{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5HVFWPJKM2I3UTGV62YZGJZR4E","short_pith_number":"pith:5HVFWPJK","schema_version":"1.0","canonical_sha256":"e9ea5b3d2a6691ba4cd5f6b1932731e129a27a8a60aa3889ee8f20c77c270dc8","source":{"kind":"arxiv","id":"2412.03572","version":2},"attestation_state":"computed","paper":{"title":"Navigation World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir Bar, Danny Tran, Gaoyue Zhou, Trevor Darrell, Yann LeCun","submitted_at":"2024-12-04T18:59:45Z","abstract_excerpt":"Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and navigation actions. To capture complex environment dynamics, NWM employs a Conditional Diffusion Transformer (CDiT), trained on a diverse collection of egocentric videos of both human and robotic agents, and scaled up to 1 billion parameters. In familiar environments, NWM can plan navigation trajectories by simulating them and evaluating whether they achieve the desi"},"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":"2412.03572","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:59:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"0ff1a459b106ea5786f884053bfb9d95ea7eca32c5ff2a1fab754ca146f9d4d4","abstract_canon_sha256":"683ec3674b206d5cd232aed711a63db6c6395c06464c4ad3e0b0663444b7fe3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:56.344739Z","signature_b64":"OAC7UMskXLrwKawBn/J+CzVe0e/QW94ou13zstzD8WWlwLYBPfF/g0eOoYkexvXcyR0Z4howlT9cNExYYHUtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ea5b3d2a6691ba4cd5f6b1932731e129a27a8a60aa3889ee8f20c77c270dc8","last_reissued_at":"2026-07-05T10:47:56.344138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:56.344138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigation World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Amir Bar, Danny Tran, Gaoyue Zhou, Trevor Darrell, Yann LeCun","submitted_at":"2024-12-04T18:59:45Z","abstract_excerpt":"Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and navigation actions. To capture complex environment dynamics, NWM employs a Conditional Diffusion Transformer (CDiT), trained on a diverse collection of egocentric videos of both human and robotic agents, and scaled up to 1 billion parameters. In familiar environments, NWM can plan navigation trajectories by simulating them and evaluating whether they achieve the desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03572","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/2412.03572/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":"2412.03572","created_at":"2026-07-05T10:47:56.344199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03572v2","created_at":"2026-07-05T10:47:56.344199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03572","created_at":"2026-07-05T10:47:56.344199+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HVFWPJKM2I3","created_at":"2026-07-05T10:47:56.344199+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HVFWPJKM2I3UTGV","created_at":"2026-07-05T10:47:56.344199+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HVFWPJK","created_at":"2026-07-05T10:47:56.344199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08436","citing_title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21406","citing_title":"Robot Self-Improvement via Human-Video Dynamics Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12603","citing_title":"From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05699","citing_title":"DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04130","citing_title":"CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24152","citing_title":"Neuro-Inspired Inverse Learning for Planning and Control","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18324","citing_title":"Improved Baselines with Representation Autoencoders","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06974","citing_title":"FeudalNav: A Simple Framework for Visual Navigation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19312","citing_title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21539","citing_title":"WorldVLA: Towards Autoregressive Action World Model","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21741","citing_title":"Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E","json":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E.json","graph_json":"https://pith.science/api/pith-number/5HVFWPJKM2I3UTGV62YZGJZR4E/graph.json","events_json":"https://pith.science/api/pith-number/5HVFWPJKM2I3UTGV62YZGJZR4E/events.json","paper":"https://pith.science/paper/5HVFWPJK"},"agent_actions":{"view_html":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E","download_json":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E.json","view_paper":"https://pith.science/paper/5HVFWPJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03572&json=true","fetch_graph":"https://pith.science/api/pith-number/5HVFWPJKM2I3UTGV62YZGJZR4E/graph.json","fetch_events":"https://pith.science/api/pith-number/5HVFWPJKM2I3UTGV62YZGJZR4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E/action/storage_attestation","attest_author":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E/action/author_attestation","sign_citation":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E/action/citation_signature","submit_replication":"https://pith.science/pith/5HVFWPJKM2I3UTGV62YZGJZR4E/action/replication_record"}},"created_at":"2026-07-05T10:47:56.344199+00:00","updated_at":"2026-07-05T10:47:56.344199+00:00"}