{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AKWEC674N26X5JXFJ5VJLAUKIK","short_pith_number":"pith:AKWEC674","canonical_record":{"source":{"id":"2607.23909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T00:55:10Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6150cf03acd99f47d0ccb2440250eff72bd60e6378ce3add90dc9ff13f5978cf","abstract_canon_sha256":"db2744f714d18ab12422a9fa3959f7f99a7b699fa877fddee3ef543be26099c6"},"schema_version":"1.0"},"canonical_sha256":"02ac417bfc6ebd7ea6e54f6a95828a429a6df67ab66a40e99886591eb45084e4","source":{"kind":"arxiv","id":"2607.23909","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23909","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23909v1","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23909","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_12","alias_value":"AKWEC674N26X","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_16","alias_value":"AKWEC674N26X5JXF","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_8","alias_value":"AKWEC674","created_at":"2026-07-28T01:23:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AKWEC674N26X5JXFJ5VJLAUKIK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T00:55:10Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6150cf03acd99f47d0ccb2440250eff72bd60e6378ce3add90dc9ff13f5978cf","abstract_canon_sha256":"db2744f714d18ab12422a9fa3959f7f99a7b699fa877fddee3ef543be26099c6"},"schema_version":"1.0"},"canonical_sha256":"02ac417bfc6ebd7ea6e54f6a95828a429a6df67ab66a40e99886591eb45084e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:17.317843Z","signature_b64":"FQDu3LXWb4j4C6OaifcH+EX2UWw6RPK3VY4XeTAODzBKuUHKqeu2eVKMoxBXpV0Z5Ozq2tPeDgbD/eP13hViDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02ac417bfc6ebd7ea6e54f6a95828a429a6df67ab66a40e99886591eb45084e4","last_reissued_at":"2026-07-28T01:23:17.316961Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:17.316961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23909","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:23:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7RsKXzAupvfX+eGdAvmX2roBSKIxRGHLvo3yPYXLq11nyH1Zc+APkiQugEnHClFgsOuD9khGSwifEHMWbnWjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:04:56.318359Z"},"content_sha256":"2d914411d126e2de00bed45f34d0cf3c283238f340ef394fa69cb0f572985a74","schema_version":"1.0","event_id":"sha256:2d914411d126e2de00bed45f34d0cf3c283238f340ef394fa69cb0f572985a74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AKWEC674N26X5JXFJ5VJLAUKIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WorldDiT: A Unified Diffusion Architecture for World and Action Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bidhan Roy, Marcos Villagra, R. Gnana Praveen, Sen Wang","submitted_at":"2026-07-27T00:55:10Z","abstract_excerpt":"Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized RGB patch targets from future camera frames. Across four LIBERO simulation suites, WorldDiT lies on the reported Pareto frontier for total model parameters "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23909","kind":"arxiv","version":1},"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/2607.23909/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:23:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uYfsAW3iX9zWhcf4TwU7D7sad9qMaVrJ6pXX5Njc/AmhFSEGzE0lvJecsCW9uEWbbjyEl3lSbMNKCQAkfWtLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:04:56.318869Z"},"content_sha256":"02b8c2ddfc4dd2266b858618d1e2ecbf25692fed52d4208b42aa95503ab6aad6","schema_version":"1.0","event_id":"sha256:02b8c2ddfc4dd2266b858618d1e2ecbf25692fed52d4208b42aa95503ab6aad6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKWEC674N26X5JXFJ5VJLAUKIK/bundle.json","state_url":"https://pith.science/pith/AKWEC674N26X5JXFJ5VJLAUKIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKWEC674N26X5JXFJ5VJLAUKIK/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":"2026-08-20T22:04:56Z","links":{"resolver":"https://pith.science/pith/AKWEC674N26X5JXFJ5VJLAUKIK","bundle":"https://pith.science/pith/AKWEC674N26X5JXFJ5VJLAUKIK/bundle.json","state":"https://pith.science/pith/AKWEC674N26X5JXFJ5VJLAUKIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKWEC674N26X5JXFJ5VJLAUKIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AKWEC674N26X5JXFJ5VJLAUKIK","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":"db2744f714d18ab12422a9fa3959f7f99a7b699fa877fddee3ef543be26099c6","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T00:55:10Z","title_canon_sha256":"6150cf03acd99f47d0ccb2440250eff72bd60e6378ce3add90dc9ff13f5978cf"},"schema_version":"1.0","source":{"id":"2607.23909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23909","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23909v1","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23909","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_12","alias_value":"AKWEC674N26X","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_16","alias_value":"AKWEC674N26X5JXF","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_8","alias_value":"AKWEC674","created_at":"2026-07-28T01:23:17Z"}],"graph_snapshots":[{"event_id":"sha256:02b8c2ddfc4dd2266b858618d1e2ecbf25692fed52d4208b42aa95503ab6aad6","target":"graph","created_at":"2026-07-28T01:23:17Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.23909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized RGB patch targets from future camera frames. Across four LIBERO simulation suites, WorldDiT lies on the reported Pareto frontier for total model parameters ","authors_text":"Bidhan Roy, Marcos Villagra, R. Gnana Praveen, Sen Wang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T00:55:10Z","title":"WorldDiT: A Unified Diffusion Architecture for World and Action Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23909","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2d914411d126e2de00bed45f34d0cf3c283238f340ef394fa69cb0f572985a74","target":"record","created_at":"2026-07-28T01:23:17Z","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":"db2744f714d18ab12422a9fa3959f7f99a7b699fa877fddee3ef543be26099c6","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T00:55:10Z","title_canon_sha256":"6150cf03acd99f47d0ccb2440250eff72bd60e6378ce3add90dc9ff13f5978cf"},"schema_version":"1.0","source":{"id":"2607.23909","kind":"arxiv","version":1}},"canonical_sha256":"02ac417bfc6ebd7ea6e54f6a95828a429a6df67ab66a40e99886591eb45084e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02ac417bfc6ebd7ea6e54f6a95828a429a6df67ab66a40e99886591eb45084e4","first_computed_at":"2026-07-28T01:23:17.316961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:17.316961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FQDu3LXWb4j4C6OaifcH+EX2UWw6RPK3VY4XeTAODzBKuUHKqeu2eVKMoxBXpV0Z5Ozq2tPeDgbD/eP13hViDA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:17.317843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d914411d126e2de00bed45f34d0cf3c283238f340ef394fa69cb0f572985a74","sha256:02b8c2ddfc4dd2266b858618d1e2ecbf25692fed52d4208b42aa95503ab6aad6"],"state_sha256":"364910500823b3a5acf600c4ea3351b97f6a0c04a4b27b4ad8e547c575eaea31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uCC0Q2K0C/eT3cCvJyMt4fy+wBzIV86MNKphg4DIca8HX62xbafGZ6TBT7B4i9/uZXvzmCytmtUyflES64+6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:04:56.322710Z","bundle_sha256":"d67f8fe737e922405b0510e2eba4d55cafd03dca07edd5a6611ed15efcf77f0d"}}