{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LYVDPBCIEIUY666TU7CWJUHZBJ","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":"81176da8129b143da27c755207c851dc34ff6751750c02523543a6cacc34db43","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-23T13:10:25Z","title_canon_sha256":"da7e0172a786a79c4ee209bf4a361ff00c1df853c5ff437be326ac86023950d5"},"schema_version":"1.0","source":{"id":"2207.11514","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.11514","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"2207.11514v2","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11514","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"LYVDPBCIEIUY","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_16","alias_value":"LYVDPBCIEIUY666T","created_at":"2026-07-05T05:22:30Z"},{"alias_kind":"pith_short_8","alias_value":"LYVDPBCI","created_at":"2026-07-05T05:22:30Z"}],"graph_snapshots":[{"event_id":"sha256:a91f5a8765ada83c4b71ce7f5490f4e34c2e18e9cb93cd836fb596a0871b5e0a","target":"graph","created_at":"2026-07-05T05:22:30Z","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/2207.11514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study open-world 3D scene understanding, a family of tasks that require agents to reason about their 3D environment with an open-set vocabulary and out-of-domain visual inputs - a critical skill for robots to operate in the unstructured 3D world. Towards this end, we propose Semantic Abstraction (SemAbs), a framework that equips 2D Vision-Language Models (VLMs) with new 3D spatial capabilities, while maintaining their zero-shot robustness. We achieve this abstraction using relevancy maps extracted from CLIP, and learn 3D spatial and geometric reasoning skills on top of those abstractions in","authors_text":"Huy Ha, Shuran Song","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-23T13:10:25Z","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11514","kind":"arxiv","version":2},"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":"sha256:3b0d8bfa033a9f935e8187f3f3848b830e3acf46efc8e94f5486912a14c6cf39","target":"record","created_at":"2026-07-05T05:22:30Z","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":"81176da8129b143da27c755207c851dc34ff6751750c02523543a6cacc34db43","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-23T13:10:25Z","title_canon_sha256":"da7e0172a786a79c4ee209bf4a361ff00c1df853c5ff437be326ac86023950d5"},"schema_version":"1.0","source":{"id":"2207.11514","kind":"arxiv","version":2}},"canonical_sha256":"5e2a37844822298f7bd3a7c564d0f90a571568b460a7bc5ee3d77514eb55947d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e2a37844822298f7bd3a7c564d0f90a571568b460a7bc5ee3d77514eb55947d","first_computed_at":"2026-07-05T05:22:30.031269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:30.031269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RNrqHKjwsKOiszE+08VqnzAVkqy41fDXYOft9oHqF1nGwkpZD6PYwY62Vp32JRFLQu38obYvk8dCsoYiJ+3RCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:30.031743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.11514","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b0d8bfa033a9f935e8187f3f3848b830e3acf46efc8e94f5486912a14c6cf39","sha256:a91f5a8765ada83c4b71ce7f5490f4e34c2e18e9cb93cd836fb596a0871b5e0a"],"state_sha256":"ac879550459444fc42a782ab8111102691d882cbdbe7de79bdc2f083a67b1ddc"}