{"as_of":"2026-08-20T10:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:164f55930fc0d2be7a4614a8f4df45b7f12d4ed30d1a739562f7af82a40a82ef","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:23:35.198553Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T21:20:40.795352Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-19T21:47:48.355586Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.15785","snapshot_observed_at":"2026-08-03T21:20:40.795352Z","title":"WALL-E 2.0: World alignment by neurosymbolic learning improves world model-based LLM agents","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.15830","last_updated":"2026-07-20T14:51:40Z","snapshot_observed_at":"2026-08-10T05:07:44.096374Z","submitted_at":"2025-11-19T19:38:05Z","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-03T21:20:40.795352Z"},"links":{"cited_paper":"/paper/2504.15785","citing_paper":"/paper/2511.15830"},"observation_digest":"sha256:2dd7700f2b295252e671f4fa6f9eb0272d16ddd2863a0ac62eb4ce12d2d35496","observation_id":"381b2162-d7f1-4777-a4eb-60a0063f497a","resolution":{"observed_at":"2026-08-03T21:20:40.795352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"cited_work":{"arxiv_id":"2504.15785","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.15785","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wall-e 2.0: World alignment by neurosymbolic learning improves world model-based llm agents","venue":null,"work_id":"54b40bcd-672c-4aeb-898b-7577a91dc4b1","year":2025},"citing_paper":{"arxiv_id":"2605.09487","last_updated":"2026-05-10T11:51:18Z","snapshot_observed_at":"2026-08-15T07:10:32.750054Z","submitted_at":"2026-05-10T11:51:18Z","title":"Kintsugi: Learning Policies by Repairing Executable Knowledge Bases","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-12T04:11:13.607637Z"},"links":{"cited_paper":"/paper/2504.15785","citing_paper":"/paper/2605.09487"},"observation_digest":"sha256:a0171b82070ab15eba934f44134c69f694bd083b85c667f88f7b185ab5ed78d9","observation_id":"da0d837b-eb56-46b4-8b67-6b4ca753ecba","resolution":{"observed_at":"2026-05-12T06:31:28.588631Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"cited_work":{"arxiv_id":"2504.15785","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.15785","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wall-e 2.0: World alignment by neurosymbolic learning improves world model-based llm agents","venue":null,"work_id":"54b40bcd-672c-4aeb-898b-7577a91dc4b1","year":2025},"citing_paper":{"arxiv_id":"2605.14175","last_updated":"2026-05-13T22:54:16Z","snapshot_observed_at":"2026-08-12T22:59:43.477202Z","submitted_at":"2026-05-13T22:54:16Z","title":"Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-05-15T04:46:58.740567Z"},"links":{"cited_paper":"/paper/2504.15785","citing_paper":"/paper/2605.14175"},"observation_digest":"sha256:dcaa188201ca4baa1bd82836b04cb4b79f7be3299ac31defc5b70a028b7277f2","observation_id":"7dcc7dfa-c9a0-48f2-ada5-7352a5bafeeb","resolution":{"observed_at":"2026-05-15T04:49:44.477072Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"cited_work":{"arxiv_id":"2504.15785","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.15785","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wall-e 2.0: World alignment by neurosymbolic learning improves world model-based llm agents","venue":null,"work_id":"54b40bcd-672c-4aeb-898b-7577a91dc4b1","year":2025},"citing_paper":{"arxiv_id":"2605.16725","last_updated":"2026-05-16T00:18:22Z","snapshot_observed_at":"2026-08-12T17:08:21.134376Z","submitted_at":"2026-05-16T00:18:22Z","title":"Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-19T21:47:11.983066Z"},"links":{"cited_paper":"/paper/2504.15785","citing_paper":"/paper/2605.16725"},"observation_digest":"sha256:6076acbf575d9719fc165dd87c402df67166fc1cc7d833def3ee6aee9306de57","observation_id":"90503fca-99b0-4e97-b4d3-dfb8bc452255","resolution":{"observed_at":"2026-05-19T21:47:48.357306Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.15785/citation-record","integrity":"/paper/2504.15785/integrity","json":"/paper/2504.15785/citation-record.json","paper":"/paper/2504.15785"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.06817","last_updated":"2023-08-11T17:45:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-12-13T18:55:15Z","title":"RT-1: Robotics Transformer for Real-World Control at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06817","snapshot_observed_at":"2026-08-16T11:23:34.750302Z","title":"Rt-1: Robotics transformer for real-world control at