{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:36PBPHCNHP2QPC4VS3SFISIZHJ","short_pith_number":"pith:36PBPHCN","schema_version":"1.0","canonical_sha256":"df9e179c4d3bf5078b9596e45449193a7c40f2946c1b7b18d3ab4802a71dbf43","source":{"kind":"arxiv","id":"2606.27780","version":1},"attestation_state":"computed","paper":{"title":"Understanding Rollout Error in Graph World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xinyuan Song, Zekun Cai","submitted_at":"2026-06-26T07:11:29Z","abstract_excerpt":"World models are often used for planning by rolling learned dynamics forward. Many planning environments, however, are not vectors or images; they are graphs of agents, tools, skills, routes, and dependencies. In these settings, a local prediction error may stay local or spread through the graph, and the failure mode changes again when edges are predicted rather than fixed. This paper studies long-horizon rollout error in Graph World Models (GWMs). We formulate a unified fixed-edge and dynamic-edge GWM framework with action nodes for node-, edge-, and graph-level decisions. We develop graph-va"},"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":"2606.27780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-26T07:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"66f16c6c5c0cdcaaecc0a11ea81e30312e44ca1673afb147e748d9bf05f55463","abstract_canon_sha256":"a8a8915d02ef210f6f5537d90dd8627604b3cfc150b7b070470cd24ef2c774e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:48.158238Z","signature_b64":"lqOvguBay9n9fQon1mn07pSDujFyfZI1nN6wzwirXkHFKOL2V5dITCFhBKgfPl/2zRe1K9IkDC5j7bfKkZAkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df9e179c4d3bf5078b9596e45449193a7c40f2946c1b7b18d3ab4802a71dbf43","last_reissued_at":"2026-06-29T01:14:48.157847Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:48.157847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Rollout Error in Graph World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xinyuan Song, Zekun Cai","submitted_at":"2026-06-26T07:11:29Z","abstract_excerpt":"World models are often used for planning by rolling learned dynamics forward. Many planning environments, however, are not vectors or images; they are graphs of agents, tools, skills, routes, and dependencies. In these settings, a local prediction error may stay local or spread through the graph, and the failure mode changes again when edges are predicted rather than fixed. This paper studies long-horizon rollout error in Graph World Models (GWMs). We formulate a unified fixed-edge and dynamic-edge GWM framework with action nodes for node-, edge-, and graph-level decisions. We develop graph-va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27780","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/2606.27780/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":"2606.27780","created_at":"2026-06-29T01:14:48.157906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27780v1","created_at":"2026-06-29T01:14:48.157906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27780","created_at":"2026-06-29T01:14:48.157906+00:00"},{"alias_kind":"pith_short_12","alias_value":"36PBPHCNHP2Q","created_at":"2026-06-29T01:14:48.157906+00:00"},{"alias_kind":"pith_short_16","alias_value":"36PBPHCNHP2QPC4V","created_at":"2026-06-29T01:14:48.157906+00:00"},{"alias_kind":"pith_short_8","alias_value":"36PBPHCN","created_at":"2026-06-29T01:14:48.157906+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/36PBPHCNHP2QPC4VS3SFISIZHJ","json":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ.json","graph_json":"https://pith.science/api/pith-number/36PBPHCNHP2QPC4VS3SFISIZHJ/graph.json","events_json":"https://pith.science/api/pith-number/36PBPHCNHP2QPC4VS3SFISIZHJ/events.json","paper":"https://pith.science/paper/36PBPHCN"},"agent_actions":{"view_html":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ","download_json":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ.json","view_paper":"https://pith.science/paper/36PBPHCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27780&json=true","fetch_graph":"https://pith.science/api/pith-number/36PBPHCNHP2QPC4VS3SFISIZHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/36PBPHCNHP2QPC4VS3SFISIZHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ/action/storage_attestation","attest_author":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ/action/author_attestation","sign_citation":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ/action/citation_signature","submit_replication":"https://pith.science/pith/36PBPHCNHP2QPC4VS3SFISIZHJ/action/replication_record"}},"created_at":"2026-06-29T01:14:48.157906+00:00","updated_at":"2026-06-29T01:14:48.157906+00:00"}