{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HVYAOCLMHVWI4FYRDCWD2X7BOY","short_pith_number":"pith:HVYAOCLM","schema_version":"1.0","canonical_sha256":"3d7007096c3d6c8e171118ac3d5fe1760f1c8841f1b1a4190ea6f4f4ac6d20f4","source":{"kind":"arxiv","id":"2004.15020","version":3},"attestation_state":"computed","paper":{"title":"Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Austin Waters, Daniel Cer, Jason Baldridge, Yinfei Yang, Zarana Parekh","submitted_at":"2020-04-30T17:59:17Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.15020","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T17:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"42aff143c3c41b6679b06ca9e9ca26cdb496b79fa8f201a7dd628414af5d1408","abstract_canon_sha256":"3ad364ec37ac678b3f6a9d0338ba62006128b9a318d31f2862d97a01efbf67ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:00.018799Z","signature_b64":"yiQTfWYPgy/l+ap2tvmu8/zUljmEzSUGmRsdrm11QwtcMUAEJ89qqpGQ3h9izgG8ep/2iWlC/moCF3zngFL0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7007096c3d6c8e171118ac3d5fe1760f1c8841f1b1a4190ea6f4f4ac6d20f4","last_reissued_at":"2026-07-05T02:26:00.018376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:00.018376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Austin Waters, Daniel Cer, Jason Baldridge, Yinfei Yang, Zarana Parekh","submitted_at":"2020-04-30T17:59:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.15020","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.15020/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.15020","created_at":"2026-07-05T02:26:00.018432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.15020v3","created_at":"2026-07-05T02:26:00.018432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.15020","created_at":"2026-07-05T02:26:00.018432+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVYAOCLMHVWI","created_at":"2026-07-05T02:26:00.018432+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVYAOCLMHVWI4FYR","created_at":"2026-07-05T02:26:00.018432+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVYAOCLM","created_at":"2026-07-05T02:26:00.018432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30968","citing_title":"Variational Adapter for Cross-modal Similarity Representation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2402.11684","citing_title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","ref_index":119,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY","json":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY.json","graph_json":"https://pith.science/api/pith-number/HVYAOCLMHVWI4FYRDCWD2X7BOY/graph.json","events_json":"https://pith.science/api/pith-number/HVYAOCLMHVWI4FYRDCWD2X7BOY/events.json","paper":"https://pith.science/paper/HVYAOCLM"},"agent_actions":{"view_html":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY","download_json":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY.json","view_paper":"https://pith.science/paper/HVYAOCLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.15020&json=true","fetch_graph":"https://pith.science/api/pith-number/HVYAOCLMHVWI4FYRDCWD2X7BOY/graph.json","fetch_events":"https://pith.science/api/pith-number/HVYAOCLMHVWI4FYRDCWD2X7BOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY/action/storage_attestation","attest_author":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY/action/author_attestation","sign_citation":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY/action/citation_signature","submit_replication":"https://pith.science/pith/HVYAOCLMHVWI4FYRDCWD2X7BOY/action/replication_record"}},"created_at":"2026-07-05T02:26:00.018432+00:00","updated_at":"2026-07-05T02:26:00.018432+00:00"}