{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XLXENTWHCH54C45JTTY37D7WQ","short_pith_number":"pith:5XLXENTW","schema_version":"1.0","canonical_sha256":"edd7723676388fde0b9d4ce78dfc7fb43af6f9221780b20cfc8ac1313550a006","source":{"kind":"arxiv","id":"2409.14066","version":1},"attestation_state":"computed","paper":{"title":"KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Grace Tang, Homer Rich Walke, Kuan Fang, Sergey Levine, Swetha Rajkumar, Yifei Zhou","submitted_at":"2024-09-21T08:45:16Z","abstract_excerpt":"Building generalist robotic systems involves effectively endowing robots with the capabilities to handle novel objects in an open-world setting. Inspired by the advances of large pre-trained models, we propose Keypoint Affordance Learning from Imagined Environments (KALIE), which adapts pre-trained Vision Language Models (VLMs) for robotic control in a scalable manner. Instead of directly producing motor commands, KALIE controls the robot by predicting point-based affordance representations based on natural language instructions and visual observations of the scene. The VLM is trained on 2D im"},"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":"2409.14066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-21T08:45:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f6b10687aeff78467050528928cd8aeec8fe91173a446b08851472dfe60ed421","abstract_canon_sha256":"12843b8a93dc2393d44eaf7434932f8c3b31a3d9d5fd2839f7978b6cd10f1a65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:11.180743Z","signature_b64":"L7DE3/kpX01HsEbYzfEw+Eqf84X/I7Nfh2SYei7szb3skZHvVbrK1SGk+Y+ODxa5kGEBEeAcbqN4dacft0KHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edd7723676388fde0b9d4ce78dfc7fb43af6f9221780b20cfc8ac1313550a006","last_reissued_at":"2026-07-05T09:10:11.180333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:11.180333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Grace Tang, Homer Rich Walke, Kuan Fang, Sergey Levine, Swetha Rajkumar, Yifei Zhou","submitted_at":"2024-09-21T08:45:16Z","abstract_excerpt":"Building generalist robotic systems involves effectively endowing robots with the capabilities to handle novel objects in an open-world setting. Inspired by the advances of large pre-trained models, we propose Keypoint Affordance Learning from Imagined Environments (KALIE), which adapts pre-trained Vision Language Models (VLMs) for robotic control in a scalable manner. Instead of directly producing motor commands, KALIE controls the robot by predicting point-based affordance representations based on natural language instructions and visual observations of the scene. The VLM is trained on 2D im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14066","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/2409.14066/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":"2409.14066","created_at":"2026-07-05T09:10:11.180389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14066v1","created_at":"2026-07-05T09:10:11.180389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14066","created_at":"2026-07-05T09:10:11.180389+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XLXENTWHCH5","created_at":"2026-07-05T09:10:11.180389+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XLXENTWHCH54C45","created_at":"2026-07-05T09:10:11.180389+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XLXENTW","created_at":"2026-07-05T09:10:11.180389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05533","citing_title":"What Objects Enable, Not What They Are: Functional Latent Spaces for Affordance Reasoning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ","json":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ.json","graph_json":"https://pith.science/api/pith-number/5XLXENTWHCH54C45JTTY37D7WQ/graph.json","events_json":"https://pith.science/api/pith-number/5XLXENTWHCH54C45JTTY37D7WQ/events.json","paper":"https://pith.science/paper/5XLXENTW"},"agent_actions":{"view_html":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ","download_json":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ.json","view_paper":"https://pith.science/paper/5XLXENTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14066&json=true","fetch_graph":"https://pith.science/api/pith-number/5XLXENTWHCH54C45JTTY37D7WQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5XLXENTWHCH54C45JTTY37D7WQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ/action/storage_attestation","attest_author":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ/action/author_attestation","sign_citation":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ/action/citation_signature","submit_replication":"https://pith.science/pith/5XLXENTWHCH54C45JTTY37D7WQ/action/replication_record"}},"created_at":"2026-07-05T09:10:11.180389+00:00","updated_at":"2026-07-05T09:10:11.180389+00:00"}