{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OM56IOUH62NL3HY2ZWRHBJTW3K","short_pith_number":"pith:OM56IOUH","schema_version":"1.0","canonical_sha256":"733be43a87f69abd9f1acda270a676dab69a0250fcd97b3ee240427860acce78","source":{"kind":"arxiv","id":"2503.04416","version":2},"attestation_state":"computed","paper":{"title":"Learning Transformer-based World Models with Contrastive Predictive Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Maxime Burchi, Radu Timofte","submitted_at":"2025-03-06T13:18:37Z","abstract_excerpt":"The DreamerV3 algorithm recently obtained remarkable performance across diverse environment domains by learning an accurate world model based on Recurrent Neural Networks (RNNs). Following the success of model-based reinforcement learning algorithms and the rapid adoption of the Transformer architecture for its superior training efficiency and favorable scaling properties, recent works such as STORM have proposed replacing RNN-based world models with Transformer-based world models using masked self-attention. However, despite the improved training efficiency of these methods, their impact on p"},"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":"2503.04416","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T13:18:37Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"51fab91f271e9ca2a45e83393b2f101caa7741fb2e8a7df17ad8034c094e83c4","abstract_canon_sha256":"e60e4ca82496ac33e5348f8512d5fb2fc365c6abce12d5ab35ab99af65b23f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:09.679799Z","signature_b64":"fF3JvCASsjMXxuulecknIDHTlsJ8IkYaweQUFEoUvdAdmS4iYv8AIhGQ19SmQdTBVMP2In4VSzokZ7vOkAuoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"733be43a87f69abd9f1acda270a676dab69a0250fcd97b3ee240427860acce78","last_reissued_at":"2026-07-05T11:09:09.679361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:09.679361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Transformer-based World Models with Contrastive Predictive Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Maxime Burchi, Radu Timofte","submitted_at":"2025-03-06T13:18:37Z","abstract_excerpt":"The DreamerV3 algorithm recently obtained remarkable performance across diverse environment domains by learning an accurate world model based on Recurrent Neural Networks (RNNs). Following the success of model-based reinforcement learning algorithms and the rapid adoption of the Transformer architecture for its superior training efficiency and favorable scaling properties, recent works such as STORM have proposed replacing RNN-based world models with Transformer-based world models using masked self-attention. However, despite the improved training efficiency of these methods, their impact on p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04416","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/2503.04416/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":"2503.04416","created_at":"2026-07-05T11:09:09.679418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04416v2","created_at":"2026-07-05T11:09:09.679418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04416","created_at":"2026-07-05T11:09:09.679418+00:00"},{"alias_kind":"pith_short_12","alias_value":"OM56IOUH62NL","created_at":"2026-07-05T11:09:09.679418+00:00"},{"alias_kind":"pith_short_16","alias_value":"OM56IOUH62NL3HY2","created_at":"2026-07-05T11:09:09.679418+00:00"},{"alias_kind":"pith_short_8","alias_value":"OM56IOUH","created_at":"2026-07-05T11:09:09.679418+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00780","citing_title":"Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07083","citing_title":"Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13013","citing_title":"JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K","json":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K.json","graph_json":"https://pith.science/api/pith-number/OM56IOUH62NL3HY2ZWRHBJTW3K/graph.json","events_json":"https://pith.science/api/pith-number/OM56IOUH62NL3HY2ZWRHBJTW3K/events.json","paper":"https://pith.science/paper/OM56IOUH"},"agent_actions":{"view_html":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K","download_json":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K.json","view_paper":"https://pith.science/paper/OM56IOUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04416&json=true","fetch_graph":"https://pith.science/api/pith-number/OM56IOUH62NL3HY2ZWRHBJTW3K/graph.json","fetch_events":"https://pith.science/api/pith-number/OM56IOUH62NL3HY2ZWRHBJTW3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K/action/storage_attestation","attest_author":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K/action/author_attestation","sign_citation":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K/action/citation_signature","submit_replication":"https://pith.science/pith/OM56IOUH62NL3HY2ZWRHBJTW3K/action/replication_record"}},"created_at":"2026-07-05T11:09:09.679418+00:00","updated_at":"2026-07-05T11:09:09.679418+00:00"}