scale","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.750302Z"},"links":{"cited_paper":"/paper/2212.06817","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:4f066644dc680d50478ab493efa2d8ae96da8056960c27eb15a7ca0f317587cf","observation_id":"23c33ece-84c8-4d02-99d0-f1905c5bdf52","resolution":{"observed_at":"2026-08-16T11:23:34.750302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14992","last_updated":"2023-10-23T07:24:28Z","snapshot_observed_at":"2026-08-15T11:39:07.998070Z","submitted_at":"2023-05-24T10:28:28Z","title":"Reasoning with Language Model is Planning with World Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14992","snapshot_observed_at":"2026-08-16T11:23:34.804590Z","title":"J., Wang, Z., Wang, D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.804590Z"},"links":{"cited_paper":"/paper/2305.14992","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:cfd572b0117b284e438a0f1898199eb00115acb9a0d27c8c2dd626899332025d","observation_id":"a93fa471-2639-4e7a-9591-7634c9722c42","resolution":{"observed_at":"2026-08-16T11:23:34.804590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.05230","last_updated":"2023-12-08T18:25:22Z","snapshot_observed_at":"2026-08-16T14:36:26.492028Z","submitted_at":"2023-12-08T18:25:22Z","title":"Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.05230","snapshot_observed_at":"2026-08-16T11:23:34.808439Z","title":"and Shu, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.808439Z"},"links":{"cited_paper":"/paper/2312.05230","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:a65ef54ccd613bec893e0de38600ecc2e711558abd228c97d814cedfd79eb5a4","observation_id":"9b52cf0a-24b9-4fb5-b655-b0ba1119abb4","resolution":{"observed_at":"2026-08-16T11:23:34.808439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03615","last_updated":"2024-10-21T11:05:27Z","snapshot_observed_at":"2026-08-18T02:46:45.321535Z","submitted_at":"2024-08-07T08:16:32Z","title":"Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03615","snapshot_observed_at":"2026-08-16T11:23:34.812401Z","title":"Optimus-1: Hybrid multimodal memory empow- ered agents excel in long-horizon tasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.812401Z"},"links":{"cited_paper":"/paper/2408.03615","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:5e5da829e6652453619892e9c746278117546f034247e298fcf2679bf5c37ee5","observation_id":"de1207a2-5b59-4240-a2ee-3c79864998ca","resolution":{"observed_at":"2026-08-16T11:23:34.812401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17382","last_updated":"2024-06-24T05:25:21Z","snapshot_observed_at":"2026-08-16T14:56:27.024868Z","submitted_at":"2023-09-29T16:36:39Z","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17382","snapshot_observed_at":"2026-08-16T11:23:34.916107Z","title":"Reason for future, act for now: A principled framework for autonomous llm agents with provable sam- ple efficiency","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.916107Z"},"links":{"cited_paper":"/paper/2309.17382","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:58ec8155eb142d64bd453445685744056f5fe81f92e1246c6d5934e67079e0d4","observation_id":"9928c843-8aa4-41ab-90c4-1c7e0afff579","resolution":{"observed_at":"2026-08-16T11:23:34.916107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01538","last_updated":"2024-01-22T02:39:17Z","snapshot_observed_at":"2026-08-17T14:59:43.859156Z","submitted_at":"2023-09-04T11:38:02Z","title":"ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01538","snapshot_observed_at":"2026-08-16T11:23:34.975620Z","title":"Chatrule: Mining logical rules with large language models for knowledge graph reasoning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.975620Z"},"links":{"cited_paper":"/paper/2309.01538","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:b6efe44cfa2c4cfbdbc396bbacfa6aaec0b89736c97f183616fb40e46bc89884","observation_id":"7dae5880-8600-4948-89d2-cc3e1ed41073","resolution":{"observed_at":"2026-08-16T11:23:34.975620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.07972","last_updated":"2021-09-20T11:49:49Z","snapshot_observed_at":"2026-08-18T16:27:44.009247Z","submitted_at":"2021-04-16T08:47:07Z","title":"Language Models are Few-Shot Butlers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.07972","snapshot_observed_at":"2026-08-16T11:23:34.979110Z","title":"and Fleuret, F","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.979110Z"},"links":{"cited_paper":"/paper/2104.07972","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:da25f04feffe70103a6c440c2fdb163c576c6c975d90bdb3f4ff33939b241d23","observation_id":"af2e81d4-0d99-4897-ae59-caa088c1aef8","resolution":{"observed_at":"2026-08-16T11:23:34.979110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04235","last_updated":"2024-03-08T17:04:49Z","snapshot_observed_at":"2026-08-19T17:51:28.356488Z","submitted_at":"2023-11-06T08:50:29Z","title":"Can LLMs Follow Simple Rules?