{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WZT4DYRR2BD5ONJCOKZ5GXRMY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"54d1ab2b18267e2fbf8149fcff7a9641a7805a5674380b47f29341950b8edd9f","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-24T14:23:12Z","title_canon_sha256":"cd258867004074deb4c94a859746b3c915fc015741b564fb43bcc8e4e89246d6"},"schema_version":"1.0","source":{"id":"2401.13478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13478","created_at":"2026-07-05T08:30:07Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13478v2","created_at":"2026-07-05T08:30:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13478","created_at":"2026-07-05T08:30:07Z"},{"alias_kind":"pith_short_12","alias_value":"7WZT4DYRR2BD","created_at":"2026-07-05T08:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"7WZT4DYRR2BD5ONJ","created_at":"2026-07-05T08:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"7WZT4DYR","created_at":"2026-07-05T08:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:cb0ab0e508a4b49f87600f5a5c9eb69973ed453b6c64b20a84991f64e271f422","target":"graph","created_at":"2026-07-05T08:30:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.13478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-24T14:23:12Z","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13478","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a69b8423c85b6699048d0170b79e111c30824996278860948b2599dbfc25093b","target":"record","created_at":"2026-07-05T08:30:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"54d1ab2b18267e2fbf8149fcff7a9641a7805a5674380b47f29341950b8edd9f","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-01-24T14:23:12Z","title_canon_sha256":"cd258867004074deb4c94a859746b3c915fc015741b564fb43bcc8e4e89246d6"},"schema_version":"1.0","source":{"id":"2401.13478","kind":"arxiv","version":2}},"canonical_sha256":"fdb33e0f118e823eb9a913959e9af1662127ff9c5c7c7dec2faa2e3ccb094cd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdb33e0f118e823eb9a913959e9af1662127ff9c5c7c7dec2faa2e3ccb094cd6","first_computed_at":"2026-07-05T08:30:07.842079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:07.842079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHPsB5pVXgkAsEMtrH0MSqs8QylotRmWNo5B2EuYcqpoWYIQNwzZysymIIvnxjLCUDJrcHz/pTeEO8oouiXuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:07.842671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a69b8423c85b6699048d0170b79e111c30824996278860948b2599dbfc25093b","sha256:cb0ab0e508a4b49f87600f5a5c9eb69973ed453b6c64b20a84991f64e271f422"],"state_sha256":"df781bd3152c7b405134fa54b6c6506af4d6dd14eb21749d49539010fa97eea3"}