{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C6F3UI6BNFCC3OSJ5ASA6ZAR2K","short_pith_number":"pith:C6F3UI6B","schema_version":"1.0","canonical_sha256":"178bba23c169442dba49e8240f6411d2889cf7557a5311e11b42ae0a1cfa5a40","source":{"kind":"arxiv","id":"2404.02157","version":1},"attestation_state":"computed","paper":{"title":"Segment Any 3D Object with Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gim Hee Lee, Seungjun Lee, Yuyang Zhao","submitted_at":"2024-04-02T17:59:10Z","abstract_excerpt":"In this paper, we investigate Open-Vocabulary 3D Instance Segmentation (OV-3DIS) with free-form language instructions. Earlier works that rely on only annotated base categories for training suffer from limited generalization to unseen novel categories. Recent works mitigate poor generalizability to novel categories by generating class-agnostic masks or projecting generalized masks from 2D to 3D, but disregard semantic or geometry information, leading to sub-optimal performance. Instead, generating generalizable but semantic-related masks directly from 3D point clouds would result in superior o"},"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":"2404.02157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T17:59:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f35c99bbc2a9de30774bf5d7232caee70ed8e42e64654f4b98ffb5a5f7455b09","abstract_canon_sha256":"e5d1c062f8365c369493806440a07bd2e45c9b9c7cc586c9716227af0eddf4e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:36.435998Z","signature_b64":"9j89snuWjvfyYVFnTTAzhFPo9B1RAu/qO3F/f84nfEjeKqkCSJe8aYORHjxVy6S7Y3waodZP6oQZQdze4Lm5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"178bba23c169442dba49e8240f6411d2889cf7557a5311e11b42ae0a1cfa5a40","last_reissued_at":"2026-07-05T08:03:36.435509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:36.435509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Any 3D Object with Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gim Hee Lee, Seungjun Lee, Yuyang Zhao","submitted_at":"2024-04-02T17:59:10Z","abstract_excerpt":"In this paper, we investigate Open-Vocabulary 3D Instance Segmentation (OV-3DIS) with free-form language instructions. Earlier works that rely on only annotated base categories for training suffer from limited generalization to unseen novel categories. Recent works mitigate poor generalizability to novel categories by generating class-agnostic masks or projecting generalized masks from 2D to 3D, but disregard semantic or geometry information, leading to sub-optimal performance. Instead, generating generalizable but semantic-related masks directly from 3D point clouds would result in superior o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02157","kind":"arxiv","version":1},"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/2404.02157/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":"2404.02157","created_at":"2026-07-05T08:03:36.435563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02157v1","created_at":"2026-07-05T08:03:36.435563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02157","created_at":"2026-07-05T08:03:36.435563+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6F3UI6BNFCC","created_at":"2026-07-05T08:03:36.435563+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6F3UI6BNFCC3OSJ","created_at":"2026-07-05T08:03:36.435563+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6F3UI6B","created_at":"2026-07-05T08:03:36.435563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00529","citing_title":"NoPA: Non-Parametric Online 3D Scene Graph Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08916","citing_title":"MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K","json":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K.json","graph_json":"https://pith.science/api/pith-number/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/graph.json","events_json":"https://pith.science/api/pith-number/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/events.json","paper":"https://pith.science/paper/C6F3UI6B"},"agent_actions":{"view_html":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K","download_json":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K.json","view_paper":"https://pith.science/paper/C6F3UI6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02157&json=true","fetch_graph":"https://pith.science/api/pith-number/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/graph.json","fetch_events":"https://pith.science/api/pith-number/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/action/storage_attestation","attest_author":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/action/author_attestation","sign_citation":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/action/citation_signature","submit_replication":"https://pith.science/pith/C6F3UI6BNFCC3OSJ5ASA6ZAR2K/action/replication_record"}},"created_at":"2026-07-05T08:03:36.435563+00:00","updated_at":"2026-07-05T08:03:36.435563+00:00"}