{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O62WK6WU5SIUO45AEAWCFG5NXN","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":"26ec312f74a007065280865689f320b02c8ceee49a2b495aaf68a8269fadf396","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T13:29:26Z","title_canon_sha256":"198f5590186568a720a3dc25603d987a60d8ec4b07d01ed0d7561314f255f9d2"},"schema_version":"1.0","source":{"id":"2508.02405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02405","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02405v1","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02405","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"O62WK6WU5SIU","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"O62WK6WU5SIUO45A","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"O62WK6WU","created_at":"2026-07-05T11:48:13Z"}],"graph_snapshots":[{"event_id":"sha256:347842cee48b5762df911daabff8316f7235dc85de630ee9a83f5d11e9187d6c","target":"graph","created_at":"2026-07-05T11:48:13Z","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/2508.02405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The control of robots for manipulation tasks generally relies on visual input. Recent advances in vision-language models (VLMs) enable the use of natural language instructions to condition visual input and control robots in a wider range of environments. However, existing methods require a large amount of data to fine-tune VLMs for operating in unseen environments. In this paper, we present a framework that learns object-arrangement tasks from just a few demonstrations. We propose a two-stage framework that divides object-arrangement tasks into a target localization stage, for picking the obje","authors_text":"Andrea Cavallaro, Changjae Oh, Chaoran Zhu, Chenglin Cui","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T13:29:26Z","title":"Improving Generalization of Language-Conditioned Robot Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02405","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:d025b9dc2a5f331db9cd6cdcff33423c78836579a3e1902f820e3f7f94806f70","target":"record","created_at":"2026-07-05T11:48:13Z","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":"26ec312f74a007065280865689f320b02c8ceee49a2b495aaf68a8269fadf396","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T13:29:26Z","title_canon_sha256":"198f5590186568a720a3dc25603d987a60d8ec4b07d01ed0d7561314f255f9d2"},"schema_version":"1.0","source":{"id":"2508.02405","kind":"arxiv","version":1}},"canonical_sha256":"77b5657ad4ec914773a0202c229badbb5d98b08a281883e40c9a6bbcfa75251f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77b5657ad4ec914773a0202c229badbb5d98b08a281883e40c9a6bbcfa75251f","first_computed_at":"2026-07-05T11:48:13.862194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:13.862194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D1N5dZ38B3WCeCfPhzGzjwZgKEjQG5ZiFLTU44toDu+IAUu6bM/qTNs5kSpTKBuKiXBvoM4OIkcVucNSUpEOAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:13.862690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d025b9dc2a5f331db9cd6cdcff33423c78836579a3e1902f820e3f7f94806f70","sha256:347842cee48b5762df911daabff8316f7235dc85de630ee9a83f5d11e9187d6c"],"state_sha256":"95c87b8ea796c2a514861c4dfc0e0ae480cbad2299f2fa1650fdacfd52c466d0"}