{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NAQCE2ZP2BJ6BBI3DKMKS4IM35","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":"c00ba65e93cf02a6c2a2aec126a54e7235219e9626e5da4d6d5c8c2752456fde","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-15T19:22:51Z","title_canon_sha256":"fc86982d82619e8306fcf6576d180ce6b59f647de2944285d3ea85858a474f11"},"schema_version":"1.0","source":{"id":"2406.10721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10721","created_at":"2026-07-05T08:32:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10721v1","created_at":"2026-07-05T08:32:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10721","created_at":"2026-07-05T08:32:20Z"},{"alias_kind":"pith_short_12","alias_value":"NAQCE2ZP2BJ6","created_at":"2026-07-05T08:32:20Z"},{"alias_kind":"pith_short_16","alias_value":"NAQCE2ZP2BJ6BBI3","created_at":"2026-07-05T08:32:20Z"},{"alias_kind":"pith_short_8","alias_value":"NAQCE2ZP","created_at":"2026-07-05T08:32:20Z"}],"graph_snapshots":[{"event_id":"sha256:a781f2a7a2c5dc2cef81bbc1aa84f6a160ae3b93fddb2713a863b476503d721a","target":"graph","created_at":"2026-07-05T08:32:20Z","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/2406.10721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"From rearranging objects on a table to putting groceries into shelves, robots must plan precise action points to perform tasks accurately and reliably. In spite of the recent adoption of vision language models (VLMs) to control robot behavior, VLMs struggle to precisely articulate robot actions using language. We introduce an automatic synthetic data generation pipeline that instruction-tunes VLMs to robotic domains and needs. Using the pipeline, we train RoboPoint, a VLM that predicts image keypoint affordances given language instructions. Compared to alternative approaches, our method requir","authors_text":"Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox, Jiafei Duan, Ranjay Krishna, Valts Blukis, Wentao Yuan, Wilbert Pumacay","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-15T19:22:51Z","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10721","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":"sha256:93116e4534c2ac7a9a43da66ffc8d775c6fb31980a68ff2e7c7314a9f9189213","target":"record","created_at":"2026-07-05T08:32:20Z","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":"c00ba65e93cf02a6c2a2aec126a54e7235219e9626e5da4d6d5c8c2752456fde","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-15T19:22:51Z","title_canon_sha256":"fc86982d82619e8306fcf6576d180ce6b59f647de2944285d3ea85858a474f11"},"schema_version":"1.0","source":{"id":"2406.10721","kind":"arxiv","version":1}},"canonical_sha256":"6820226b2fd053e0851b1a98a9710cdf470ed7cd2ad6c4d6981de2f0cda880c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6820226b2fd053e0851b1a98a9710cdf470ed7cd2ad6c4d6981de2f0cda880c5","first_computed_at":"2026-07-05T08:32:20.907240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:20.907240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1UioDiqF6uQRdEVPOgUEuR2yaFX5i/Xa7c8h8eKa8Z4qWWG6DM5kd0oylWFt4butsHyO1XRthGqdIjtwRalUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:20.907744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93116e4534c2ac7a9a43da66ffc8d775c6fb31980a68ff2e7c7314a9f9189213","sha256:a781f2a7a2c5dc2cef81bbc1aa84f6a160ae3b93fddb2713a863b476503d721a"],"state_sha256":"946ae3484f89ed64ae884960fafe3c8836ea163203b18b1759463315d4e9ac18"}