{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AEGHTH546Q66D3X6AFGZ5G5ZRO","short_pith_number":"pith:AEGHTH54","schema_version":"1.0","canonical_sha256":"010c799fbcf43de1eefe014d9e9bb98bb987cee9da555bae017da49f0cef5267","source":{"kind":"arxiv","id":"2506.01795","version":1},"attestation_state":"computed","paper":{"title":"R2SM: Referring and Reasoning for Selective Masks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Sun, Hwann-Tzong Chen, Wei-En Tai, Yu-Chiang Frank Wang, Yu-Lin Shih","submitted_at":"2025-06-02T15:36:31Z","abstract_excerpt":"We introduce a new task, Referring and Reasoning for Selective Masks (R2SM), which extends text-guided segmentation by incorporating mask-type selection driven by user intent. This task challenges vision-language models to determine whether to generate a modal (visible) or amodal (complete) segmentation mask based solely on natural language prompts. To support the R2SM task, we present the R2SM dataset, constructed by augmenting annotations of COCOA-cls, D2SA, and MUVA. The R2SM dataset consists of both modal and amodal text queries, each paired with the corresponding ground-truth mask, enabli"},"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":"2506.01795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T15:36:31Z","cross_cats_sorted":[],"title_canon_sha256":"e65ed0fa276c78ecd10efb523064564da7467a2865eff4503cd67636506ac0b9","abstract_canon_sha256":"67c15b8f4ad9b1b5254de6058f511846b8832a15e3f402a24e34b5706963be66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:19.449801Z","signature_b64":"jBoDpJeYDm8mOSSXtdmHJDZ4AKCHZKY6V1w7ax8Y7iowEqL84Nw2sGZwh7v/GZwGryUrmET0yqlKOEUZyltmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"010c799fbcf43de1eefe014d9e9bb98bb987cee9da555bae017da49f0cef5267","last_reissued_at":"2026-07-05T11:14:19.449325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:19.449325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R2SM: Referring and Reasoning for Selective Masks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Sun, Hwann-Tzong Chen, Wei-En Tai, Yu-Chiang Frank Wang, Yu-Lin Shih","submitted_at":"2025-06-02T15:36:31Z","abstract_excerpt":"We introduce a new task, Referring and Reasoning for Selective Masks (R2SM), which extends text-guided segmentation by incorporating mask-type selection driven by user intent. This task challenges vision-language models to determine whether to generate a modal (visible) or amodal (complete) segmentation mask based solely on natural language prompts. To support the R2SM task, we present the R2SM dataset, constructed by augmenting annotations of COCOA-cls, D2SA, and MUVA. The R2SM dataset consists of both modal and amodal text queries, each paired with the corresponding ground-truth mask, enabli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01795","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/2506.01795/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":"2506.01795","created_at":"2026-07-05T11:14:19.449390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01795v1","created_at":"2026-07-05T11:14:19.449390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01795","created_at":"2026-07-05T11:14:19.449390+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEGHTH546Q66","created_at":"2026-07-05T11:14:19.449390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEGHTH546Q66D3X6","created_at":"2026-07-05T11:14:19.449390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEGHTH54","created_at":"2026-07-05T11:14:19.449390+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/AEGHTH546Q66D3X6AFGZ5G5ZRO","json":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO.json","graph_json":"https://pith.science/api/pith-number/AEGHTH546Q66D3X6AFGZ5G5ZRO/graph.json","events_json":"https://pith.science/api/pith-number/AEGHTH546Q66D3X6AFGZ5G5ZRO/events.json","paper":"https://pith.science/paper/AEGHTH54"},"agent_actions":{"view_html":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO","download_json":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO.json","view_paper":"https://pith.science/paper/AEGHTH54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01795&json=true","fetch_graph":"https://pith.science/api/pith-number/AEGHTH546Q66D3X6AFGZ5G5ZRO/graph.json","fetch_events":"https://pith.science/api/pith-number/AEGHTH546Q66D3X6AFGZ5G5ZRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO/action/storage_attestation","attest_author":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO/action/author_attestation","sign_citation":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO/action/citation_signature","submit_replication":"https://pith.science/pith/AEGHTH546Q66D3X6AFGZ5G5ZRO/action/replication_record"}},"created_at":"2026-07-05T11:14:19.449390+00:00","updated_at":"2026-07-05T11:14:19.449390+00:00"}