{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:52QZYAY3Z5RXCXU6TGD5GY2YJ7","short_pith_number":"pith:52QZYAY3","schema_version":"1.0","canonical_sha256":"eea19c031bcf63715e9e9987d363584ffc722fad7f75139a55952555447f6dff","source":{"kind":"arxiv","id":"2606.10594","version":1},"attestation_state":"computed","paper":{"title":"Segment and Select: Vision-Language Segmentation in 3D Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yuenan Hou, Yulin Chen, Zhihang Zhong","submitted_at":"2026-06-09T08:58:59Z","abstract_excerpt":"3D vision-language segmentation aims to segment target objects in 3D scenarios according to the linguistic instructions and visual observations. Prior art heavily relies on the coarse superpoint representation to reduce the computation complexity, which suffers from poor segmentation quality and messy object boundaries. In this paper, we propose the SEGment-And-select (SEGA3D) paradigm for 3D visionlanguage segmentation that directly operates on the fine-grained visual information and is free from the superpoint dependency. Specifically, we first leverage a mask candidate generator to provide "},"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":"2606.10594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-09T08:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"74da786e04351bdf1f818d78dda051de07e7143550d4cd129607610e3d63ac69","abstract_canon_sha256":"fd7eef3564280ef199de27a389db392f25cbcd56ccd962a3641c84e00720b504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:28.507963Z","signature_b64":"xLAtU7LdfEh4ySsn7akqhOu6XuhsSJXKIVIRFD/LzX2pu17P8LeO5Z7kryBKTwRspukXmr2s+AyLIyZMAy6UAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea19c031bcf63715e9e9987d363584ffc722fad7f75139a55952555447f6dff","last_reissued_at":"2026-06-10T01:10:28.507143Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:28.507143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment and Select: Vision-Language Segmentation in 3D Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yuenan Hou, Yulin Chen, Zhihang Zhong","submitted_at":"2026-06-09T08:58:59Z","abstract_excerpt":"3D vision-language segmentation aims to segment target objects in 3D scenarios according to the linguistic instructions and visual observations. Prior art heavily relies on the coarse superpoint representation to reduce the computation complexity, which suffers from poor segmentation quality and messy object boundaries. In this paper, we propose the SEGment-And-select (SEGA3D) paradigm for 3D visionlanguage segmentation that directly operates on the fine-grained visual information and is free from the superpoint dependency. Specifically, we first leverage a mask candidate generator to provide "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10594","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/2606.10594/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":"2606.10594","created_at":"2026-06-10T01:10:28.507265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10594v1","created_at":"2026-06-10T01:10:28.507265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10594","created_at":"2026-06-10T01:10:28.507265+00:00"},{"alias_kind":"pith_short_12","alias_value":"52QZYAY3Z5RX","created_at":"2026-06-10T01:10:28.507265+00:00"},{"alias_kind":"pith_short_16","alias_value":"52QZYAY3Z5RXCXU6","created_at":"2026-06-10T01:10:28.507265+00:00"},{"alias_kind":"pith_short_8","alias_value":"52QZYAY3","created_at":"2026-06-10T01:10:28.507265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7","json":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7.json","graph_json":"https://pith.science/api/pith-number/52QZYAY3Z5RXCXU6TGD5GY2YJ7/graph.json","events_json":"https://pith.science/api/pith-number/52QZYAY3Z5RXCXU6TGD5GY2YJ7/events.json","paper":"https://pith.science/paper/52QZYAY3"},"agent_actions":{"view_html":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7","download_json":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7.json","view_paper":"https://pith.science/paper/52QZYAY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10594&json=true","fetch_graph":"https://pith.science/api/pith-number/52QZYAY3Z5RXCXU6TGD5GY2YJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/52QZYAY3Z5RXCXU6TGD5GY2YJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7/action/storage_attestation","attest_author":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7/action/author_attestation","sign_citation":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7/action/citation_signature","submit_replication":"https://pith.science/pith/52QZYAY3Z5RXCXU6TGD5GY2YJ7/action/replication_record"}},"created_at":"2026-06-10T01:10:28.507265+00:00","updated_at":"2026-06-10T01:10:28.507265+00:00"}