{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:43VFREDKACBWJWUMZQC5NLCM6W","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":"3371e61e119e3a44c8cdca48275b34bb51101ec7dddbc179d3c1d4b0413e2619","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-17T17:59:59Z","title_canon_sha256":"8ee80e42a34dd259a0dd6072a34618c81c1737a54a3cb2599b816544ebfecc18"},"schema_version":"1.0","source":{"id":"2403.11289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11289","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11289v2","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11289","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"43VFREDKACBW","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"43VFREDKACBWJWUM","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"43VFREDK","created_at":"2026-07-05T08:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:71d66f347bb5c3e0885e8d5c01b486a3f4608b7851dc280aef36967845911c95","target":"graph","created_at":"2026-07-05T08:57:55Z","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/2403.11289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the integration of Multi-modal Large Language Models (MLLMs) with robotic systems has significantly improved robots' ability to understand and execute natural language instructions, their performance in manipulation tasks remains limited due to a lack of robotics-specific knowledge. Conventional MLLMs are typically trained on generic image-text pairs, leaving them deficient in understanding affordances and physical concepts crucial for manipulation. To address this gap, we propose ManipVQA, a novel framework that infuses MLLMs with manipulation-centric knowledge through a Visual Question","authors_text":"Hao Dong, Hongsheng Li, Iaroslav Ponomarenko, Peng Gao, Siyuan Huang, Xiaobin Hu, Xiaoqi Li, Zhengkai Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-17T17:59:59Z","title":"ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11289","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":"sha256:24da8c9045ef0eabb97d9e2f8e60956419c15a61fe6dcee23ae95580f4a27651","target":"record","created_at":"2026-07-05T08:57:55Z","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":"3371e61e119e3a44c8cdca48275b34bb51101ec7dddbc179d3c1d4b0413e2619","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-17T17:59:59Z","title_canon_sha256":"8ee80e42a34dd259a0dd6072a34618c81c1737a54a3cb2599b816544ebfecc18"},"schema_version":"1.0","source":{"id":"2403.11289","kind":"arxiv","version":2}},"canonical_sha256":"e6ea58906a008364da8ccc05d6ac4cf5aaba6018ab8fed9ebde9ec76ce76b4e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6ea58906a008364da8ccc05d6ac4cf5aaba6018ab8fed9ebde9ec76ce76b4e2","first_computed_at":"2026-07-05T08:57:55.394203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:55.394203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fgZavjNub7PUKVjpSkznrDqSIcIePf1556zPZ0WaMuskK5JvqnB/FKR6w3SZjIYP3lQ7Z/48NTJjwRJ+vDRLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:55.394737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24da8c9045ef0eabb97d9e2f8e60956419c15a61fe6dcee23ae95580f4a27651","sha256:71d66f347bb5c3e0885e8d5c01b486a3f4608b7851dc280aef36967845911c95"],"state_sha256":"69b991da577b8730818feda9b5ff95962a6ac104d15bd78a23c9f89b1cab831f"}