{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U4FV2L2IEF6LOTKTEZMBZGAEM4","short_pith_number":"pith:U4FV2L2I","schema_version":"1.0","canonical_sha256":"a70b5d2f48217cb74d5326581c9804671b6360a4dd90d6e4a933917d6f7e8584","source":{"kind":"arxiv","id":"2406.01451","version":1},"attestation_state":"computed","paper":{"title":"SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Danni Yang, Haowei Wang, Jiayi Ji, Rongrong Ji, Tianyu Guo, Xiaoshuai Sun, Yiwei Ma","submitted_at":"2024-06-03T15:42:30Z","abstract_excerpt":"In this paper, we introduce SemiRES, a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle in applying semi-supervised techniques to RES is the prevalence of noisy pseudo-labels, particularly at the boundaries of objects. SemiRES incorporates the Segment Anything Model (SAM), renowned for its precise boundary demarcation, to improve the accuracy of these pseudo-labels. Within SemiRES, we offer two alternative matching strategies: IoU-based Optimal Matching (IOM) and Composite Parts Integration (CPI). These strate"},"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":"2406.01451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T15:42:30Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"ad1798cc82dc694eef835e908656606382411022cf9d541de371917e12cc7794","abstract_canon_sha256":"2f5c298d1126ae321ce5da94b0383248aef91f5e35398f1aed38b1d5d4132e15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:40.020583Z","signature_b64":"VQXEs3pW2Ox7L6darL0nZA8Sw0W/+fo+W0Pl2AiE7TGeRujo37k71rUddi7X/26Px5gbnPMvJhD+1MDQZVpPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a70b5d2f48217cb74d5326581c9804671b6360a4dd90d6e4a933917d6f7e8584","last_reissued_at":"2026-07-05T08:26:40.020085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:40.020085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Danni Yang, Haowei Wang, Jiayi Ji, Rongrong Ji, Tianyu Guo, Xiaoshuai Sun, Yiwei Ma","submitted_at":"2024-06-03T15:42:30Z","abstract_excerpt":"In this paper, we introduce SemiRES, a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle in applying semi-supervised techniques to RES is the prevalence of noisy pseudo-labels, particularly at the boundaries of objects. SemiRES incorporates the Segment Anything Model (SAM), renowned for its precise boundary demarcation, to improve the accuracy of these pseudo-labels. Within SemiRES, we offer two alternative matching strategies: IoU-based Optimal Matching (IOM) and Composite Parts Integration (CPI). These strate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01451","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/2406.01451/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":"2406.01451","created_at":"2026-07-05T08:26:40.020144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01451v1","created_at":"2026-07-05T08:26:40.020144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01451","created_at":"2026-07-05T08:26:40.020144+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4FV2L2IEF6L","created_at":"2026-07-05T08:26:40.020144+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4FV2L2IEF6LOTKT","created_at":"2026-07-05T08:26:40.020144+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4FV2L2I","created_at":"2026-07-05T08:26:40.020144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11994","citing_title":"SAMST: A Transformer framework based on SAM pseudo label filtering for remote sensing semi-supervised semantic segmentation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4","json":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4.json","graph_json":"https://pith.science/api/pith-number/U4FV2L2IEF6LOTKTEZMBZGAEM4/graph.json","events_json":"https://pith.science/api/pith-number/U4FV2L2IEF6LOTKTEZMBZGAEM4/events.json","paper":"https://pith.science/paper/U4FV2L2I"},"agent_actions":{"view_html":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4","download_json":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4.json","view_paper":"https://pith.science/paper/U4FV2L2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01451&json=true","fetch_graph":"https://pith.science/api/pith-number/U4FV2L2IEF6LOTKTEZMBZGAEM4/graph.json","fetch_events":"https://pith.science/api/pith-number/U4FV2L2IEF6LOTKTEZMBZGAEM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4/action/storage_attestation","attest_author":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4/action/author_attestation","sign_citation":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4/action/citation_signature","submit_replication":"https://pith.science/pith/U4FV2L2IEF6LOTKTEZMBZGAEM4/action/replication_record"}},"created_at":"2026-07-05T08:26:40.020144+00:00","updated_at":"2026-07-05T08:26:40.020144+00:00"}