{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VFQNJE4KGFUTOXUXECXUWHKNG5","short_pith_number":"pith:VFQNJE4K","schema_version":"1.0","canonical_sha256":"a960d4938a3169375e9720af4b1d4d375b125ff8260225ef5e0e7345aee2527b","source":{"kind":"arxiv","id":"2502.04728","version":2},"attestation_state":"computed","paper":{"title":"Generating Symbolic World Models via Test-time Scaling of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuxiang Frank Xia, Ge Lin, Ge Zhang, Jie Fu, Tim Z. Xiao, Weiyang Liu, Yuhuan Yuan, Zhouliang Yu","submitted_at":"2025-02-07T07:52:25Z","abstract_excerpt":"Solving complex planning problems requires Large Language Models (LLMs) to explicitly model the state transition to avoid rule violations, comply with constraints, and ensure optimality-a task hindered by the inherent ambiguity of natural language. To overcome such ambiguity, Planning Domain Definition Language (PDDL) is leveraged as a planning abstraction that enables precise and formal state descriptions. With PDDL, we can generate a symbolic world model where classic searching algorithms, such as A*, can be seamlessly applied to find optimal plans. However, directly generating PDDL domains "},"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":"2502.04728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-07T07:52:25Z","cross_cats_sorted":[],"title_canon_sha256":"4ad5b14be7c1760c387bd231d0f047c13b2eeb1f0452bc8565e46826ac444873","abstract_canon_sha256":"bb7692e58375350edd9c50ef73af88455499928104f11502302c39c27323e9e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:04.444413Z","signature_b64":"K0SNebOdvJg0SE6+FpxjBD7JjEmVSoiyTkm3u5lL8O8enVuR+WW8Q3rjr8f7hk9l47H58tHoa81pjOScibjdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a960d4938a3169375e9720af4b1d4d375b125ff8260225ef5e0e7345aee2527b","last_reissued_at":"2026-07-05T11:00:04.443925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:04.443925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Symbolic World Models via Test-time Scaling of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fuxiang Frank Xia, Ge Lin, Ge Zhang, Jie Fu, Tim Z. Xiao, Weiyang Liu, Yuhuan Yuan, Zhouliang Yu","submitted_at":"2025-02-07T07:52:25Z","abstract_excerpt":"Solving complex planning problems requires Large Language Models (LLMs) to explicitly model the state transition to avoid rule violations, comply with constraints, and ensure optimality-a task hindered by the inherent ambiguity of natural language. To overcome such ambiguity, Planning Domain Definition Language (PDDL) is leveraged as a planning abstraction that enables precise and formal state descriptions. With PDDL, we can generate a symbolic world model where classic searching algorithms, such as A*, can be seamlessly applied to find optimal plans. However, directly generating PDDL domains "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04728","kind":"arxiv","version":2},"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/2502.04728/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":"2502.04728","created_at":"2026-07-05T11:00:04.443983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04728v2","created_at":"2026-07-05T11:00:04.443983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04728","created_at":"2026-07-05T11:00:04.443983+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFQNJE4KGFUT","created_at":"2026-07-05T11:00:04.443983+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFQNJE4KGFUTOXUX","created_at":"2026-07-05T11:00:04.443983+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFQNJE4K","created_at":"2026-07-05T11:00:04.443983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07602","citing_title":"Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5","json":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5.json","graph_json":"https://pith.science/api/pith-number/VFQNJE4KGFUTOXUXECXUWHKNG5/graph.json","events_json":"https://pith.science/api/pith-number/VFQNJE4KGFUTOXUXECXUWHKNG5/events.json","paper":"https://pith.science/paper/VFQNJE4K"},"agent_actions":{"view_html":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5","download_json":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5.json","view_paper":"https://pith.science/paper/VFQNJE4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04728&json=true","fetch_graph":"https://pith.science/api/pith-number/VFQNJE4KGFUTOXUXECXUWHKNG5/graph.json","fetch_events":"https://pith.science/api/pith-number/VFQNJE4KGFUTOXUXECXUWHKNG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5/action/storage_attestation","attest_author":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5/action/author_attestation","sign_citation":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5/action/citation_signature","submit_replication":"https://pith.science/pith/VFQNJE4KGFUTOXUXECXUWHKNG5/action/replication_record"}},"created_at":"2026-07-05T11:00:04.443983+00:00","updated_at":"2026-07-05T11:00:04.443983+00:00"}