{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOY5FLSKXYWWXIV7Q3FLL4ZTUA","short_pith_number":"pith:XOY5FLSK","schema_version":"1.0","canonical_sha256":"bbb1d2ae4abe2d6ba2bf86cab5f333a03b11e12f66bbee3ffc165bbd82c594b0","source":{"kind":"arxiv","id":"2405.12399","version":2},"attestation_state":"computed","paper":{"title":"Diffusion for World Modeling: Visual Details Matter in Atari","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adam Jelley, Amos Storkey, Anssi Kanervisto, Eloi Alonso, Fran\\c{c}ois Fleuret, Tim Pearce, Vincent Micheli","submitted_at":"2024-05-20T22:51:05Z","abstract_excerpt":"World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequences of discrete latent variables to model environment dynamics. However, this compression into a compact discrete representation may ignore visual details that are important for reinforcement learning. Concurrently, diffusion models have become a dominant approach for image generation, challenging well-established methods modeling discrete latents. Motivated by this paradigm shift, we introduce DIAMOND (DIffusion As a "},"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":"2405.12399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-20T22:51:05Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"d00cae06bf27bb47eca734da77f151b7d59deb338b5a747087e638b17fbc7e4a","abstract_canon_sha256":"8517d900eef8eaea8977bf0de55de725528298e103a795a7300af97e815b78e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:30.926130Z","signature_b64":"CXF31Gi7xLm/1c7OObPPkVDBdembRxHiTds6AyDeVWUw3Pu8NB4tGUTBZc8YPha6ZIaVuDVsGqg6170uvrPzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbb1d2ae4abe2d6ba2bf86cab5f333a03b11e12f66bbee3ffc165bbd82c594b0","last_reissued_at":"2026-07-05T09:28:30.925634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:30.925634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion for World Modeling: Visual Details Matter in Atari","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Adam Jelley, Amos Storkey, Anssi Kanervisto, Eloi Alonso, Fran\\c{c}ois Fleuret, Tim Pearce, Vincent Micheli","submitted_at":"2024-05-20T22:51:05Z","abstract_excerpt":"World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequences of discrete latent variables to model environment dynamics. However, this compression into a compact discrete representation may ignore visual details that are important for reinforcement learning. Concurrently, diffusion models have become a dominant approach for image generation, challenging well-established methods modeling discrete latents. Motivated by this paradigm shift, we introduce DIAMOND (DIffusion As a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12399","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/2405.12399/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":"2405.12399","created_at":"2026-07-05T09:28:30.925692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12399v2","created_at":"2026-07-05T09:28:30.925692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12399","created_at":"2026-07-05T09:28:30.925692+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOY5FLSKXYWW","created_at":"2026-07-05T09:28:30.925692+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOY5FLSKXYWWXIV7","created_at":"2026-07-05T09:28:30.925692+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOY5FLSK","created_at":"2026-07-05T09:28:30.925692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12987","citing_title":"Diffusion Transformer World-Action Model for AV Scene Prediction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04130","citing_title":"CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02586","citing_title":"Fewer, Better Frames: A Compute-Normalized Proof of Concept for Coherence-First World-Model Rendering with Model-Guided FSR4 Frame Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29360","citing_title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11537","citing_title":"Simulus: Combining Improvements in Sample-Efficient World Model Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19538","citing_title":"DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":297,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08268","citing_title":"Insider Attacks in Multi-Agent LLM Consensus Systems","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA","json":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA.json","graph_json":"https://pith.science/api/pith-number/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/graph.json","events_json":"https://pith.science/api/pith-number/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/events.json","paper":"https://pith.science/paper/XOY5FLSK"},"agent_actions":{"view_html":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA","download_json":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA.json","view_paper":"https://pith.science/paper/XOY5FLSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12399&json=true","fetch_graph":"https://pith.science/api/pith-number/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/graph.json","fetch_events":"https://pith.science/api/pith-number/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/action/storage_attestation","attest_author":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/action/author_attestation","sign_citation":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/action/citation_signature","submit_replication":"https://pith.science/pith/XOY5FLSKXYWWXIV7Q3FLL4ZTUA/action/replication_record"}},"created_at":"2026-07-05T09:28:30.925692+00:00","updated_at":"2026-07-05T09:28:30.925692+00:00"}