{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IBX6D2YRYXG65OC4HMRAP4XIWH","short_pith_number":"pith:IBX6D2YR","schema_version":"1.0","canonical_sha256":"406fe1eb11c5cdeeb85c3b2207f2e8b1c718293d991301a6fd24b07929c2a1a7","source":{"kind":"arxiv","id":"2503.00936","version":1},"attestation_state":"computed","paper":{"title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Jingchen Ni, Yansong Tang, Yong Liu, Yuji Wang","submitted_at":"2025-03-02T15:19:37Z","abstract_excerpt":"Zero-shot Referring Image Segmentation (RIS) identifies the instance mask that best aligns with a specified referring expression without training and fine-tuning, significantly reducing the labor-intensive annotation process. Despite achieving commendable results, previous CLIP-based models have a critical drawback: the models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects. This is because they generate all possible masks on an image and evaluate each masked region for similarity to the given expression, often resulting in decreased sensitivi"},"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":"2503.00936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T15:19:37Z","cross_cats_sorted":[],"title_canon_sha256":"3daa96911d15f9415240aca260be75be420b09458588a63ab828abdeeb5b2ae8","abstract_canon_sha256":"83a68b04b9b763ecaba759391fa4c701bc87454945933ac5936a91bce2f5603b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:32.782885Z","signature_b64":"t/jmZzhAifVcR+UwiFeJ2GQjQQ5Y+BCFdMpyKvqXCwBShyKWzavFKUrNZItst2PHmyRbB0NsFr9AMksw9YiSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"406fe1eb11c5cdeeb85c3b2207f2e8b1c718293d991301a6fd24b07929c2a1a7","last_reissued_at":"2026-07-05T10:22:32.782358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:32.782358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Jingchen Ni, Yansong Tang, Yong Liu, Yuji Wang","submitted_at":"2025-03-02T15:19:37Z","abstract_excerpt":"Zero-shot Referring Image Segmentation (RIS) identifies the instance mask that best aligns with a specified referring expression without training and fine-tuning, significantly reducing the labor-intensive annotation process. Despite achieving commendable results, previous CLIP-based models have a critical drawback: the models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects. This is because they generate all possible masks on an image and evaluate each masked region for similarity to the given expression, often resulting in decreased sensitivi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00936","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/2503.00936/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":"2503.00936","created_at":"2026-07-05T10:22:32.782432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00936v1","created_at":"2026-07-05T10:22:32.782432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00936","created_at":"2026-07-05T10:22:32.782432+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBX6D2YRYXG6","created_at":"2026-07-05T10:22:32.782432+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBX6D2YRYXG65OC4","created_at":"2026-07-05T10:22:32.782432+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBX6D2YR","created_at":"2026-07-05T10:22:32.782432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03583","citing_title":"A Large-Scale Referring Remote Sensing Image Segmentation Dataset and Benchmark","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH","json":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH.json","graph_json":"https://pith.science/api/pith-number/IBX6D2YRYXG65OC4HMRAP4XIWH/graph.json","events_json":"https://pith.science/api/pith-number/IBX6D2YRYXG65OC4HMRAP4XIWH/events.json","paper":"https://pith.science/paper/IBX6D2YR"},"agent_actions":{"view_html":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH","download_json":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH.json","view_paper":"https://pith.science/paper/IBX6D2YR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00936&json=true","fetch_graph":"https://pith.science/api/pith-number/IBX6D2YRYXG65OC4HMRAP4XIWH/graph.json","fetch_events":"https://pith.science/api/pith-number/IBX6D2YRYXG65OC4HMRAP4XIWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH/action/storage_attestation","attest_author":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH/action/author_attestation","sign_citation":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH/action/citation_signature","submit_replication":"https://pith.science/pith/IBX6D2YRYXG65OC4HMRAP4XIWH/action/replication_record"}},"created_at":"2026-07-05T10:22:32.782432+00:00","updated_at":"2026-07-05T10:22:32.782432+00:00"}