{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KA5K6DVWTHK7GOYCL5DUUHZI2P","short_pith_number":"pith:KA5K6DVW","schema_version":"1.0","canonical_sha256":"503aaf0eb699d5f33b025f474a1f28d3e6c0e88df10b68e0f3e26cd95e8131bf","source":{"kind":"arxiv","id":"2501.00195","version":1},"attestation_state":"computed","paper":{"title":"Towards Unraveling and Improving Generalization in World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hang Wang, Junshan Zhang, Qiaoyi Fang, Weiyu Du","submitted_at":"2024-12-31T00:15:43Z","abstract_excerpt":"World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness and generalization capabilities of world models. Thus motivated, we develop a stochastic differential equation formulation by treating the world model learning as a stochastic dynamical system, and characterize the impact of latent representation errors on robustness and generalization, for both cases with zero-drift representation errors and with non-zero-dr"},"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":"2501.00195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T00:15:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e55719ddf4e21c57c98236ea24eefc5951d24d7901d604e06d70a83b822748c","abstract_canon_sha256":"5b1fdbf3d87c8f9b3d441310cd50579b4cde006875a2ca2be34c0ed8655556a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:40.531248Z","signature_b64":"H4gpdcc8WWuEg5NAXnhKfsvvb08RdyAuXczcW76uPrPMVPMJ8TN81/dfPsNBMcfP0+G7IZqsZe8nFd93ALtPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"503aaf0eb699d5f33b025f474a1f28d3e6c0e88df10b68e0f3e26cd95e8131bf","last_reissued_at":"2026-07-05T09:55:40.530763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:40.530763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Unraveling and Improving Generalization in World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hang Wang, Junshan Zhang, Qiaoyi Fang, Weiyu Du","submitted_at":"2024-12-31T00:15:43Z","abstract_excerpt":"World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness and generalization capabilities of world models. Thus motivated, we develop a stochastic differential equation formulation by treating the world model learning as a stochastic dynamical system, and characterize the impact of latent representation errors on robustness and generalization, for both cases with zero-drift representation errors and with non-zero-dr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00195","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/2501.00195/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":"2501.00195","created_at":"2026-07-05T09:55:40.530826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00195v1","created_at":"2026-07-05T09:55:40.530826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00195","created_at":"2026-07-05T09:55:40.530826+00:00"},{"alias_kind":"pith_short_12","alias_value":"KA5K6DVWTHK7","created_at":"2026-07-05T09:55:40.530826+00:00"},{"alias_kind":"pith_short_16","alias_value":"KA5K6DVWTHK7GOYC","created_at":"2026-07-05T09:55:40.530826+00:00"},{"alias_kind":"pith_short_8","alias_value":"KA5K6DVW","created_at":"2026-07-05T09:55:40.530826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13092","citing_title":"Certified World Models: Predictability Across Configuration, Horizon, and Resolution","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13092","citing_title":"Certified World Models: Predictability Across Configuration, Horizon, and Resolution","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26782","citing_title":"Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P","json":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P.json","graph_json":"https://pith.science/api/pith-number/KA5K6DVWTHK7GOYCL5DUUHZI2P/graph.json","events_json":"https://pith.science/api/pith-number/KA5K6DVWTHK7GOYCL5DUUHZI2P/events.json","paper":"https://pith.science/paper/KA5K6DVW"},"agent_actions":{"view_html":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P","download_json":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P.json","view_paper":"https://pith.science/paper/KA5K6DVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00195&json=true","fetch_graph":"https://pith.science/api/pith-number/KA5K6DVWTHK7GOYCL5DUUHZI2P/graph.json","fetch_events":"https://pith.science/api/pith-number/KA5K6DVWTHK7GOYCL5DUUHZI2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P/action/storage_attestation","attest_author":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P/action/author_attestation","sign_citation":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P/action/citation_signature","submit_replication":"https://pith.science/pith/KA5K6DVWTHK7GOYCL5DUUHZI2P/action/replication_record"}},"created_at":"2026-07-05T09:55:40.530826+00:00","updated_at":"2026-07-05T09:55:40.530826+00:00"}