{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HVYAOCLMHVWI4FYRDCWD2X7BOY","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":"3ad364ec37ac678b3f6a9d0338ba62006128b9a318d31f2862d97a01efbf67ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:59:17Z","title_canon_sha256":"42aff143c3c41b6679b06ca9e9ca26cdb496b79fa8f201a7dd628414af5d1408"},"schema_version":"1.0","source":{"id":"2004.15020","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.15020","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"arxiv_version","alias_value":"2004.15020v3","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.15020","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"pith_short_12","alias_value":"HVYAOCLMHVWI","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"HVYAOCLMHVWI4FYR","created_at":"2026-07-05T02:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"HVYAOCLM","created_at":"2026-07-05T02:26:00Z"}],"graph_snapshots":[{"event_id":"sha256:1aea3a6fec11b9219839e5bdc9c5f75d49d932278a311fe23fcc9d511b22ca4d","target":"graph","created_at":"2026-07-05T02:26:00Z","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/2004.15020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By supporting multi-modal retrieval training and evaluation, image captioning datasets have spurred remarkable progress on representation learning. Unfortunately, datasets have limited cross-modal associations: images are not paired with other images, captions are only paired with other captions of the same image, there are no negative associations and there are missing positive cross-modal associations. This undermines research into how inter-modality learning impacts intra-modality tasks. We address this gap with Crisscrossed Captions (CxC), an extension of the MS-COCO dataset with human sem","authors_text":"Austin Waters, Daniel Cer, Jason Baldridge, Yinfei Yang, Zarana Parekh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:59:17Z","title":"Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.15020","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":"sha256:544c02595c6021f403786e35ab5a8595df24f291e67f4ff732bc1d2fc11813f5","target":"record","created_at":"2026-07-05T02:26:00Z","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":"3ad364ec37ac678b3f6a9d0338ba62006128b9a318d31f2862d97a01efbf67ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:59:17Z","title_canon_sha256":"42aff143c3c41b6679b06ca9e9ca26cdb496b79fa8f201a7dd628414af5d1408"},"schema_version":"1.0","source":{"id":"2004.15020","kind":"arxiv","version":3}},"canonical_sha256":"3d7007096c3d6c8e171118ac3d5fe1760f1c8841f1b1a4190ea6f4f4ac6d20f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d7007096c3d6c8e171118ac3d5fe1760f1c8841f1b1a4190ea6f4f4ac6d20f4","first_computed_at":"2026-07-05T02:26:00.018376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:00.018376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yiQTfWYPgy/l+ap2tvmu8/zUljmEzSUGmRsdrm11QwtcMUAEJ89qqpGQ3h9izgG8ep/2iWlC/moCF3zngFL0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:00.018799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.15020","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:544c02595c6021f403786e35ab5a8595df24f291e67f4ff732bc1d2fc11813f5","sha256:1aea3a6fec11b9219839e5bdc9c5f75d49d932278a311fe23fcc9d511b22ca4d"],"state_sha256":"992f60a48b5e9c3ae521b909f072f5cd62b676df82eb0f4e17642edf969e8d27"}