{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FI5MQKIKIZYTL5TSNFLEE57XBL","short_pith_number":"pith:FI5MQKIK","schema_version":"1.0","canonical_sha256":"2a3ac8290a467135f67269564277f70ac82c7a4f7d0c7294b2efa5d27a277d01","source":{"kind":"arxiv","id":"2312.12198","version":2},"attestation_state":"computed","paper":{"title":"Mask Grounding for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Henry Zheng, Xuchong Qiu, Yizeng Han, Yong Xien Chng","submitted_at":"2023-12-19T14:34:36Z","abstract_excerpt":"Referring Image Segmentation (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Despite significant progress in recent years, most state-of-the-art (SOTA) methods still suffer from considerable language-image modality gap at the pixel and word level. These methods generally 1) rely on sentence-level language features for language-image alignment and 2) lack explicit training supervision for fine-grained visual grounding. Consequently, they exhibit weak object-level correspondence between visual and language features. Without we"},"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":"2312.12198","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T14:34:36Z","cross_cats_sorted":[],"title_canon_sha256":"10723780d19729362236a394f8c89d703593492b58ce18ee0da8bda6d43189c2","abstract_canon_sha256":"fe43d75ab33f42f21a900557e5ef50910611aa4509c484b6ed707e4b6cc4d174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:59.182679Z","signature_b64":"2cd9kPI2aqz/M8YKvaOHGFs5U9n3Mm5RTF7poCbzEfw6hTdGGN9sOou7FLhTXC+2X+97mXnDUbxFjCB2wdUgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a3ac8290a467135f67269564277f70ac82c7a4f7d0c7294b2efa5d27a277d01","last_reissued_at":"2026-07-05T07:59:59.182211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:59.182211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask Grounding for Referring Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Henry Zheng, Xuchong Qiu, Yizeng Han, Yong Xien Chng","submitted_at":"2023-12-19T14:34:36Z","abstract_excerpt":"Referring Image Segmentation (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Despite significant progress in recent years, most state-of-the-art (SOTA) methods still suffer from considerable language-image modality gap at the pixel and word level. These methods generally 1) rely on sentence-level language features for language-image alignment and 2) lack explicit training supervision for fine-grained visual grounding. Consequently, they exhibit weak object-level correspondence between visual and language features. Without we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12198","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/2312.12198/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":"2312.12198","created_at":"2026-07-05T07:59:59.182270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12198v2","created_at":"2026-07-05T07:59:59.182270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12198","created_at":"2026-07-05T07:59:59.182270+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI5MQKIKIZYT","created_at":"2026-07-05T07:59:59.182270+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI5MQKIKIZYTL5TS","created_at":"2026-07-05T07:59:59.182270+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI5MQKIK","created_at":"2026-07-05T07:59:59.182270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08580","citing_title":"Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL","json":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL.json","graph_json":"https://pith.science/api/pith-number/FI5MQKIKIZYTL5TSNFLEE57XBL/graph.json","events_json":"https://pith.science/api/pith-number/FI5MQKIKIZYTL5TSNFLEE57XBL/events.json","paper":"https://pith.science/paper/FI5MQKIK"},"agent_actions":{"view_html":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL","download_json":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL.json","view_paper":"https://pith.science/paper/FI5MQKIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12198&json=true","fetch_graph":"https://pith.science/api/pith-number/FI5MQKIKIZYTL5TSNFLEE57XBL/graph.json","fetch_events":"https://pith.science/api/pith-number/FI5MQKIKIZYTL5TSNFLEE57XBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL/action/storage_attestation","attest_author":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL/action/author_attestation","sign_citation":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL/action/citation_signature","submit_replication":"https://pith.science/pith/FI5MQKIKIZYTL5TSNFLEE57XBL/action/replication_record"}},"created_at":"2026-07-05T07:59:59.182270+00:00","updated_at":"2026-07-05T07:59:59.182270+00:00"}