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04235","snapshot_observed_at":"2026-08-16T11:23:34.983922Z","title":"Can llms follow simple rules? arXiv preprint arXiv:2311.04235, 2023a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.983922Z"},"links":{"cited_paper":"/paper/2311.04235","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:513ea5677bfc3a3063cd15a23b797e15eee4fddda81457513538673c1884100f","observation_id":"81081c5a-76ad-4cd6-8029-7fe86da35a89","resolution":{"observed_at":"2026-08-16T11:23:34.983922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-20T07:04:06.309989Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-16T11:23:34.987387Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.987387Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:3c32716a7d0eb4479899140181feca3719f088377137878d369da45de1fc3e6a","observation_id":"bf5a3cf6-c8e9-49a2-817e-79b8603ec493","resolution":{"observed_at":"2026-08-16T11:23:34.987387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03768","last_updated":"2021-03-14T22:44:38Z","snapshot_observed_at":"2026-08-19T18:51:42.906395Z","submitted_at":"2020-10-08T05:13:36Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03768","snapshot_observed_at":"2026-08-16T11:23:34.995788Z","title":"ALFRED: A benchmark for interpreting grounded instructions for everyday tasks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.995788Z"},"links":{"cited_paper":"/paper/2010.03768","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:aa6a3ba2737a3e08b88f94ed94c18001c3b4d59b8da9297615bba56a28300c62","observation_id":"002b68d1-30ae-46de-9e23-c4edae3391b3","resolution":{"observed_at":"2026-08-16T11:23:34.995788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12275","last_updated":"2024-09-20T18:56:41Z","snapshot_observed_at":"2026-08-19T13:14:49.887477Z","submitted_at":"2024-02-19T16:39:18Z","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12275","snapshot_observed_at":"2026-08-16T11:23:35.063040Z","title":"Worldcoder, a model- based llm agent: Building world models by writing code and interacting with the environment","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.063040Z"},"links":{"cited_paper":"/paper/2402.12275","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:0132b3b24e2be4e03388d723948c455785ee6f15e7f9041e95c913fd3eb41294","observation_id":"fad37ba7-765a-48ae-95b5-27632166be69","resolution":{"observed_at":"2026-08-16T11:23:35.063040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08155","last_updated":"2023-10-03T20:47:10Z","snapshot_observed_at":"2026-08-08T22:28:26.004138Z","submitted_at":"2023-08-16T05:57:52Z","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08155","snapshot_observed_at":"2026-08-16T11:23:35.165317Z","title":"Autogen: Enabling next-gen llm applications via multi-agent conversation framework","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.165317Z"},"links":{"cited_paper":"/paper/2308.08155","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:98220e48ade0b08bb1049bbcf1123c2f96229476c5cc3109e959f393ea4e1b1b","observation_id":"12965d76-8a4a-4c3d-a3ab-4902c32a1ac7","resolution":{"observed_at":"2026-08-16T11:23:35.165317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10900","last_updated":"2024-10-09T03:42:22Z","snapshot_observed_at":"2026-08-18T08:56:15.780288Z","submitted_at":"2024-06-16T11:44:43Z","title":"AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10900","snapshot_observed_at":"2026-08-16T11:23:35.170484Z","title":"L., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.170484Z"},"links":{"cited_paper":"/paper/2406.10900","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:1018389a84b3d7cc276948e38d3c7f72c62fa8694cd9997a819158bf8c500163","observation_id":"25cb27ca-bc7a-4a79-b0d9-50da628c93f1","resolution":{"observed_at":"2026-08-16T11:23:35.170484Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12278","last_updated":"2024-10-02T23:37:50Z","snapshot_observed_at":"2026-08-20T07:01:49.691370Z","submitted_at":"2024-09-18T19:28:04Z","title":"Making Large Language Models into World Models with Precondition and Effect Knowledge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12278","snapshot_observed_at":"2026-08-16T11:23:35.174374Z","title":"Making large language models into world models with precondition and effect