{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D4FDP6BITI57OCVSULEREV6GWQ","short_pith_number":"pith:D4FDP6BI","canonical_record":{"source":{"id":"2405.17418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"7d94128136195e55f43ce625d9717e957ac92db02d38afade04c0ce082ca9be5","abstract_canon_sha256":"6964983d1663a973717bf4739a0f61b79665b2f2ebf6bf2c0c02262d290638cb"},"schema_version":"1.0"},"canonical_sha256":"1f0a37f8289a3bf70ab2a2c91257c6b429c651ac2f90a299b0fe44efcf86ce25","source":{"kind":"arxiv","id":"2405.17418","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17418","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17418v2","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17418","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"D4FDP6BITI57","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"D4FDP6BITI57OCVS","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"D4FDP6BI","created_at":"2026-07-05T10:34:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D4FDP6BITI57OCVSULEREV6GWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"7d94128136195e55f43ce625d9717e957ac92db02d38afade04c0ce082ca9be5","abstract_canon_sha256":"6964983d1663a973717bf4739a0f61b79665b2f2ebf6bf2c0c02262d290638cb"},"schema_version":"1.0"},"canonical_sha256":"1f0a37f8289a3bf70ab2a2c91257c6b429c651ac2f90a299b0fe44efcf86ce25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:07.916969Z","signature_b64":"6sDeas0Cp8mhPqjmQxIGQBV58dRdHz2AB22kyaxDucV8gKfSofZ1ySnLJ3UGcEZw/tgHj4zzwLrJAkhuDXZoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f0a37f8289a3bf70ab2a2c91257c6b429c651ac2f90a299b0fe44efcf86ce25","last_reissued_at":"2026-07-05T10:34:07.916404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:07.916404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17418","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":"2026-07-05T10:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eaQ0l2xyQpSXVLtKrdoq+X/904g7Yqk9raGRWO01SgBtOtdjQ5TCOxQ5ay7UlmppK9YToCg4hJC6mPPoUsecDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:27:07.054261Z"},"content_sha256":"5db5e3768c25e087c6bf4377abd3b80439100bf4c2513a947d0b3f3f491b920e","schema_version":"1.0","event_id":"sha256:5db5e3768c25e087c6bf4377abd3b80439100bf4c2513a947d0b3f3f491b920e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D4FDP6BITI57OCVSULEREV6GWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxuan Li, Chuyan Xiong, Guanqun Wang, Jiaming Liu, Jiaxin Ge, Kaichen Zhou, Liang Heng, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Xiaoqi Li","submitted_at":"2024-05-27T17:58:48Z","abstract_excerpt":"Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal information and predict SE(3) poses. While VLAs have shown promising progress, they may suffer from failures when faced with novel and complex tasks. To emulate human-like reasoning for more robust manipulation, we propose the self-corrected (SC-)VLA framework, which integrates fast system for directly predicting actions and slow system for reflecting on failed actions within a single VLA policy. For the fast system, we inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17418","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/2405.17418/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":"2026-07-05T10:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x21Q0l8e79DMDZSHvKdi1RNGZ3TYzcDY6n5qJgYAYCzxk6uZdVdqa5vY6Ud6y8vmCq1e7l31wJHhvFOzs2/xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:27:07.054802Z"},"content_sha256":"90ff49d770b25d3144411191e6dfb808f566c230f75393b5cd20a22792e617a9","schema_version":"1.0","event_id":"sha256:90ff49d770b25d3144411191e6dfb808f566c230f75393b5cd20a22792e617a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4FDP6BITI57OCVSULEREV6GWQ/bundle.json","state_url":"https://pith.science/pith/D4FDP6BITI57OCVSULEREV6GWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4FDP6BITI57OCVSULEREV6GWQ/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":"2026-08-04T21:27:07Z","links":{"resolver":"https://pith.science/pith/D4FDP6BITI57OCVSULEREV6GWQ","bundle":"https://pith.science/pith/D4FDP6BITI57OCVSULEREV6GWQ/bundle.json","state":"https://pith.science/pith/D4FDP6BITI57OCVSULEREV6GWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4FDP6BITI57OCVSULEREV6GWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D4FDP6BITI57OCVSULEREV6GWQ","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":"6964983d1663a973717bf4739a0f61b79665b2f2ebf6bf2c0c02262d290638cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:58:48Z","title_canon_sha256":"7d94128136195e55f43ce625d9717e957ac92db02d38afade04c0ce082ca9be5"},"schema_version":"1.0","source":{"id":"2405.17418","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17418","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17418v2","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17418","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"D4FDP6BITI57","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"D4FDP6BITI57OCVS","created_at":"2026-07-05T10:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"D4FDP6BI","created_at":"2026-07-05T10:34:07Z"}],"graph_snapshots":[{"event_id":"sha256:90ff49d770b25d3144411191e6dfb808f566c230f75393b5cd20a22792e617a9","target":"graph","created_at":"2026-07-05T10:34:07Z","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/2405.17418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal information and predict SE(3) poses. While VLAs have shown promising progress, they may suffer from failures when faced with novel and complex tasks. To emulate human-like reasoning for more robust manipulation, we propose the self-corrected (SC-)VLA framework, which integrates fast system for directly predicting actions and slow system for reflecting on failed actions within a single VLA policy. For the fast system, we inc","authors_text":"Chenxuan Li, Chuyan Xiong, Guanqun Wang, Jiaming Liu, Jiaxin Ge, Kaichen Zhou, Liang Heng, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Xiaoqi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:58:48Z","title":"A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17418","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":"sha256:5db5e3768c25e087c6bf4377abd3b80439100bf4c2513a947d0b3f3f491b920e","target":"record","created_at":"2026-07-05T10:34:07Z","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":"6964983d1663a973717bf4739a0f61b79665b2f2ebf6bf2c0c02262d290638cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T17:58:48Z","title_canon_sha256":"7d94128136195e55f43ce625d9717e957ac92db02d38afade04c0ce082ca9be5"},"schema_version":"1.0","source":{"id":"2405.17418","kind":"arxiv","version":2}},"canonical_sha256":"1f0a37f8289a3bf70ab2a2c91257c6b429c651ac2f90a299b0fe44efcf86ce25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f0a37f8289a3bf70ab2a2c91257c6b429c651ac2f90a299b0fe44efcf86ce25","first_computed_at":"2026-07-05T10:34:07.916404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:07.916404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6sDeas0Cp8mhPqjmQxIGQBV58dRdHz2AB22kyaxDucV8gKfSofZ1ySnLJ3UGcEZw/tgHj4zzwLrJAkhuDXZoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:07.916969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17418","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5db5e3768c25e087c6bf4377abd3b80439100bf4c2513a947d0b3f3f491b920e","sha256:90ff49d770b25d3144411191e6dfb808f566c230f75393b5cd20a22792e617a9"],"state_sha256":"104ddea6a75cf01167caa709080cf3b017d1ca482ce37616123ce26fa8b617d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2NuGeesK8qYs4psFEDic5NfXY9zEBSOpTbeCB+/Qhbt8lWNv6WaUSS9Z1wmv4pWCE2dt4cg9g3yl/p3Yr1zBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:27:07.060174Z","bundle_sha256":"fe093edd4034dab06401709a19a9ceeee6e408ac8a361301b4977c80b6fb6ad4"}}