{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PLA2XMAEZLNEXL2JFTJSIBT3J","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":"fd1f0949b20f7ac1345cbfd7e6cdaf99e8e1285263972d833cac9517e3f087b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T09:47:07Z","title_canon_sha256":"e43c6a23a1e1d144103afb995e7b8189086f09de08ed08db4fb8101be9c19201"},"schema_version":"1.0","source":{"id":"2402.08327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08327","created_at":"2026-07-05T08:27:45Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08327v2","created_at":"2026-07-05T08:27:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08327","created_at":"2026-07-05T08:27:45Z"},{"alias_kind":"pith_short_12","alias_value":"4PLA2XMAEZLN","created_at":"2026-07-05T08:27:45Z"},{"alias_kind":"pith_short_16","alias_value":"4PLA2XMAEZLNEXL2","created_at":"2026-07-05T08:27:45Z"},{"alias_kind":"pith_short_8","alias_value":"4PLA2XMA","created_at":"2026-07-05T08:27:45Z"}],"graph_snapshots":[{"event_id":"sha256:5984bb6836ab91febed6e37b9d3fe23ac12aa3aff775858e9705cb5a1113b18c","target":"graph","created_at":"2026-07-05T08:27:45Z","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/2402.08327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) excel in natural language and visual understanding but are challenged by exacting tasks such as Knowledge-based Visual Question Answering (KB-VQA) which involve the retrieval of relevant information from document collections to use in shaping answers to questions. We present an extensive training and evaluation framework, M2KR, for KB-VQA. M2KR contains a collection of vision and language tasks which we have incorporated into a single suite of benchmark tasks for training and evaluating general-purpose multi-modal retrievers. We use M2KR to develop PreFLMR, a pre","authors_text":"Bill Byrne, Jingbiao Mei, Jinghong Chen, Weizhe Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T09:47:07Z","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08327","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":"sha256:5a7b1965fafd0e640089632853ef15ef6e3ffe9e627c20cfd415e4cfcf9c3545","target":"record","created_at":"2026-07-05T08:27:45Z","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":"fd1f0949b20f7ac1345cbfd7e6cdaf99e8e1285263972d833cac9517e3f087b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T09:47:07Z","title_canon_sha256":"e43c6a23a1e1d144103afb995e7b8189086f09de08ed08db4fb8101be9c19201"},"schema_version":"1.0","source":{"id":"2402.08327","kind":"arxiv","version":2}},"canonical_sha256":"e3d60d5d802656d25d7a4966992033da4c359fe0fbe33397b4d034e9e46c1119","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3d60d5d802656d25d7a4966992033da4c359fe0fbe33397b4d034e9e46c1119","first_computed_at":"2026-07-05T08:27:45.988610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:45.988610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8qqg9iplCwk1bFOA5bYscUe6bQBqAxyVZIW6ZEcWvomygD1ujy7SV9FDt7SKo/oToj82nXpDqyVfSCCdm8oBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:45.989160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a7b1965fafd0e640089632853ef15ef6e3ffe9e627c20cfd415e4cfcf9c3545","sha256:5984bb6836ab91febed6e37b9d3fe23ac12aa3aff775858e9705cb5a1113b18c"],"state_sha256":"a47362f55afd84fb6ff5acb167eb2e909f6f685975b8103f65b32b83494436d2"}