstract_excerpt":"World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated state changes that are hard to score with ordinary regression losses. A parameterized world model is a trained transition predictor; its errors are easier to measure with quantities such as NodeMSE, delta accuracy, and validity accuracy, but it is usually weaker as a standalone planner. We compare these two families on four graph-structured planning benchmarks and introduce operational hallucination metrics for the agent-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27806","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/2606.27806/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.27806","created_at":"2026-06-29T01:14:49.039637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27806v1","created_at":"2026-06-29T01:14:49.039637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27806","created_at":"2026-06-29T01:14:49.039637+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XOLTHNIEYEW","created_at":"2026-06-29T01:14:49.039637+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XOLTHNIEYEWIMDT","created_at":"2026-06-29T01:14:49.039637+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XOLTHNI","created_at":"2026-06-29T01:14:49.039637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K","json":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K.json","graph_json":"https://pith.science/api/pith-number/3XOLTHNIEYEWIMDTDOUI53CP7K/graph.json","events_json":"https://pith.science/api/pith-number/3XOLTHNIEYEWIMDTDOUI53CP7K/events.json","paper":"https://pith.science/paper/3XOLTHNI"},"agent_actions":{"view_html":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K","download_json":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K.json","view_paper":"https://pith.science/paper/3XOLTHNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27806&json=true","fetch_graph":"https://pith.science/api/pith-number/3XOLTHNIEYEWIMDTDOUI53CP7K/graph.json","fetch_events":"https://pith.science/api/pith-number/3XOLTHNIEYEWIMDTDOUI53CP7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K/action/storage_attestation","attest_author":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K/action/author_attestation","sign_citation":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K/action/citation_signature","submit_replication":"https://pith.science/pith/3XOLTHNIEYEWIMDTDOUI53CP7K/action/replication_record"}},"created_at":"2026-06-29T01:14:49.039637+00:00","updated_at":"2026-06-29T01:14:49.039637+00:00"}