{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UITKPTYGBZQGBV4TLRT7XW6FWS","short_pith_number":"pith:UITKPTYG","canonical_record":{"source":{"id":"2504.15785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-22T10:58:27Z","cross_cats_sorted":[],"title_canon_sha256":"d7fc4b853323ab21a51350d117b83e1699836c7c569f4b7883a6e935fbd64ed4","abstract_canon_sha256":"9b919ade85440caae04bb37b1c8e3a66ba087d698aec5197fa7f973cd5107238"},"schema_version":"1.0"},"canonical_sha256":"a226a7cf060e6060d7935c67fbdbc5b48fb8343f04554ba5fbf31add9353a963","source":{"kind":"arxiv","id":"2504.15785","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15785","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15785v1","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15785","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"UITKPTYGBZQG","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"UITKPTYGBZQGBV4T","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"UITKPTYG","created_at":"2026-07-05T10:52:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UITKPTYGBZQGBV4TLRT7XW6FWS","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-22T10:58:27Z","cross_cats_sorted":[],"title_canon_sha256":"d7fc4b853323ab21a51350d117b83e1699836c7c569f4b7883a6e935fbd64ed4","abstract_canon_sha256":"9b919ade85440caae04bb37b1c8e3a66ba087d698aec5197fa7f973cd5107238"},"schema_version":"1.0"},"canonical_sha256":"a226a7cf060e6060d7935c67fbdbc5b48fb8343f04554ba5fbf31add9353a963","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:29.946655Z","signature_b64":"fcK8ka7AdJ+leBUjG0vXFx7FvL5kUoICYBlb1ZC5JQYizE+bO8KJJlBFKfwMh++0OZIOixcKHiaRvObV1CefBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a226a7cf060e6060d7935c67fbdbc5b48fb8343f04554ba5fbf31add9353a963","last_reissued_at":"2026-07-05T10:52:29.946143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:29.946143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15785","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6xbkGc2prqeQKMjcbiKIJ+jrDmX4YbyQio8A3O31XRvwvR8woHU09YnE6R3Ge2m3Lzgquw5ZQwX2uat7tcOZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:21:33.296636Z"},"content_sha256":"591469011ab341c8d341d75cb5c5efdbb568057607f481a1b1de88531a117a18","schema_version":"1.0","event_id":"sha256:591469011ab341c8d341d75cb5c5efdbb568057607f481a1b1de88531a117a18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UITKPTYGBZQGBV4TLRT7XW6FWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengqi Zhang, Deheng Ye, Guodong Long, Jing Jiang, Siyu Zhou, Tianyi Zhou, Yijun Yang","submitted_at":"2025-04-22T10:58:27Z","abstract_excerpt":"Can we build accurate world models out of large language models (LLMs)? How can world models benefit LLM agents? The gap between the prior knowledge of LLMs and the specified environment's dynamics usually bottlenecks LLMs' performance as world models. To bridge the gap, we propose a training-free \"world alignment\" that learns an environment's symbolic knowledge complementary to LLMs. The symbolic knowledge covers action rules, knowledge graphs, and scene graphs, which are extracted by LLMs from exploration trajectories and encoded into executable codes to regulate LLM agents' policies. We fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15785","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/2504.15785/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EeEPyRuJui/3F/1oSFuqpgKdjjd4FkhWNda96Cl0yBn3bmjenyibwc8PHfOeQpT8nwjGUAXcYFXfCukFcAzoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:21:33.297717Z"},"content_sha256":"842e6b15c1c288fd147ec684c518fce11065f7707d15f8639166a8cd5c725879","schema_version":"1.0","event_id":"sha256:842e6b15c1c288fd147ec684c518fce11065f7707d15f8639166a8cd5c725879"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UITKPTYGBZQGBV4TLRT7XW6FWS/bundle.json","state_url":"https://pith.science/pith/UITKPTYGBZQGBV4TLRT7XW6FWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UITKPTYGBZQGBV4TLRT7XW6FWS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T23:21:33Z","links":{"resolver":"https://pith.science/pith/UITKPTYGBZQGBV4TLRT7XW6FWS","bundle":"https://pith.science/pith/UITKPTYGBZQGBV4TLRT7XW6FWS/bundle.json","state":"https://pith.science/pith/UITKPTYGBZQGBV4TLRT7XW6FWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UITKPTYGBZQGBV4TLRT7XW6FWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UITKPTYGBZQGBV4TLRT7XW6FWS","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":"9b919ade85440caae04bb37b1c8e3a66ba087d698aec5197fa7f973cd5107238","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-22T10:58:27Z","title_canon_sha256":"d7fc4b853323ab21a51350d117b83e1699836c7c569f4b7883a6e935fbd64ed4"},"schema_version":"1.0","source":{"id":"2504.15785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15785","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15785v1","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15785","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"UITKPTYGBZQG","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"UITKPTYGBZQGBV4T","created_at":"2026-07-05T10:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"UITKPTYG","created_at":"2026-07-05T10:52:29Z"}],"graph_snapshots":[{"event_id":"sha256:842e6b15c1c288fd147ec684c518fce11065f7707d15f8639166a8cd5c725879","target":"graph","created_at":"2026-07-05T10:52:29Z","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/2504.15785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can we build accurate world models out of large language models (LLMs)? How can world models benefit LLM agents? The gap between the prior knowledge of LLMs and the specified environment's dynamics usually bottlenecks LLMs' performance as world models. To bridge the gap, we propose a training-free \"world alignment\" that learns an environment's symbolic knowledge complementary to LLMs. The symbolic knowledge covers action rules, knowledge graphs, and scene graphs, which are extracted by LLMs from exploration trajectories and encoded into executable codes to regulate LLM agents' policies. We fur","authors_text":"Chengqi Zhang, Deheng Ye, Guodong Long, Jing Jiang, Siyu Zhou, Tianyi Zhou, Yijun Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15785","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":"sha256:591469011ab341c8d341d75cb5c5efdbb568057607f481a1b1de88531a117a18","target":"record","created_at":"2026-07-05T10:52:29Z","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":"9b919ade85440caae04bb37b1c8e3a66ba087d698aec5197fa7f973cd5107238","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-22T10:58:27Z","title_canon_sha256":"d7fc4b853323ab21a51350d117b83e1699836c7c569f4b7883a6e935fbd64ed4"},"schema_version":"1.0","source":{"id":"2504.15785","kind":"arxiv","version":1}},"canonical_sha256":"a226a7cf060e6060d7935c67fbdbc5b48fb8343f04554ba5fbf31add9353a963","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a226a7cf060e6060d7935c67fbdbc5b48fb8343f04554ba5fbf31add9353a963","first_computed_at":"2026-07-05T10:52:29.946143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:29.946143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fcK8ka7AdJ+leBUjG0vXFx7FvL5kUoICYBlb1ZC5JQYizE+bO8KJJlBFKfwMh++0OZIOixcKHiaRvObV1CefBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:29.946655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:591469011ab341c8d341d75cb5c5efdbb568057607f481a1b1de88531a117a18","sha256:842e6b15c1c288fd147ec684c518fce11065f7707d15f8639166a8cd5c725879"],"state_sha256":"eafdfd197064d00d24b17ce2ea056fcb6cfb1f9862b2171fdba6d813c1aa6e24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hL0cu/v6YDjypOMnf/bdLgZAhMQHtGoqjG6tb4qHahOEgomjr2H+QfJMCy0GdyW6Wg9KCtNjHtoCdNs34O9YCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:21:33.304359Z","bundle_sha256":"95aa55c885dc6f107ee59cc729eec2a09b4adba2c1a190cf6fe9f16765478a14"}}