{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BSMSHSVDD5IA765XDLNM7HB2VA","short_pith_number":"pith:BSMSHSVD","schema_version":"1.0","canonical_sha256":"0c9923caa31f500ffbb71adacf9c3aa81a9acfcd54f1790b903c67b727527b1a","source":{"kind":"arxiv","id":"2305.11481","version":3},"attestation_state":"computed","paper":{"title":"CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Jiachen Shen, Jiangyun Li, Jing Liu, Wenxuan Wang, Xingjian He, Yan Zhang, Yisi Zhang","submitted_at":"2023-05-19T07:17:27Z","abstract_excerpt":"Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and text, most of existing methods either introduce complex designs towards fine-grained vision-language alignment or lack required dense alignment, resulting in scalability issues or mis-segmentation problems such as over- or under-segmentation. To achieve effective and efficient fine-grained feature alignment in the RIS task, we explore the potential of masked"},"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":"2305.11481","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-19T07:17:27Z","cross_cats_sorted":[],"title_canon_sha256":"df60f70c721a90f7f7045656bcd9d00619b5a8afd0a2a5cd6489396a6513da8d","abstract_canon_sha256":"baa0621b0efa10d9f05c1a0941e24ba6e6f597469ad819c837d0d153db458c51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:54.067460Z","signature_b64":"ugDXXi1TW+PHf2tiNrQYZAjIqPJBs6l1hJdSXkr7ODYwvN+RHaDlisUsb86kFyoti80Oy7Kx0IOYpmKej9DMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c9923caa31f500ffbb71adacf9c3aa81a9acfcd54f1790b903c67b727527b1a","last_reissued_at":"2026-07-05T07:44:54.066948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:54.066948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Jiachen Shen, Jiangyun Li, Jing Liu, Wenxuan Wang, Xingjian He, Yan Zhang, Yisi Zhang","submitted_at":"2023-05-19T07:17:27Z","abstract_excerpt":"Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and text, most of existing methods either introduce complex designs towards fine-grained vision-language alignment or lack required dense alignment, resulting in scalability issues or mis-segmentation problems such as over- or under-segmentation. To achieve effective and efficient fine-grained feature alignment in the RIS task, we explore the potential of masked"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11481","kind":"arxiv","version":3},"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/2305.11481/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":"2305.11481","created_at":"2026-07-05T07:44:54.067014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11481v3","created_at":"2026-07-05T07:44:54.067014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11481","created_at":"2026-07-05T07:44:54.067014+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSMSHSVDD5IA","created_at":"2026-07-05T07:44:54.067014+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSMSHSVDD5IA765X","created_at":"2026-07-05T07:44:54.067014+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSMSHSVD","created_at":"2026-07-05T07:44:54.067014+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/BSMSHSVDD5IA765XDLNM7HB2VA","json":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA.json","graph_json":"https://pith.science/api/pith-number/BSMSHSVDD5IA765XDLNM7HB2VA/graph.json","events_json":"https://pith.science/api/pith-number/BSMSHSVDD5IA765XDLNM7HB2VA/events.json","paper":"https://pith.science/paper/BSMSHSVD"},"agent_actions":{"view_html":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA","download_json":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA.json","view_paper":"https://pith.science/paper/BSMSHSVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11481&json=true","fetch_graph":"https://pith.science/api/pith-number/BSMSHSVDD5IA765XDLNM7HB2VA/graph.json","fetch_events":"https://pith.science/api/pith-number/BSMSHSVDD5IA765XDLNM7HB2VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA/action/storage_attestation","attest_author":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA/action/author_attestation","sign_citation":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA/action/citation_signature","submit_replication":"https://pith.science/pith/BSMSHSVDD5IA765XDLNM7HB2VA/action/replication_record"}},"created_at":"2026-07-05T07:44:54.067014+00:00","updated_at":"2026-07-05T07:44:54.067014+00:00"}