{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PFUQQ4JETGZE2EYF6CWT5QD7DM","short_pith_number":"pith:PFUQQ4JE","canonical_record":{"source":{"id":"2503.19757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-25T15:19:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4c1b39aebdda1a75a8bfd8658fd6cde20937c267d8ce434aacff2ead47dd8da3","abstract_canon_sha256":"9565dc7af7367b2a63e02ad1cf89a2249b9d5b7c87e6865f7065d2200ca98d52"},"schema_version":"1.0"},"canonical_sha256":"796908712499b24d1305f0ad3ec07f1b27010de045c2850f0d9f022252cafd5f","source":{"kind":"arxiv","id":"2503.19757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19757","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19757v2","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19757","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"PFUQQ4JETGZE","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"PFUQQ4JETGZE2EYF","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"PFUQQ4JE","created_at":"2026-07-05T12:06:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PFUQQ4JETGZE2EYF6CWT5QD7DM","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-25T15:19:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4c1b39aebdda1a75a8bfd8658fd6cde20937c267d8ce434aacff2ead47dd8da3","abstract_canon_sha256":"9565dc7af7367b2a63e02ad1cf89a2249b9d5b7c87e6865f7065d2200ca98d52"},"schema_version":"1.0"},"canonical_sha256":"796908712499b24d1305f0ad3ec07f1b27010de045c2850f0d9f022252cafd5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:08.333874Z","signature_b64":"oAQejFZ4JxrNv6kkT4y4/VB2TW/w2iiK3WR8TCOls5JGE/GqgrLFaX/GXpJ0b1V5zSX+ELNNeohuoIO5o6bRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796908712499b24d1305f0ad3ec07f1b27010de045c2850f0d9f022252cafd5f","last_reissued_at":"2026-07-05T12:06:08.333354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:08.333354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19757","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":"2026-07-05T12:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bvrzULdVSpGK3EMecTDVUav1oL/U6cU5H8+UISEH+aupBVVCYsL5QwNBZRxY0LJc+eHUqQsvkOGeng8VBvi4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:48:41.259254Z"},"content_sha256":"bd766943bddbe7dcae7973226d0411a4de326946ff78d98c76cb45ee76f10f7b","schema_version":"1.0","event_id":"sha256:bd766943bddbe7dcae7973226d0411a4de326946ff78d98c76cb45ee76f10f7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PFUQQ4JETGZE2EYF6CWT5QD7DM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengyang Zhao, Haonan Duan, Hengjun Pu, Jifeng Dai, Ronglei Tong, Tianyi Zhang, Xizhou Zhu, Yuntao Chen, Yu Qiao, Yuwen Xiong, Zhi Hou","submitted_at":"2025-03-25T15:19:56Z","abstract_excerpt":"While recent vision-language-action models trained on diverse robot datasets exhibit promising generalization capabilities with limited in-domain data, their reliance on compact action heads to predict discretized or continuous actions constrains adaptability to heterogeneous action spaces. We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences through a unified multimodal diffusion process. Departing from prior methods that condition denoising on fused embeddings via shallow networks, Dita employs in-context conditioning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19757","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/2503.19757/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":"2026-07-05T12:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y+HR4zb9wuhi59IZ7KbcKD1OFQyI5JXQgu3IFTL8J7RKXeMMc/8++amKF5Tc19wnoxtZSGErbaj7j1wXSDwHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:48:41.260403Z"},"content_sha256":"d1d317976f12f53771681326f24b3e8fdf894d20fe7654d5eb89fc314b0f4634","schema_version":"1.0","event_id":"sha256:d1d317976f12f53771681326f24b3e8fdf894d20fe7654d5eb89fc314b0f4634"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM/bundle.json","state_url":"https://pith.science/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM/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":"2026-08-07T15:48:41Z","links":{"resolver":"https://pith.science/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM","bundle":"https://pith.science/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM/bundle.json","state":"https://pith.science/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFUQQ4JETGZE2EYF6CWT5QD7DM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PFUQQ4JETGZE2EYF6CWT5QD7DM","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":"9565dc7af7367b2a63e02ad1cf89a2249b9d5b7c87e6865f7065d2200ca98d52","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-25T15:19:56Z","title_canon_sha256":"4c1b39aebdda1a75a8bfd8658fd6cde20937c267d8ce434aacff2ead47dd8da3"},"schema_version":"1.0","source":{"id":"2503.19757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19757","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19757v2","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19757","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"PFUQQ4JETGZE","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"PFUQQ4JETGZE2EYF","created_at":"2026-07-05T12:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"PFUQQ4JE","created_at":"2026-07-05T12:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:d1d317976f12f53771681326f24b3e8fdf894d20fe7654d5eb89fc314b0f4634","target":"graph","created_at":"2026-07-05T12:06:08Z","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/2503.19757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent vision-language-action models trained on diverse robot datasets exhibit promising generalization capabilities with limited in-domain data, their reliance on compact action heads to predict discretized or continuous actions constrains adaptability to heterogeneous action spaces. We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences through a unified multimodal diffusion process. Departing from prior methods that condition denoising on fused embeddings via shallow networks, Dita employs in-context conditioning ","authors_text":"Chengyang Zhao, Haonan Duan, Hengjun Pu, Jifeng Dai, Ronglei Tong, Tianyi Zhang, Xizhou Zhu, Yuntao Chen, Yu Qiao, Yuwen Xiong, Zhi Hou","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-25T15:19:56Z","title":"Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19757","kind":"arxiv","version":2},"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:bd766943bddbe7dcae7973226d0411a4de326946ff78d98c76cb45ee76f10f7b","target":"record","created_at":"2026-07-05T12:06:08Z","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":"9565dc7af7367b2a63e02ad1cf89a2249b9d5b7c87e6865f7065d2200ca98d52","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-25T15:19:56Z","title_canon_sha256":"4c1b39aebdda1a75a8bfd8658fd6cde20937c267d8ce434aacff2ead47dd8da3"},"schema_version":"1.0","source":{"id":"2503.19757","kind":"arxiv","version":2}},"canonical_sha256":"796908712499b24d1305f0ad3ec07f1b27010de045c2850f0d9f022252cafd5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"796908712499b24d1305f0ad3ec07f1b27010de045c2850f0d9f022252cafd5f","first_computed_at":"2026-07-05T12:06:08.333354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:08.333354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oAQejFZ4JxrNv6kkT4y4/VB2TW/w2iiK3WR8TCOls5JGE/GqgrLFaX/GXpJ0b1V5zSX+ELNNeohuoIO5o6bRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:08.333874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd766943bddbe7dcae7973226d0411a4de326946ff78d98c76cb45ee76f10f7b","sha256:d1d317976f12f53771681326f24b3e8fdf894d20fe7654d5eb89fc314b0f4634"],"state_sha256":"2ee579abd90ddb1a610614b320acdd914feab99ace42d40267426e61f8f239a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y/J8jb3ST6/lYTkkSbg7YShCDVrxe5wLtc4Fw94/jbtdwdk4d9wiHljTN3d4FeVDsdc8YRa6SMS4OYoSwsvfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:48:41.329358Z","bundle_sha256":"366589755f1a751e8a32cb32e1686da6873e94a89fffd6aa6843faff213cd4a3"}}