{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:42OZI7MVPWTCLD4LKZJCSMPEYA","short_pith_number":"pith:42OZI7MV","schema_version":"1.0","canonical_sha256":"e69d947d957da6258f8b56522931e4c0025eef3b88f69c9282c667715ed94e64","source":{"kind":"arxiv","id":"2607.08397","version":1},"attestation_state":"computed","paper":{"title":"Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Doermann, Nan Xi, Shun Liu, Tianyu Luan, Xuan Gong, Yang Liu","submitted_at":"2026-07-09T12:21:06Z","abstract_excerpt":"Referring Image Segmentation (RIS) aims to segment image regions specified by natural language, enabling fine-grained and controllable visual understanding. Extending RIS to endoscopic imagery, however, presents unique challenges, including scarce high-quality annotations and complex, domain-specific image-text relationships. Although recent vision-language models demonstrate strong cross-domain alignment, they often fail to capture fine-grained textual cues in endoscopic settings, resulting in suboptimal performance and limited generalization. To address these challenges, we introduce ReferEn"},"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":"2607.08397","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T12:21:06Z","cross_cats_sorted":[],"title_canon_sha256":"1fce2105ddc4dc864475368c0a35883849c5ee55a884effd72eb52021d15f14d","abstract_canon_sha256":"7e998ac360f2cad2d59887e6506dd6c23ab6800739e5a1f9be0f9f5d0199f8ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:49.058688Z","signature_b64":"+cnPjvf5gLrTD0rfFKF3bE//dwSs5Q5BK26Lez3aAdBa6eIIxlW0PAagrtj1ac0majzuDtDa22sNQ3r0JN+8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e69d947d957da6258f8b56522931e4c0025eef3b88f69c9282c667715ed94e64","last_reissued_at":"2026-07-10T01:19:49.058286Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:49.058286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Doermann, Nan Xi, Shun Liu, Tianyu Luan, Xuan Gong, Yang Liu","submitted_at":"2026-07-09T12:21:06Z","abstract_excerpt":"Referring Image Segmentation (RIS) aims to segment image regions specified by natural language, enabling fine-grained and controllable visual understanding. Extending RIS to endoscopic imagery, however, presents unique challenges, including scarce high-quality annotations and complex, domain-specific image-text relationships. Although recent vision-language models demonstrate strong cross-domain alignment, they often fail to capture fine-grained textual cues in endoscopic settings, resulting in suboptimal performance and limited generalization. To address these challenges, we introduce ReferEn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08397","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/2607.08397/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":"2607.08397","created_at":"2026-07-10T01:19:49.058350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08397v1","created_at":"2026-07-10T01:19:49.058350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08397","created_at":"2026-07-10T01:19:49.058350+00:00"},{"alias_kind":"pith_short_12","alias_value":"42OZI7MVPWTC","created_at":"2026-07-10T01:19:49.058350+00:00"},{"alias_kind":"pith_short_16","alias_value":"42OZI7MVPWTCLD4L","created_at":"2026-07-10T01:19:49.058350+00:00"},{"alias_kind":"pith_short_8","alias_value":"42OZI7MV","created_at":"2026-07-10T01:19:49.058350+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/42OZI7MVPWTCLD4LKZJCSMPEYA","json":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA.json","graph_json":"https://pith.science/api/pith-number/42OZI7MVPWTCLD4LKZJCSMPEYA/graph.json","events_json":"https://pith.science/api/pith-number/42OZI7MVPWTCLD4LKZJCSMPEYA/events.json","paper":"https://pith.science/paper/42OZI7MV"},"agent_actions":{"view_html":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA","download_json":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA.json","view_paper":"https://pith.science/paper/42OZI7MV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08397&json=true","fetch_graph":"https://pith.science/api/pith-number/42OZI7MVPWTCLD4LKZJCSMPEYA/graph.json","fetch_events":"https://pith.science/api/pith-number/42OZI7MVPWTCLD4LKZJCSMPEYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA/action/storage_attestation","attest_author":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA/action/author_attestation","sign_citation":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA/action/citation_signature","submit_replication":"https://pith.science/pith/42OZI7MVPWTCLD4LKZJCSMPEYA/action/replication_record"}},"created_at":"2026-07-10T01:19:49.058350+00:00","updated_at":"2026-07-10T01:19:49.058350+00:00"}