{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5XLXENTWHCH54C45JTTY37D7WQ","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":"12843b8a93dc2393d44eaf7434932f8c3b31a3d9d5fd2839f7978b6cd10f1a65","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-21T08:45:16Z","title_canon_sha256":"f6b10687aeff78467050528928cd8aeec8fe91173a446b08851472dfe60ed421"},"schema_version":"1.0","source":{"id":"2409.14066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14066","created_at":"2026-07-05T09:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14066v1","created_at":"2026-07-05T09:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14066","created_at":"2026-07-05T09:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"5XLXENTWHCH5","created_at":"2026-07-05T09:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"5XLXENTWHCH54C45","created_at":"2026-07-05T09:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"5XLXENTW","created_at":"2026-07-05T09:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:b7f37b7a1645cc3ba61b1368eb57e3cb042c67ca78054b4c8170a89018014829","target":"graph","created_at":"2026-07-05T09:10:11Z","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/2409.14066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Grace Tang, Homer Rich Walke, Kuan Fang, Sergey Levine, Swetha Rajkumar, Yifei Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-21T08:45:16Z","title":"KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14066","kind":"arxiv","version":1},"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:bdcb3bc5bf930afa0eaaf228cfe46964a699094c0b497be9bba820335b87067e","target":"record","created_at":"2026-07-05T09:10:11Z","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":"12843b8a93dc2393d44eaf7434932f8c3b31a3d9d5fd2839f7978b6cd10f1a65","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-21T08:45:16Z","title_canon_sha256":"f6b10687aeff78467050528928cd8aeec8fe91173a446b08851472dfe60ed421"},"schema_version":"1.0","source":{"id":"2409.14066","kind":"arxiv","version":1}},"canonical_sha256":"edd7723676388fde0b9d4ce78dfc7fb43af6f9221780b20cfc8ac1313550a006","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edd7723676388fde0b9d4ce78dfc7fb43af6f9221780b20cfc8ac1313550a006","first_computed_at":"2026-07-05T09:10:11.180333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:11.180333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L7DE3/kpX01HsEbYzfEw+Eqf84X/I7Nfh2SYei7szb3skZHvVbrK1SGk+Y+ODxa5kGEBEeAcbqN4dacft0KHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:11.180743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdcb3bc5bf930afa0eaaf228cfe46964a699094c0b497be9bba820335b87067e","sha256:b7f37b7a1645cc3ba61b1368eb57e3cb042c67ca78054b4c8170a89018014829"],"state_sha256":"e86f2d0084a177455b2691a1fd0ec3b19685478e67348618679e783c912b912e"}