{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5PKVZVCHMZ5ZMO47VR3VQEPOJ6","short_pith_number":"pith:5PKVZVCH","schema_version":"1.0","canonical_sha256":"ebd55cd447667b963b9fac775811ee4fbccb817cb87515d057f7c6e2395a48b2","source":{"kind":"arxiv","id":"2407.20664","version":2},"attestation_state":"computed","paper":{"title":"3D-GRES: Generalized 3D Referring Expression Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changli Wu, Gen Luo, Haowei Wang, Henghui Ding, Jiayi Ji, Rongrong Ji, Xiaoshuai Sun, Yihang Liu, Yiwei Ma","submitted_at":"2024-07-30T08:59:05Z","abstract_excerpt":"3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-obj"},"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":"2407.20664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T08:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"a3dcba926a74a4d151edeb2590e9d4c61e22dffb2e7714c5d666f4260d3bb5c5","abstract_canon_sha256":"689fbcadf22343318aeafac42e2051a882e10b4405d9c3c4bbdbdd430278740b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:31.892961Z","signature_b64":"k8gIbgskQ4fL+NiBgMbB7UlrybGLywytgJ8JjWevw1WBWXf9xAV3YiIaEBLvG/ZbcUlia5JTSw8Y/Pdi5MOnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebd55cd447667b963b9fac775811ee4fbccb817cb87515d057f7c6e2395a48b2","last_reissued_at":"2026-07-05T08:50:31.892482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:31.892482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-GRES: Generalized 3D Referring Expression Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changli Wu, Gen Luo, Haowei Wang, Henghui Ding, Jiayi Ji, Rongrong Ji, Xiaoshuai Sun, Yihang Liu, Yiwei Ma","submitted_at":"2024-07-30T08:59:05Z","abstract_excerpt":"3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20664","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/2407.20664/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":"2407.20664","created_at":"2026-07-05T08:50:31.892540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20664v2","created_at":"2026-07-05T08:50:31.892540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20664","created_at":"2026-07-05T08:50:31.892540+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PKVZVCHMZ5Z","created_at":"2026-07-05T08:50:31.892540+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PKVZVCHMZ5ZMO47","created_at":"2026-07-05T08:50:31.892540+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PKVZVCH","created_at":"2026-07-05T08:50:31.892540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02402","citing_title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6","json":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6.json","graph_json":"https://pith.science/api/pith-number/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/graph.json","events_json":"https://pith.science/api/pith-number/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/events.json","paper":"https://pith.science/paper/5PKVZVCH"},"agent_actions":{"view_html":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6","download_json":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6.json","view_paper":"https://pith.science/paper/5PKVZVCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20664&json=true","fetch_graph":"https://pith.science/api/pith-number/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/action/storage_attestation","attest_author":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/action/author_attestation","sign_citation":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/action/citation_signature","submit_replication":"https://pith.science/pith/5PKVZVCHMZ5ZMO47VR3VQEPOJ6/action/replication_record"}},"created_at":"2026-07-05T08:50:31.892540+00:00","updated_at":"2026-07-05T08:50:31.892540+00:00"}