{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WGSMB4W54P27UGXZYQCYPLWQHE","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":"34c19c5c4b1ec0752a65c927d773d1079c235d068e917d43569d1038b6735668","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-06T08:12:11Z","title_canon_sha256":"fe862d1900949878611adf7763a3f89dcedf0288e21ee0797cc018d98bfe91b7"},"schema_version":"1.0","source":{"id":"2305.03972","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03972","created_at":"2026-07-05T08:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03972v4","created_at":"2026-07-05T08:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03972","created_at":"2026-07-05T08:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"WGSMB4W54P27","created_at":"2026-07-05T08:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"WGSMB4W54P27UGXZ","created_at":"2026-07-05T08:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"WGSMB4W5","created_at":"2026-07-05T08:29:15Z"}],"graph_snapshots":[{"event_id":"sha256:83f2e1b332d496c317d2919b2553b2334721d85ec280a7aa587e9aa0ca55adc8","target":"graph","created_at":"2026-07-05T08:29:15Z","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/2305.03972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of multi-modal search requests from users has highlighted the importance of multi-modal retrieval (i.e. image-to-text or text-to-image retrieval), yet the more complex task of image-to-multi-modal retrieval, crucial for many industry applications, remains under-explored. To address this gap and promote further research, we introduce and define the concept of Image-to-Multi-Modal Retrieval (IMMR), a process designed to retrieve rich multi-modal (i.e. image and text) documents based on image queries. We focus on representation learning for IMMR and analyze three key challenges for it: 1","authors_text":"Chen Ju, Junchi Yan, Shuai Xiao, Weilin Huang, Xiaoyi Zeng, Xu Chen, Zhonghua Zhai, Zida Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-06T08:12:11Z","title":"Category-Oriented Representation Learning for Image to Multi-Modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03972","kind":"arxiv","version":4},"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:feedb112e9a80a78f456c96121c61f893cee1c9fa7b23d001ad176dcc09b1a4c","target":"record","created_at":"2026-07-05T08:29:15Z","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":"34c19c5c4b1ec0752a65c927d773d1079c235d068e917d43569d1038b6735668","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-06T08:12:11Z","title_canon_sha256":"fe862d1900949878611adf7763a3f89dcedf0288e21ee0797cc018d98bfe91b7"},"schema_version":"1.0","source":{"id":"2305.03972","kind":"arxiv","version":4}},"canonical_sha256":"b1a4c0f2dde3f5fa1af9c40587aed039275eaed17038ad2e9d09542cc448272a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1a4c0f2dde3f5fa1af9c40587aed039275eaed17038ad2e9d09542cc448272a","first_computed_at":"2026-07-05T08:29:15.105245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:15.105245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NgFeJqN6HGcY3mf/jo2thKbQGoiHBd+BwzGciatDeEpP7xDxnatn/hYrkUXgSqV/1YklpG5l+VIKK4OPVcYRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:15.105774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03972","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feedb112e9a80a78f456c96121c61f893cee1c9fa7b23d001ad176dcc09b1a4c","sha256:83f2e1b332d496c317d2919b2553b2334721d85ec280a7aa587e9aa0ca55adc8"],"state_sha256":"2cef5ea77bcf9826eb9f947c5dac694ecc002a6cc85ebe1b8c61ff312c09aa4e"}