{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZLDUZFFATEEIZQCQFOUSHURSK5","short_pith_number":"pith:ZLDUZFFA","schema_version":"1.0","canonical_sha256":"cac74c94a099088cc0502ba923d232577fcd5f7f8b2587d689ca3348ea744893","source":{"kind":"arxiv","id":"2406.11548","version":6},"attestation_state":"computed","paper":{"title":"AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengyu Shen, Chuyan Xiong, Hao Dong, Jeremy Liu, Kaichen Zhou, Ruiping Wang, Xiaoqi Li","submitted_at":"2024-06-17T13:44:53Z","abstract_excerpt":"The ability to reflect on and correct failures is crucial for robotic systems to interact stably with real-life objects.Observing the generalization and reasoning capabilities of Multimodal Large Language Models (MLLMs), previous approaches have aimed to utilize these models to enhance robotic systems accordingly.However, these methods typically focus on high-level planning corrections using an additional MLLM, with limited utilization of failed samples to correct low-level contact poses which is particularly prone to occur during articulated object manipulation.To address this gap, we propose"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.11548","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-17T13:44:53Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c879916d63caecd3bb596fdbf2d7becdfad0a3a2e79062c9f92995b881a2946c","abstract_canon_sha256":"cc2b0721590de69565ab28dd9d2c909a36bf2712a01a430636e830943dbe0c0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:12.554040Z","signature_b64":"zdYhflxISpdAtEyfULn11lr3YjKq/9yn6B5tKN4nCUa8XnUNy25vzUufYbxqZRtBlhqm9pwgDfQN/NXcrf8bAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cac74c94a099088cc0502ba923d232577fcd5f7f8b2587d689ca3348ea744893","last_reissued_at":"2026-07-05T09:36:12.553494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:12.553494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIC MLLM: Autonomous Interactive Correction MLLM for Robust Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengyu Shen, Chuyan Xiong, Hao Dong, Jeremy Liu, Kaichen Zhou, Ruiping Wang, Xiaoqi Li","submitted_at":"2024-06-17T13:44:53Z","abstract_excerpt":"The ability to reflect on and correct failures is crucial for robotic systems to interact stably with real-life objects.Observing the generalization and reasoning capabilities of Multimodal Large Language Models (MLLMs), previous approaches have aimed to utilize these models to enhance robotic systems accordingly.However, these methods typically focus on high-level planning corrections using an additional MLLM, with limited utilization of failed samples to correct low-level contact poses which is particularly prone to occur during articulated object manipulation.To address this gap, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11548","kind":"arxiv","version":6},"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/2406.11548/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.11548","created_at":"2026-07-05T09:36:12.553556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11548v6","created_at":"2026-07-05T09:36:12.553556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11548","created_at":"2026-07-05T09:36:12.553556+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLDUZFFATEEI","created_at":"2026-07-05T09:36:12.553556+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLDUZFFATEEIZQCQ","created_at":"2026-07-05T09:36:12.553556+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLDUZFFA","created_at":"2026-07-05T09:36:12.553556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28401","citing_title":"Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5","json":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5.json","graph_json":"https://pith.science/api/pith-number/ZLDUZFFATEEIZQCQFOUSHURSK5/graph.json","events_json":"https://pith.science/api/pith-number/ZLDUZFFATEEIZQCQFOUSHURSK5/events.json","paper":"https://pith.science/paper/ZLDUZFFA"},"agent_actions":{"view_html":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5","download_json":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5.json","view_paper":"https://pith.science/paper/ZLDUZFFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11548&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLDUZFFATEEIZQCQFOUSHURSK5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLDUZFFATEEIZQCQFOUSHURSK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5/action/storage_attestation","attest_author":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5/action/author_attestation","sign_citation":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5/action/citation_signature","submit_replication":"https://pith.science/pith/ZLDUZFFATEEIZQCQFOUSHURSK5/action/replication_record"}},"created_at":"2026-07-05T09:36:12.553556+00:00","updated_at":"2026-07-05T09:36:12.553556+00:00"}