knowledge","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.174374Z"},"links":{"cited_paper":"/paper/2409.12278","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:78fab276d8d85bd12251e625fc43e069a9d8d192ebdaca8462eb2f9d737c2691","observation_id":"9bc48c44-b96c-4d8e-a06a-211c0d0db9f9","resolution":{"observed_at":"2026-08-16T11:23:35.174374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08883","last_updated":"2024-12-16T00:37:33Z","snapshot_observed_at":"2026-08-16T14:43:07.280344Z","submitted_at":"2023-11-15T11:42:41Z","title":"Distilling Rule-based Knowledge into Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08883","snapshot_observed_at":"2026-08-16T11:23:35.177709Z","title":"Enabling large language models to learn from rules","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.177709Z"},"links":{"cited_paper":"/paper/2311.08883","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:40285f2a53dc05e176b2c76c8d43302ae7b285d33afe7dc07b622ec4032bb128","observation_id":"fcb084c1-4fd3-45c5-8731-8d2ea0910aab","resolution":{"observed_at":"2026-08-16T11:23:35.177709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15746","last_updated":"2023-10-24T11:40:34Z","snapshot_observed_at":"2026-08-16T22:50:59.817909Z","submitted_at":"2023-10-24T11:40:34Z","title":"Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15746","snapshot_observed_at":"2026-08-16T11:23:35.180569Z","title":"Failures pave the way: En- hancing large language models through tuning-free rule accumulation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.180569Z"},"links":{"cited_paper":"/paper/2310.15746","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:2abee709100d190ef9b32e743142ab843cc5d5d14672ca17b1a6be2af5e1213f","observation_id":"408d6e04-f94f-4611-96b2-40f5fc579868","resolution":{"observed_at":"2026-08-16T11:23:35.180569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.07484","last_updated":"2024-10-11T23:32:09Z","snapshot_observed_at":"2026-08-16T13:10:54.596357Z","submitted_at":"2024-10-09T23:37:36Z","title":"WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.07484","snapshot_observed_at":"2026-08-16T11:23:35.183907Z","title":"Wall-e: World alignment by rule learning improves world model-based llm agents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.183907Z"},"links":{"cited_paper":"/paper/2410.07484","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:541873a5b81cdc0575f7641d93a144b904d287b930f1d246e8be2263dffc7cbe","observation_id":"5d767370-c9d3-42bf-a774-1130256d6c53","resolution":{"observed_at":"2026-08-16T11:23:35.183907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10592","last_updated":"2023-10-02T16:38:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-20T18:25:35Z","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10592","snapshot_observed_at":"2026-08-16T11:23:35.187414Z","title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.187414Z"},"links":{"cited_paper":"/paper/2304.10592","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:8e97cffe2c8682fe06c6feadda3ac84df06bb63e8ec96b8c58fbdca7e3c8602e","observation_id":"fa7c1634-d81e-4874-9e24-8640756080e8","resolution":{"observed_at":"2026-08-16T11:23:35.187414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:23:35.700656Z","title":null,"venue":null,"work_id":"1ace5433-b61d-4694-995a-b71c2aa57db7","year":2024},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.191212Z"},"links":{"citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:ee6517d4f1271aa3c10316dfb43a0c59b0d08973af533387eba9d5b5f83094d3","observation_id":"6f824eb6-8bdb-4d25-b811-3e3b66269490","resolution":{"observed_at":"2026-08-16T11:23:35.704979Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:23:35.656900Z","title":null,"venue":null,"work_id":"307a763b-a7a6-4756-8206-6e32f5f22807","year":2023},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.194967Z"},"links":{"citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:c8b82989b18698edb034467646c54c65c374d378d6b1a329b735f0cf7d2babb2","observation_id":"2e2f28ea-c108-4910-b38e-fdbfb4faa2ce","resolution":{"observed_at":"2026-08-16T11:23:35.693880Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:23:35.474690Z","title":"Action failed: Not enough {resource} to make {tool_name}","venue":null,"work_id":"2274986f-6baf-4b88-8da2-3183d2867581","year":2022},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.198553Z"},"links":{"citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:ed2ba1dbf43f7fc8d102358d0f07a1352857d7f47c256dadbfa2c2f785fe8532","observation_id":"8ce34c54-add4-4fd8-aaf1-0cd58d00fe40","resolution":{"observed_at":"2026-08-16T11:23:35.543696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11366","last_updated":"2023-10-10T05:21:45Z","snapshot_observed_at":"2026-08-17T19:15:32.679249Z","submitted_at":"2023-03-20T18:08:50Z","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11366","snapshot_observed_at":"2026-08-16T11:23:34.991247Z","title":"Reflexion: Language agents with verbal reinforcement learning.