{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DLKAUXP6AMHMKDE5PU4TRPJOJN","short_pith_number":"pith:DLKAUXP6","schema_version":"1.0","canonical_sha256":"1ad40a5dfe030ec50c9d7d3938bd2e4b7d3abe1e28604a7aec47e8a9a0d12018","source":{"kind":"arxiv","id":"1903.02741","version":1},"attestation_state":"computed","paper":{"title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Chi Zhang, Feng Gao, Song-Chun Zhu, Yixin Zhu","submitted_at":"2019-03-07T06:28:44Z","abstract_excerpt":"Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and human intelligence in terms of higher-level vision problems, especially ones involving reasoning. Earlier attempts in equipping machines with high-level reasoning have hovered around Visual Question Answering (VQA), one typical task associating vision and language understanding. In this work, we propose a new dataset, built in the context of Raven's Progress"},"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":"1903.02741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-07T06:28:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a53553a5828913edb3ad61c565b0f2d665529677e5544d1ea80a1c263109b270","abstract_canon_sha256":"26a7d9e910387c75f136a39308dceccba0cd06eaf983a9b3989b34f897f1c5b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:51.251473Z","signature_b64":"EUCnytuTfEENfZiKMu7+RKgC/Ts6R7hpnhLvzggA0tHW26mOJZJ8+FAjO5u3vnSgbz+jlf1ZLbDDR1x91/TgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ad40a5dfe030ec50c9d7d3938bd2e4b7d3abe1e28604a7aec47e8a9a0d12018","last_reissued_at":"2026-05-17T23:51:51.250788Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:51.250788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Baoxiong Jia, Chi Zhang, Feng Gao, Song-Chun Zhu, Yixin Zhu","submitted_at":"2019-03-07T06:28:44Z","abstract_excerpt":"Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and tracking. Unfortunately, there is still an enormous performance gap between artificial vision systems and human intelligence in terms of higher-level vision problems, especially ones involving reasoning. Earlier attempts in equipping machines with high-level reasoning have hovered around Visual Question Answering (VQA), one typical task associating vision and language understanding. In this work, we propose a new dataset, built in the context of Raven's Progress"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02741","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1903.02741","created_at":"2026-05-17T23:51:51.250886+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02741v1","created_at":"2026-05-17T23:51:51.250886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02741","created_at":"2026-05-17T23:51:51.250886+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLKAUXP6AMHM","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLKAUXP6AMHMKDE5","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLKAUXP6","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN","json":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN.json","graph_json":"https://pith.science/api/pith-number/DLKAUXP6AMHMKDE5PU4TRPJOJN/graph.json","events_json":"https://pith.science/api/pith-number/DLKAUXP6AMHMKDE5PU4TRPJOJN/events.json","paper":"https://pith.science/paper/DLKAUXP6"},"agent_actions":{"view_html":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN","download_json":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN.json","view_paper":"https://pith.science/paper/DLKAUXP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02741&json=true","fetch_graph":"https://pith.science/api/pith-number/DLKAUXP6AMHMKDE5PU4TRPJOJN/graph.json","fetch_events":"https://pith.science/api/pith-number/DLKAUXP6AMHMKDE5PU4TRPJOJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN/action/storage_attestation","attest_author":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN/action/author_attestation","sign_citation":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN/action/citation_signature","submit_replication":"https://pith.science/pith/DLKAUXP6AMHMKDE5PU4TRPJOJN/action/replication_record"}},"created_at":"2026-05-17T23:51:51.250886+00:00","updated_at":"2026-05-17T23:51:51.250886+00:00"}