{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OA7KLRV4HOEZ3NMINSQB2WBOSX","short_pith_number":"pith:OA7KLRV4","canonical_record":{"source":{"id":"2603.19312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T19:48:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c996afe7bd20ae820ffebacb3d8545c079f16c9dbec5cd86e4964808eaa7e042","abstract_canon_sha256":"6a9f8b9150e3eed0763657a4c826c7ce16de4fc43189b9aea2b3d38f9c9389c8"},"schema_version":"1.0"},"canonical_sha256":"703ea5c6bc3b899db5886ca01d582e95d47de7674dcd3215a243ba77cc8114f7","source":{"kind":"arxiv","id":"2603.19312","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19312","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19312v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19312","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"OA7KLRV4HOEZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OA7KLRV4HOEZ3NMI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OA7KLRV4","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OA7KLRV4HOEZ3NMINSQB2WBOSX","target":"record","payload":{"canonical_record":{"source":{"id":"2603.19312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T19:48:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c996afe7bd20ae820ffebacb3d8545c079f16c9dbec5cd86e4964808eaa7e042","abstract_canon_sha256":"6a9f8b9150e3eed0763657a4c826c7ce16de4fc43189b9aea2b3d38f9c9389c8"},"schema_version":"1.0"},"canonical_sha256":"703ea5c6bc3b899db5886ca01d582e95d47de7674dcd3215a243ba77cc8114f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.585343Z","signature_b64":"i6dVz7U7s1aHVxYy9CB96k8DS/Kj2hz9pEZmae8NSK/spMf2GLaFweu1LzWHU/kL2puPChTcDEOPcCbLCMZ1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"703ea5c6bc3b899db5886ca01d582e95d47de7674dcd3215a243ba77cc8114f7","last_reissued_at":"2026-05-17T23:38:53.584673Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.584673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.19312","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZqdHZs6lAqeGHw2S3tovlh8/FR3YLwMsJ/ooOq6CFtI2SC7wKDddYFORYPFFaHsPve8DUGrnI8Ab3aIXX3DLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:00:49.654125Z"},"content_sha256":"32be6f75c53d360c44743b9449bf7226522a446f68fdc7e69cbf37ae72e189c0","schema_version":"1.0","event_id":"sha256:32be6f75c53d360c44743b9449bf7226522a446f68fdc7e69cbf37ae72e189c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OA7KLRV4HOEZ3NMINSQB2WBOSX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LeWorldModel trains the first stable end-to-end JEPA from raw pixels using only two loss terms.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Damien Scieur, Lucas Maes, Quentin Le Lidec, Randall Balestriero, Yann LeCun","submitted_at":"2026-03-13T19:48:14Z","abstract_excerpt":"Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision to avoid representation collapse. In this work, we introduce LeWorldModel (LeWM), the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a regularizer enforcing Gaussian-distributed latent embeddings. This reduces tunable loss hyperparameters from s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LeWM is the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a regularizer enforcing Gaussian-distributed latent embeddings, reducing tunable loss hyperparameters from six to one.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Gaussian regularizer alone is sufficient to prevent representation collapse across diverse 2D and 3D control tasks without any auxiliary supervision or pre-trained encoders.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LeWorldModel trains the first stable end-to-end JEPA from raw pixels using only two loss terms.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e893dc285675daa050d70f68e802f6128c4f622eb21072acfc2ffbfad5d01c5a"},"source":{"id":"2603.19312","kind":"arxiv","version":2},"verdict":{"id":"0032a5ee-32be-4bf5-a7c6-5e61edf10d97","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T04:03:29.162452Z","strongest_claim":"LeWM is the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a regularizer enforcing Gaussian-distributed latent embeddings, reducing tunable loss hyperparameters from six to one.","one_line_summary":"LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Gaussian regularizer alone is sufficient to prevent representation collapse across diverse 2D and 3D control tasks without any auxiliary supervision or pre-trained encoders.","pith_extraction_headline":"LeWorldModel trains the first stable end-to-end JEPA from raw pixels using only two loss terms."