{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LYVDPBCIEIUY666TU7CWJUHZBJ","short_pith_number":"pith:LYVDPBCI","schema_version":"1.0","canonical_sha256":"5e2a37844822298f7bd3a7c564d0f90a571568b460a7bc5ee3d77514eb55947d","source":{"kind":"arxiv","id":"2207.11514","version":2},"attestation_state":"computed","paper":{"title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Huy Ha, Shuran Song","submitted_at":"2022-07-23T13:10:25Z","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"},"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":"2207.11514","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-23T13:10:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"da7e0172a786a79c4ee209bf4a361ff00c1df853c5ff437be326ac86023950d5","abstract_canon_sha256":"81176da8129b143da27c755207c851dc34ff6751750c02523543a6cacc34db43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:30.031743Z","signature_b64":"RNrqHKjwsKOiszE+08VqnzAVkqy41fDXYOft9oHqF1nGwkpZD6PYwY62Vp32JRFLQu38obYvk8dCsoYiJ+3RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e2a37844822298f7bd3a7c564d0f90a571568b460a7bc5ee3d77514eb55947d","last_reissued_at":"2026-07-05T05:22:30.031269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:30.031269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Huy Ha, Shuran Song","submitted_at":"2022-07-23T13:10:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11514","kind":"arxiv","version":2},"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/2207.11514/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":"2207.11514","created_at":"2026-07-05T05:22:30.031332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11514v2","created_at":"2026-07-05T05:22:30.031332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11514","created_at":"2026-07-05T05:22:30.031332+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYVDPBCIEIUY","created_at":"2026-07-05T05:22:30.031332+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYVDPBCIEIUY666T","created_at":"2026-07-05T05:22:30.031332+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYVDPBCI","created_at":"2026-07-05T05:22:30.031332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18483","citing_title":"Steadily moving semi-infinite fracture in plane poroelasticity","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21292","citing_title":"Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ","json":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ.json","graph_json":"https://pith.science/api/pith-number/LYVDPBCIEIUY666TU7CWJUHZBJ/graph.json","events_json":"https://pith.science/api/pith-number/LYVDPBCIEIUY666TU7CWJUHZBJ/events.json","paper":"https://pith.science/paper/LYVDPBCI"},"agent_actions":{"view_html":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ","download_json":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ.json","view_paper":"https://pith.science/paper/LYVDPBCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11514&json=true","fetch_graph":"https://pith.science/api/pith-number/LYVDPBCIEIUY666TU7CWJUHZBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LYVDPBCIEIUY666TU7CWJUHZBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ/action/storage_attestation","attest_author":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ/action/author_attestation","sign_citation":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ/action/citation_signature","submit_replication":"https://pith.science/pith/LYVDPBCIEIUY666TU7CWJUHZBJ/action/replication_record"}},"created_at":"2026-07-05T05:22:30.031332+00:00","updated_at":"2026-07-05T05:22:30.031332+00:00"}