{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3N2KLXLFOTPOS7SYX3SZL24ZHQ","short_pith_number":"pith:3N2KLXLF","schema_version":"1.0","canonical_sha256":"db74a5dd6574dee97e58bee595eb993c39e2ed4e21ba4c9b94e80ba6c0aa8059","source":{"kind":"arxiv","id":"2409.06445","version":2},"attestation_state":"computed","paper":{"title":"Learning Generative Interactive Environments By Trained Agent Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Danda Paudel, Luc Van Gool, Naser Kazemi, Nedko Savov","submitted_at":"2024-09-10T12:00:40Z","abstract_excerpt":"World models are increasingly pivotal in interpreting and simulating the rules and actions of complex environments. Genie, a recent model, excels at learning from visually diverse environments but relies on costly human-collected data. We observe that their alternative method of using random agents is too limited to explore the environment. We propose to improve the model by employing reinforcement learning based agents for data generation. This approach produces diverse datasets that enhance the model's ability to adapt and perform well across various scenarios and realistic actions within th"},"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":"2409.06445","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-10T12:00:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3bb691436d5f0bc20d30d7e3205f47ebbb1502128a9335260824247768e4a2be","abstract_canon_sha256":"7babb7321f0053058ef8e8d6cf608e65bd0503d0e57fc2aa98651cd3e02b42eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:21.690250Z","signature_b64":"g71BgrA5aVx3Ya6lYnvS+LFByjlkv2AyUfRucZLkgF61Ex0dTRa0xjrVV/ieGd+KqeHaP+qmpI5DqG8ChaVQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db74a5dd6574dee97e58bee595eb993c39e2ed4e21ba4c9b94e80ba6c0aa8059","last_reissued_at":"2026-07-05T09:22:21.689745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:21.689745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Generative Interactive Environments By Trained Agent Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Danda Paudel, Luc Van Gool, Naser Kazemi, Nedko Savov","submitted_at":"2024-09-10T12:00:40Z","abstract_excerpt":"World models are increasingly pivotal in interpreting and simulating the rules and actions of complex environments. Genie, a recent model, excels at learning from visually diverse environments but relies on costly human-collected data. We observe that their alternative method of using random agents is too limited to explore the environment. We propose to improve the model by employing reinforcement learning based agents for data generation. This approach produces diverse datasets that enhance the model's ability to adapt and perform well across various scenarios and realistic actions within th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06445","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/2409.06445/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":"2409.06445","created_at":"2026-07-05T09:22:21.689812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06445v2","created_at":"2026-07-05T09:22:21.689812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06445","created_at":"2026-07-05T09:22:21.689812+00:00"},{"alias_kind":"pith_short_12","alias_value":"3N2KLXLFOTPO","created_at":"2026-07-05T09:22:21.689812+00:00"},{"alias_kind":"pith_short_16","alias_value":"3N2KLXLFOTPOS7SY","created_at":"2026-07-05T09:22:21.689812+00:00"},{"alias_kind":"pith_short_8","alias_value":"3N2KLXLF","created_at":"2026-07-05T09:22:21.689812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.21853","citing_title":"A Survey of Interactive Generative Video","ref_index":134,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ","json":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ.json","graph_json":"https://pith.science/api/pith-number/3N2KLXLFOTPOS7SYX3SZL24ZHQ/graph.json","events_json":"https://pith.science/api/pith-number/3N2KLXLFOTPOS7SYX3SZL24ZHQ/events.json","paper":"https://pith.science/paper/3N2KLXLF"},"agent_actions":{"view_html":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ","download_json":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ.json","view_paper":"https://pith.science/paper/3N2KLXLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06445&json=true","fetch_graph":"https://pith.science/api/pith-number/3N2KLXLFOTPOS7SYX3SZL24ZHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3N2KLXLFOTPOS7SYX3SZL24ZHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ/action/storage_attestation","attest_author":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ/action/author_attestation","sign_citation":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ/action/citation_signature","submit_replication":"https://pith.science/pith/3N2KLXLFOTPOS7SYX3SZL24ZHQ/action/replication_record"}},"created_at":"2026-07-05T09:22:21.689812+00:00","updated_at":"2026-07-05T09:22:21.689812+00:00"}