(2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.991247Z"},"links":{"cited_paper":"/paper/2303.11366","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:f8fcaf8724493f663f2537fae25aa9e66c0ec8b39b60b290fbbebd0a51dc42ec","observation_id":"0844abc8-e8fc-4dbe-be49-c2a86f79b888","resolution":{"observed_at":"2026-08-16T11:23:34.991247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.02561","last_updated":"2024-03-03T08:12:36Z","snapshot_observed_at":"2026-08-16T15:03:03.025603Z","submitted_at":"2023-09-05T20:21:03Z","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.02561","snapshot_observed_at":"2026-08-16T11:23:34.792958Z","title":"Physically grounded vision- language models for robotic manipulation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.792958Z"},"links":{"cited_paper":"/paper/2309.02561","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:e3a66810d643d02b3175c42d06ada51e1ac1c91386a9f20b37a156f6ad47fb81","observation_id":"842169d1-ed27-4c45-8818-7a784ebf42b1","resolution":{"observed_at":"2026-08-16T11:23:34.792958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.04104","last_updated":"2024-04-17T17:41:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-01-10T18:12:16Z","title":"Mastering Diverse Domains through World Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.04104","snapshot_observed_at":"2026-08-16T11:23:34.800527Z","title":"Mastering diverse domains through world models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.800527Z"},"links":{"cited_paper":"/paper/2301.04104","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:d11ce9550614cc513c3868129b7d20c1c6275e4666f85c2f4c146c590da664fd","observation_id":"119d13e4-205d-4603-a080-767800b1e367","resolution":{"observed_at":"2026-08-16T11:23:34.800527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08566","last_updated":"2023-12-13T23:35:31Z","snapshot_observed_at":"2026-08-16T14:34:57.001260Z","submitted_at":"2023-12-13T23:35:31Z","title":"Learning adaptive planning representations with natural language guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08566","snapshot_observed_at":"2026-08-16T11:23:35.133282Z","title":"S., Feng, J., Ko- rneev, N., Tenenbaum, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:35.133282Z"},"links":{"cited_paper":"/paper/2312.08566","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:231033a2424dec5f0376afb82d9b264f017e14ba77af2f1d2eb35d1a55c53a3e","observation_id":"2630d68f-d42f-4cc6-b9cc-34d75cd0de1d","resolution":{"observed_at":"2026-08-16T11:23:35.133282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06780","last_updated":"2022-02-12T20:02:13Z","snapshot_observed_at":"2026-08-16T17:56:40.043488Z","submitted_at":"2021-09-14T15:49:31Z","title":"Benchmarking the Spectrum of Agent Capabilities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.06780","snapshot_observed_at":"2026-08-16T11:23:34.796804Z","title":"Benchmarking the spectrum of agent capabilities","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.796804Z"},"links":{"cited_paper":"/paper/2109.06780","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:d4b2f01ab2851d087b9737ef2ffb186188e7e79ddc12f930d2b85b230148aa00","observation_id":"64766794-f8cd-4386-89a4-4b03de697775","resolution":{"observed_at":"2026-08-16T11:23:34.796804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06886","last_updated":"2025-08-25T02:20:09Z","snapshot_observed_at":"2026-08-17T00:52:37.891311Z","submitted_at":"2024-07-09T14:14:47Z","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06886","snapshot_observed_at":"2026-08-16T11:23:34.827015Z","title":"Aligning cyber space with physical world: A comprehensive survey on embodied ai","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-16T11:23:34.827015Z"},"links":{"cited_paper":"/paper/2407.06886","citing_paper":"/paper/2504.15785"},"observation_digest":"sha256:7932ce3df2c413ad8b389240ce8e06c79a6771030d390f74438c41bfddc184cc","observation_id":"a0b70f27-c3c6-45b8-853a-d47a95f7ce52","resolution":{"observed_at":"2026-08-16T11:23:34.827015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.15785","last_updated":"2025-04-22T10:58:27Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-18T18:16:30.868523Z","submitted_at":"2025-04-22T10:58:27Z","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":27},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 4 inbound Pith citation observations for arXiv:2504.15785."}