{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FAPW5K2NDU4AHDHXH4CYLIXKVL","short_pith_number":"pith:FAPW5K2N","schema_version":"1.0","canonical_sha256":"281f6eab4d1d38038cf73f0585a2eaaaf313d58c880406372903c2612b614567","source":{"kind":"arxiv","id":"2402.14245","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fei Ni, Jianye Hao, Jinyi Liu, Lingzhi Fu, Yan Zheng, Yibin Chen, Yifu Yuan","submitted_at":"2024-02-22T03:14:03Z","abstract_excerpt":"Recently, there has been considerable attention towards leveraging large language models (LLMs) to enhance decision-making processes. However, aligning the natural language text instructions generated by LLMs with the vectorized operations required for execution presents a significant challenge, often necessitating task-specific details. To circumvent the need for such task-specific granularity, inspired by preference-based policy learning approaches, we investigate the utilization of multimodal LLMs to provide automated preference feedback solely from image inputs to guide decision-making. In"},"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":"2402.14245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-22T03:14:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"05c52fb868351da9254f2a330b235e472c27248d669792379ebe979d9da0897c","abstract_canon_sha256":"4a8eec1c353d4cc2b2ae5e7ef4334002b96d15909410bfa11bfe020c65fdc25d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:07.382014Z","signature_b64":"DO0ZlOdKDHFGg7hJBw2KMuKY1HFMICv0hxdy9uWxfetIkp3vH/xtm3vgBsf1xYm6f8oUtic3TVS+dPv4IvHHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"281f6eab4d1d38038cf73f0585a2eaaaf313d58c880406372903c2612b614567","last_reissued_at":"2026-07-05T07:48:07.381453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:07.381453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Fei Ni, Jianye Hao, Jinyi Liu, Lingzhi Fu, Yan Zheng, Yibin Chen, Yifu Yuan","submitted_at":"2024-02-22T03:14:03Z","abstract_excerpt":"Recently, there has been considerable attention towards leveraging large language models (LLMs) to enhance decision-making processes. However, aligning the natural language text instructions generated by LLMs with the vectorized operations required for execution presents a significant challenge, often necessitating task-specific details. To circumvent the need for such task-specific granularity, inspired by preference-based policy learning approaches, we investigate the utilization of multimodal LLMs to provide automated preference feedback solely from image inputs to guide decision-making. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14245","kind":"arxiv","version":1},"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/2402.14245/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":"2402.14245","created_at":"2026-07-05T07:48:07.381519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14245v1","created_at":"2026-07-05T07:48:07.381519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14245","created_at":"2026-07-05T07:48:07.381519+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAPW5K2NDU4A","created_at":"2026-07-05T07:48:07.381519+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAPW5K2NDU4AHDHX","created_at":"2026-07-05T07:48:07.381519+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAPW5K2N","created_at":"2026-07-05T07:48:07.381519+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":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL","json":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL.json","graph_json":"https://pith.science/api/pith-number/FAPW5K2NDU4AHDHXH4CYLIXKVL/graph.json","events_json":"https://pith.science/api/pith-number/FAPW5K2NDU4AHDHXH4CYLIXKVL/events.json","paper":"https://pith.science/paper/FAPW5K2N"},"agent_actions":{"view_html":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL","download_json":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL.json","view_paper":"https://pith.science/paper/FAPW5K2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14245&json=true","fetch_graph":"https://pith.science/api/pith-number/FAPW5K2NDU4AHDHXH4CYLIXKVL/graph.json","fetch_events":"https://pith.science/api/pith-number/FAPW5K2NDU4AHDHXH4CYLIXKVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL/action/storage_attestation","attest_author":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL/action/author_attestation","sign_citation":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL/action/citation_signature","submit_replication":"https://pith.science/pith/FAPW5K2NDU4AHDHXH4CYLIXKVL/action/replication_record"}},"created_at":"2026-07-05T07:48:07.381519+00:00","updated_at":"2026-07-05T07:48:07.381519+00:00"}