{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WMPMRD5PGPQTC6X7UNLJZHKEEX","short_pith_number":"pith:WMPMRD5P","schema_version":"1.0","canonical_sha256":"b31ec88faf33e1317affa3569c9d4425d952d68a5ae1fbf9006cfb728f498e1d","source":{"kind":"arxiv","id":"2505.11852","version":1},"attestation_state":"computed","paper":{"title":"MedSG-Bench: A Benchmark for Medical Image Sequences Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangyu Wang, Huihuan Xu, Jingkun Yue, Siqi Zhang, Xiaohong Liu, Zinan Jia, Zongbo Han","submitted_at":"2025-05-17T05:31:17Z","abstract_excerpt":"Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image scenarios, real-world clinical applications often involve sequential images, where accurate lesion localization across different modalities and temporal tracking of disease progression (e.g., pre- vs. post-treatment comparison) require fine-grained cross-image semantic alignment and context-aware reasoning. To remedy the underrepresentation of image sequences in e"},"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":"2505.11852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T05:31:17Z","cross_cats_sorted":[],"title_canon_sha256":"e8c484f55c583449f70d3f4aedb110b516fe299040fe066bb3f637ae73c92f40","abstract_canon_sha256":"d2ce2b83a972d774032ab0f3db2e6f248dc0302d2f7641d5e66ebb259c867f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:53.148076Z","signature_b64":"L2W88u55KZOQ5lyckEpY0DUIkEtX5qq7PnlvHm3ld+Nkx+XvBUssG6W8Cc3g3mmeL43GqaaQHFEZo/QBNcuhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31ec88faf33e1317affa3569c9d4425d952d68a5ae1fbf9006cfb728f498e1d","last_reissued_at":"2026-07-05T11:04:53.147654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:53.147654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedSG-Bench: A Benchmark for Medical Image Sequences Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangyu Wang, Huihuan Xu, Jingkun Yue, Siqi Zhang, Xiaohong Liu, Zinan Jia, Zongbo Han","submitted_at":"2025-05-17T05:31:17Z","abstract_excerpt":"Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image scenarios, real-world clinical applications often involve sequential images, where accurate lesion localization across different modalities and temporal tracking of disease progression (e.g., pre- vs. post-treatment comparison) require fine-grained cross-image semantic alignment and context-aware reasoning. To remedy the underrepresentation of image sequences in e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11852","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/2505.11852/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":"2505.11852","created_at":"2026-07-05T11:04:53.147713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11852v1","created_at":"2026-07-05T11:04:53.147713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11852","created_at":"2026-07-05T11:04:53.147713+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMPMRD5PGPQT","created_at":"2026-07-05T11:04:53.147713+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMPMRD5PGPQTC6X7","created_at":"2026-07-05T11:04:53.147713+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMPMRD5P","created_at":"2026-07-05T11:04:53.147713+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/WMPMRD5PGPQTC6X7UNLJZHKEEX","json":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX.json","graph_json":"https://pith.science/api/pith-number/WMPMRD5PGPQTC6X7UNLJZHKEEX/graph.json","events_json":"https://pith.science/api/pith-number/WMPMRD5PGPQTC6X7UNLJZHKEEX/events.json","paper":"https://pith.science/paper/WMPMRD5P"},"agent_actions":{"view_html":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX","download_json":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX.json","view_paper":"https://pith.science/paper/WMPMRD5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11852&json=true","fetch_graph":"https://pith.science/api/pith-number/WMPMRD5PGPQTC6X7UNLJZHKEEX/graph.json","fetch_events":"https://pith.science/api/pith-number/WMPMRD5PGPQTC6X7UNLJZHKEEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX/action/storage_attestation","attest_author":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX/action/author_attestation","sign_citation":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX/action/citation_signature","submit_replication":"https://pith.science/pith/WMPMRD5PGPQTC6X7UNLJZHKEEX/action/replication_record"}},"created_at":"2026-07-05T11:04:53.147713+00:00","updated_at":"2026-07-05T11:04:53.147713+00:00"}