{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SILTR7TUVRKMN5BTJN2NZDV3J3","short_pith_number":"pith:SILTR7TU","canonical_record":{"source":{"id":"2412.03293","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c","abstract_canon_sha256":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68"},"schema_version":"1.0"},"canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","source":{"kind":"arxiv","id":"2412.03293","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03293","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03293v3","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03293","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"SILTR7TUVRKM","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"SILTR7TUVRKMN5BT","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"SILTR7TU","created_at":"2026-07-05T11:15:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SILTR7TUVRKMN5BTJN2NZDV3J3","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03293","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c","abstract_canon_sha256":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68"},"schema_version":"1.0"},"canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:40.888065Z","signature_b64":"r8At97LK4dBK0Es1LGBnZb/dL8zxhUPTQn3ontZzvA0+RugLRQLSj7ceWj6L/bbU9LMuxeC/NnwoJTaCyxYhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","last_reissued_at":"2026-07-05T11:15:40.887499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:40.887499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03293","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnblf9T/QEeql+GJa0t/1paSWnEy9BzL8h2Du49Zf0XkFX/9Oh7Zj2rHMdEIvfBYFdgCybIwrPZPOn8PQ66SDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T01:51:08.076028Z"},"content_sha256":"c485636a8be18d71c3fa8716ffaae36d5d6cd98ac30aa20ddf10787107c7a14e","schema_version":"1.0","event_id":"sha256:c485636a8be18d71c3fa8716ffaae36d5d6cd98ac30aa20ddf10787107c7a14e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SILTR7TUVRKMN5BTJN2NZDV3J3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Chengmeng Li, Feifei Feng, Jinming Li, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Yaxin Peng, Yichen Zhu, Zhibin Tang, Zhongyi Zhou","submitted_at":"2024-12-04T13:11:38Z","abstract_excerpt":"In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the model to reason effectively over the user's query in the context of current observations. Subsequently, a diffusion model is attached to generate robust action outputs. To enhance policy learning through self-reasoning, we introduce a novel reasoning injection module that integrates reasoning phrases directly into the policy learning process. The whole frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03293","kind":"arxiv","version":3},"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/2412.03293/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":"2026-07-05T11:15:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0DPUG11aG5br+r7XAgb0IY6Xo4C8AtoGJ5S8JuC4znBVmECvvA0IDO1k0xwHnBFMyd1M7cL0UF+2MTdOWMxFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T01:51:08.076416Z"},"content_sha256":"a4d50aabbb6a3a15280225f0f6a5002b57fc2665be814ddd7e78d762d1019058","schema_version":"1.0","event_id":"sha256:a4d50aabbb6a3a15280225f0f6a5002b57fc2665be814ddd7e78d762d1019058"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/bundle.json","state_url":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/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":"2026-07-26T01:51:08Z","links":{"resolver":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3","bundle":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/bundle.json","state":"https://pith.science/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SILTR7TUVRKMN5BTJN2NZDV3J3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SILTR7TUVRKMN5BTJN2NZDV3J3","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":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c"},"schema_version":"1.0","source":{"id":"2412.03293","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03293","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03293v3","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03293","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"SILTR7TUVRKM","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"SILTR7TUVRKMN5BT","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"SILTR7TU","created_at":"2026-07-05T11:15:40Z"}],"graph_snapshots":[{"event_id":"sha256:a4d50aabbb6a3a15280225f0f6a5002b57fc2665be814ddd7e78d762d1019058","target":"graph","created_at":"2026-07-05T11:15:40Z","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/2412.03293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the model to reason effectively over the user's query in the context of current observations. Subsequently, a diffusion model is attached to generate robust action outputs. To enhance policy learning through self-reasoning, we introduce a novel reasoning injection module that integrates reasoning phrases directly into the policy learning process. The whole frame","authors_text":"Chaomin Shen, Chengmeng Li, Feifei Feng, Jinming Li, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Yaxin Peng, Yichen Zhu, Zhibin Tang, Zhongyi Zhou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","title":"Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03293","kind":"arxiv","version":3},"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:c485636a8be18d71c3fa8716ffaae36d5d6cd98ac30aa20ddf10787107c7a14e","target":"record","created_at":"2026-07-05T11:15:40Z","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":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c"},"schema_version":"1.0","source":{"id":"2412.03293","kind":"arxiv","version":3}},"canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","first_computed_at":"2026-07-05T11:15:40.887499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:40.887499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8At97LK4dBK0Es1LGBnZb/dL8zxhUPTQn3ontZzvA0+RugLRQLSj7ceWj6L/bbU9LMuxeC/NnwoJTaCyxYhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:40.888065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03293","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c485636a8be18d71c3fa8716ffaae36d5d6cd98ac30aa20ddf10787107c7a14e","sha256:a4d50aabbb6a3a15280225f0f6a5002b57fc2665be814ddd7e78d762d1019058"],"state_sha256":"f1116af6be95e0e6874ef8f027fffe012ca65b85ae3af3b68d522bfb17f7230e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xj72+qL0A8WlVra5A63ogYpLcX95OsKWkPpUPYgJx0jZLozaaUyMU8J3R/cU+F9tf3UCK2bNLpJOYjkKMyoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T01:51:08.078757Z","bundle_sha256":"5c49f8d08be4e2f89ba10026d4d9baafe8448af9cd73f925b09db436fef11a41"}}