{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7WZT4DYRR2BD5ONJCOKZ5GXRMY","short_pith_number":"pith:7WZT4DYR","schema_version":"1.0","canonical_sha256":"fdb33e0f118e823eb9a913959e9af1662127ff9c5c7c7dec2faa2e3ccb094cd6","source":{"kind":"arxiv","id":"2401.13478","version":2},"attestation_state":"computed","paper":{"title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM"],"primary_cat":"cs.IR","authors_text":"Bohao Yang, Chenghao Xiao, Chenghua Lin, Ge Zhang, Haoran Zhang, Jie Fu, Kaijing Ma, Kang Zhu, Noura Al Moubayed, Siwei Wu, Wenhao Huang, Wenhu Chen, Yiming Liang, Yizhi Li","submitted_at":"2024-01-24T14:23:12Z","abstract_excerpt":"Multi-modal information retrieval (MMIR) is a rapidly evolving field, where significant progress, particularly in image-text pairing, has been made through advanced representation learning and cross-modality alignment research. However, current benchmarks for evaluating MMIR performance in image-text pairing within the scientific domain show a notable gap, where chart and table images described in scholarly language usually do not play a significant role. To bridge this gap, we develop a specialised scientific MMIR (SciMMIR) benchmark by leveraging open-access paper collections to extract data"},"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":"2401.13478","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-24T14:23:12Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"cd258867004074deb4c94a859746b3c915fc015741b564fb43bcc8e4e89246d6","abstract_canon_sha256":"54d1ab2b18267e2fbf8149fcff7a9641a7805a5674380b47f29341950b8edd9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:07.842671Z","signature_b64":"JHPsB5pVXgkAsEMtrH0MSqs8QylotRmWNo5B2EuYcqpoWYIQNwzZysymIIvnxjLCUDJrcHz/pTeEO8oouiXuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdb33e0f118e823eb9a913959e9af1662127ff9c5c7c7dec2faa2e3ccb094cd6","last_reissued_at":"2026-07-05T08:30:07.842079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:07.842079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM"],"primary_cat":"cs.IR","authors_text":"Bohao Yang, Chenghao Xiao, Chenghua Lin, Ge Zhang, Haoran Zhang, Jie Fu, Kaijing Ma, Kang Zhu, Noura Al Moubayed, Siwei Wu, Wenhao Huang, Wenhu Chen, Yiming Liang, Yizhi Li","submitted_at":"2024-01-24T14:23:12Z","abstract_excerpt":"Multi-modal information retrieval (MMIR) is a rapidly evolving field, where significant progress, particularly in image-text pairing, has been made through advanced representation learning and cross-modality alignment research. However, current benchmarks for evaluating MMIR performance in image-text pairing within the scientific domain show a notable gap, where chart and table images described in scholarly language usually do not play a significant role. To bridge this gap, we develop a specialised scientific MMIR (SciMMIR) benchmark by leveraging open-access paper collections to extract data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13478","kind":"arxiv","version":2},"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/2401.13478/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":"2401.13478","created_at":"2026-07-05T08:30:07.842211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13478v2","created_at":"2026-07-05T08:30:07.842211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13478","created_at":"2026-07-05T08:30:07.842211+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WZT4DYRR2BD","created_at":"2026-07-05T08:30:07.842211+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WZT4DYRR2BD5ONJ","created_at":"2026-07-05T08:30:07.842211+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WZT4DYR","created_at":"2026-07-05T08:30:07.842211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY","json":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY.json","graph_json":"https://pith.science/api/pith-number/7WZT4DYRR2BD5ONJCOKZ5GXRMY/graph.json","events_json":"https://pith.science/api/pith-number/7WZT4DYRR2BD5ONJCOKZ5GXRMY/events.json","paper":"https://pith.science/paper/7WZT4DYR"},"agent_actions":{"view_html":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY","download_json":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY.json","view_paper":"https://pith.science/paper/7WZT4DYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13478&json=true","fetch_graph":"https://pith.science/api/pith-number/7WZT4DYRR2BD5ONJCOKZ5GXRMY/graph.json","fetch_events":"https://pith.science/api/pith-number/7WZT4DYRR2BD5ONJCOKZ5GXRMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY/action/storage_attestation","attest_author":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY/action/author_attestation","sign_citation":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY/action/citation_signature","submit_replication":"https://pith.science/pith/7WZT4DYRR2BD5ONJCOKZ5GXRMY/action/replication_record"}},"created_at":"2026-07-05T08:30:07.842211+00:00","updated_at":"2026-07-05T08:30:07.842211+00:00"}