{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:D4RPOMOSCV7CL6LRU74U4ZYDVH","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":"d91bbcba2140478f0796f1e49be7a9aba1af4c2617ff75514c46b98ee53874bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T12:28:12Z","title_canon_sha256":"4b018209e3f5aaaa6d0220757316ed9a82c14e9a50619196128393b2692d2d2c"},"schema_version":"1.0","source":{"id":"2205.12029","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12029","created_at":"2026-07-05T06:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12029v3","created_at":"2026-07-05T06:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12029","created_at":"2026-07-05T06:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"D4RPOMOSCV7C","created_at":"2026-07-05T06:09:04Z"},{"alias_kind":"pith_short_16","alias_value":"D4RPOMOSCV7CL6LR","created_at":"2026-07-05T06:09:04Z"},{"alias_kind":"pith_short_8","alias_value":"D4RPOMOS","created_at":"2026-07-05T06:09:04Z"}],"graph_snapshots":[{"event_id":"sha256:10b6b302dd61e3daf50076d31e224a44502a6d1746fda419f75c2aeffc9496d3","target":"graph","created_at":"2026-07-05T06:09:04Z","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/2205.12029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a joint representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across m","authors_text":"Mar\\c{c}al Rusi\\~nol, Mickael Coustaty, Oriol Ramos Terrades, Souhail Bakkali, Zuheng Ming","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T12:28:12Z","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12029","kind":"arxiv","version":3},"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":"sha256:42c4334a53ba5f171caaefaca7d6e58c43bdb5b079f5bbcdb6e80f34d6fe9f7d","target":"record","created_at":"2026-07-05T06:09:04Z","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":"d91bbcba2140478f0796f1e49be7a9aba1af4c2617ff75514c46b98ee53874bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-24T12:28:12Z","title_canon_sha256":"4b018209e3f5aaaa6d0220757316ed9a82c14e9a50619196128393b2692d2d2c"},"schema_version":"1.0","source":{"id":"2205.12029","kind":"arxiv","version":3}},"canonical_sha256":"1f22f731d2157e25f971a7f94e6703a9fd847de40a47116c4716d0188bbc6741","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f22f731d2157e25f971a7f94e6703a9fd847de40a47116c4716d0188bbc6741","first_computed_at":"2026-07-05T06:09:04.731080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:04.731080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+bF5z09Z/DFj/qkUDMPC5Rjof6gQPhH+v5p5TBpxpvGv2t/xxkZ4QG02KWPPtiRjSrnIByARfTKTZto3VFWmAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:04.731494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12029","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42c4334a53ba5f171caaefaca7d6e58c43bdb5b079f5bbcdb6e80f34d6fe9f7d","sha256:10b6b302dd61e3daf50076d31e224a44502a6d1746fda419f75c2aeffc9496d3"],"state_sha256":"cccdf16171a75982c466d4ae6acf5cb0af39e53b23f98007df432645a3a1b16f"}