},"references":{"count":57,"sample":[{"doi":"","year":2016,"title":"End-to-end training of deep visuomotor policies.Journal of Machine Learning Research, 17(39):1–40, 2016","work_id":"a556dd56-01e4-4727-a65b-696c8a91ddfb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"World Models","work_id":"07227eee-8445-4c98-bce4-c6a6fd5ed907","ref_index":2,"cited_arxiv_id":"1803.10122","is_internal_anchor":true},{"doi":"","year":2023,"title":"Transformers are sample-efficient world models","work_id":"b39e8f37-9056-4866-a159-dacf3389c224","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Training Agents Inside of Scalable World Models","work_id":"f0464a07-aaee-486f-a0b1-a4bce0bbc3e4","ref_index":4,"cited_arxiv_id":"2509.24527","is_internal_anchor":true},{"doi":"","year":2022,"title":"A path towards autonomous machine intelligence version 0.9","work_id":"be31d909-e137-4d1d-ac0a-d54910a75946","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":57,"snapshot_sha256":"b7cdc6d899ac61f44d8afa22af899cfd96657609a030a6b451fadd754fcfd549","internal_anchors":13},"formal_canon":{"evidence_count":3,"snapshot_sha256":"478ca22640ab1adaea918b9964ea55e158037c87adcfd2bf41c5e988034a4937"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0032a5ee-32be-4bf5-a7c6-5e61edf10d97"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TqRo4Ff1l0mBAN2ojQbo9xvJx3Uek965qwKuyWPjL60/E/dwRtfRzb8jg59oZA8+ZuAVZ0hM1UBJktPwxN9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:00:49.655184Z"},"content_sha256":"fe621797a34940319fac5678613a4d4cee7ac1b5590659c959378d2e01fbb087","schema_version":"1.0","event_id":"sha256:fe621797a34940319fac5678613a4d4cee7ac1b5590659c959378d2e01fbb087"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX/bundle.json","state_url":"https://pith.science/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T15:00:49Z","links":{"resolver":"https://pith.science/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX","bundle":"https://pith.science/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX/bundle.json","state":"https://pith.science/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OA7KLRV4HOEZ3NMINSQB2WBOSX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OA7KLRV4HOEZ3NMINSQB2WBOSX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6a9f8b9150e3eed0763657a4c826c7ce16de4fc43189b9aea2b3d38f9c9389c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T19:48:14Z","title_canon_sha256":"c996afe7bd20ae820ffebacb3d8545c079f16c9dbec5cd86e4964808eaa7e042"},"schema_version":"1.0","source":{"id":"2603.19312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19312","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19312v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19312","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"OA7KLRV4HOEZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OA7KLRV4HOEZ3NMI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OA7KLRV4","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fe621797a34940319fac5678613a4d4cee7ac1b5590659c959378d2e01fbb087","target":"graph","created_at":"2026-05-17T23:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"LeWM is the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a regularizer enforcing Gaussian-distributed latent embeddings, reducing tunable loss hyperparameters from six to one."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Gaussian regularizer alone is sufficient to prevent representation collapse across diverse 2D and 3D control tasks without any auxiliary supervision or pre-trained encoders."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LeWorldModel trains the first stable end-to-end JEPA from raw pixels using only two loss terms."