{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FTICY4F3PZOUNS5FF76OM2VP7M","short_pith_number":"pith:FTICY4F3","schema_version":"1.0","canonical_sha256":"2cd02c70bb7e5d46cba52ffce66aaffb2f09ce0412690a1c65b50756b45cbb47","source":{"kind":"arxiv","id":"2605.20110","version":1},"attestation_state":"computed","paper":{"title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Wang, Long Xing, Qiaosheng Zhang, Shengyuan Ding, Shuangrui Ding, Yibin Wang, Yizhuo Li, Yuhang Zang, Zhixiong Zhang","submitted_at":"2026-05-19T16:59:11Z","abstract_excerpt":"Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended target sets remains challenging. Previous Large Vision Language Model (LVLM)-based methods represent referred targets with one or more special tokens sequentially, treating multiple targets as separate outputs rather than a coherent set and offering little incentive to capture set-level properties such as completeness and mutual exclusivity. We reformulate open-ended referring segmentation as explicit set-level concept"},"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":"2605.20110","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T16:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"c7f22f40432295d5c604cdc738cd46a0b36fedb06d540aff826476db730d30e7","abstract_canon_sha256":"792769a69089e679e2c8136c2ff201b004e2d894d2eb2e8a8c0e0c08276722ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:06:02.476625Z","signature_b64":"KprIQTW2JmVXtAdyvOK5dVdGRU7vd0KS2aCplvXdgLdkNtxNyGFc3dnlBDhdPTNAZ1PAdPHYKC57fdBqTRr1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd02c70bb7e5d46cba52ffce66aaffb2f09ce0412690a1c65b50756b45cbb47","last_reissued_at":"2026-05-20T02:06:02.475939Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:06:02.475939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Wang, Long Xing, Qiaosheng Zhang, Shengyuan Ding, Shuangrui Ding, Yibin Wang, Yizhuo Li, Yuhang Zang, Zhixiong Zhang","submitted_at":"2026-05-19T16:59:11Z","abstract_excerpt":"Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended target sets remains challenging. Previous Large Vision Language Model (LVLM)-based methods represent referred targets with one or more special tokens sequentially, treating multiple targets as separate outputs rather than a coherent set and offering little incentive to capture set-level properties such as completeness and mutual exclusivity. We reformulate open-ended referring segmentation as explicit set-level concept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20110","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/2605.20110/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":"2605.20110","created_at":"2026-05-20T02:06:02.476045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20110v1","created_at":"2026-05-20T02:06:02.476045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20110","created_at":"2026-05-20T02:06:02.476045+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTICY4F3PZOU","created_at":"2026-05-20T02:06:02.476045+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTICY4F3PZOUNS5F","created_at":"2026-05-20T02:06:02.476045+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTICY4F3","created_at":"2026-05-20T02:06:02.476045+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/FTICY4F3PZOUNS5FF76OM2VP7M","json":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M.json","graph_json":"https://pith.science/api/pith-number/FTICY4F3PZOUNS5FF76OM2VP7M/graph.json","events_json":"https://pith.science/api/pith-number/FTICY4F3PZOUNS5FF76OM2VP7M/events.json","paper":"https://pith.science/paper/FTICY4F3"},"agent_actions":{"view_html":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M","download_json":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M.json","view_paper":"https://pith.science/paper/FTICY4F3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20110&json=true","fetch_graph":"https://pith.science/api/pith-number/FTICY4F3PZOUNS5FF76OM2VP7M/graph.json","fetch_events":"https://pith.science/api/pith-number/FTICY4F3PZOUNS5FF76OM2VP7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M/action/storage_attestation","attest_author":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M/action/author_attestation","sign_citation":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M/action/citation_signature","submit_replication":"https://pith.science/pith/FTICY4F3PZOUNS5FF76OM2VP7M/action/replication_record"}},"created_at":"2026-05-20T02:06:02.476045+00:00","updated_at":"2026-05-20T02:06:02.476045+00:00"}