}],"snapshot_sha256":"e893dc285675daa050d70f68e802f6128c4f622eb21072acfc2ffbfad5d01c5a"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"478ca22640ab1adaea918b9964ea55e158037c87adcfd2bf41c5e988034a4937"},"paper":{"abstract_excerpt":"Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision to avoid representation collapse. In this work, we introduce LeWorldModel (LeWM), the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a regularizer enforcing Gaussian-distributed latent embeddings. This reduces tunable loss hyperparameters from s","authors_text":"Damien Scieur, Lucas Maes, Quentin Le Lidec, Randall Balestriero, Yann LeCun","cross_cats":["cs.AI"],"headline":"LeWorldModel trains the first stable end-to-end JEPA from raw pixels using only two loss terms.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T19:48:14Z","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels"},"references":{"count":57,"internal_anchors":13,"resolved_work":57,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"End-to-end training of deep visuomotor policies.Journal of Machine Learning Research, 17(39):1–40, 2016","work_id":"a556dd56-01e4-4727-a65b-696c8a91ddfb","year":2016},{"cited_arxiv_id":"1803.10122","doi":"","is_internal_anchor":true,"ref_index":2,"title":"World Models","work_id":"07227eee-8445-4c98-bce4-c6a6fd5ed907","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Transformers are sample-efficient world models","work_id":"b39e8f37-9056-4866-a159-dacf3389c224","year":2023},{"cited_arxiv_id":"2509.24527","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Training Agents Inside of Scalable World Models","work_id":"f0464a07-aaee-486f-a0b1-a4bce0bbc3e4","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"A path towards autonomous machine intelligence version 0.9","work_id":"be31d909-e137-4d1d-ac0a-d54910a75946","year":2022}],"snapshot_sha256":"b7cdc6d899ac61f44d8afa22af899cfd96657609a030a6b451fadd754fcfd549"},"source":{"id":"2603.19312","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T04:03:29.162452Z","id":"0032a5ee-32be-4bf5-a7c6-5e61edf10d97","model_set":{"reader":"grok-4.3"},"one_line_summary":"LeWM is the first end-to-end trainable JEPA from pixels that uses only two loss terms for stable training and fast planning on 2D/3D control tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LeWorldModel trains the first stable end-to-end JEPA from raw pixels using only two loss terms.","strongest_claim":"LeWM is the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-embedding prediction loss and a regularizer enforcing Gaussian-distributed latent embeddings, reducing tunable loss hyperparameters from six to one.","weakest_assumption":"That the Gaussian regularizer alone is sufficient to prevent representation collapse across diverse 2D and 3D control tasks without any auxiliary supervision or pre-trained encoders."}},"verdict_id":"0032a5ee-32be-4bf5-a7c6-5e61edf10d97"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:32be6f75c53d360c44743b9449bf7226522a446f68fdc7e69cbf37ae72e189c0","target":"record","created_at":"2026-05-17T23:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6a9f8b9150e3eed0763657a4c826c7ce16de4fc43189b9aea2b3d38f9c9389c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-13T19:48:14Z","title_canon_sha256":"c996afe7bd20ae820ffebacb3d8545c079f16c9dbec5cd86e4964808eaa7e042"},"schema_version":"1.0","source":{"id":"2603.19312","kind":"arxiv","version":2}},"canonical_sha256":"703ea5c6bc3b899db5886ca01d582e95d47de7674dcd3215a243ba77cc8114f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"703ea5c6bc3b899db5886ca01d582e95d47de7674dcd3215a243ba77cc8114f7","first_computed_at":"2026-05-17T23:38:53.584673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.584673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i6dVz7U7s1aHVxYy9CB96k8DS/Kj2hz9pEZmae8NSK/spMf2GLaFweu1LzWHU/kL2puPChTcDEOPcCbLCMZ1DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.585343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.19312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32be6f75c53d360c44743b9449bf7226522a446f68fdc7e69cbf37ae72e189c0","sha256:fe621797a34940319fac5678613a4d4cee7ac1b5590659c959378d2e01fbb087"],"state_sha256":"88bd614eebf2ed9b8bb7f072d9678489300276d984cfacb8c3cfeb86b9285380"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k55BgZfMpG8MBKR9ERi5MUxuArJ5tBd8yAIt/KOs2dojNuxrA9hnkF8vTb7Y14NoOisvN/muhBkmGh7+xGzfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T15:00:49.660104Z","bundle_sha256":"fc700da5ab0b6234622dd55755cdb04c96e770dd151b8b3dce2f907971a7cf70"}}