{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HNVBROS3CGOSJEP5MGLQTT7KNM","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":"c681a4049f4d3c7ec7aa805e8eb231fda5a4a87341eabdf1a381fb31582b3737","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T17:59:54Z","title_canon_sha256":"2e0ee427a499f4b09e5ea30299c8a746c0159ab2faa36fb69ad52b31f970b4e9"},"schema_version":"1.0","source":{"id":"2305.17540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17540","created_at":"2026-07-05T06:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17540v2","created_at":"2026-07-05T06:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17540","created_at":"2026-07-05T06:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"HNVBROS3CGOS","created_at":"2026-07-05T06:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"HNVBROS3CGOSJEP5","created_at":"2026-07-05T06:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"HNVBROS3","created_at":"2026-07-05T06:15:33Z"}],"graph_snapshots":[{"event_id":"sha256:7a0b353bfd4ead13c4f6a3092903d7bd63f5336cf4033f68864abae38b75332d","target":"graph","created_at":"2026-07-05T06:15:33Z","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/2305.17540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-caption pretraining has been quite successfully used for downstream vision tasks like zero-shot image classification and object detection. However, image-caption pretraining is still a hard problem -- it requires multiple concepts (nouns) from captions to be aligned to several objects in images. To tackle this problem, we go to the roots -- the best learner, children. We take inspiration from cognitive science studies dealing with children's language learning to propose a curriculum learning framework. The learning begins with easy-to-align image caption pairs containing one concept per ","authors_text":"Alireza Zareian, Bo Wu, Hammad A. Ayyubi, Rahul Lokesh, Shih-Fu Chang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T17:59:54Z","title":"Learning from Children: Improving Image-Caption Pretraining via Curriculum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17540","kind":"arxiv","version":2},"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":"sha256:983d7b62aff18cd2160b7fc69368e7d3cebc5d5412c23cea189f02f2cb62cb41","target":"record","created_at":"2026-07-05T06:15:33Z","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":"c681a4049f4d3c7ec7aa805e8eb231fda5a4a87341eabdf1a381fb31582b3737","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T17:59:54Z","title_canon_sha256":"2e0ee427a499f4b09e5ea30299c8a746c0159ab2faa36fb69ad52b31f970b4e9"},"schema_version":"1.0","source":{"id":"2305.17540","kind":"arxiv","version":2}},"canonical_sha256":"3b6a18ba5b119d2491fd619709cfea6b363dc7b6cb2d5668176bb524663f878e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b6a18ba5b119d2491fd619709cfea6b363dc7b6cb2d5668176bb524663f878e","first_computed_at":"2026-07-05T06:15:33.179381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:33.179381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WfM58T0NmXVNQc6owDBalavhDqJYKh1+wMczsWXyX842hYY/gdBcjb6r4lTCblDGy4Z1TrPlbfewpQXUxaJBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:33.179888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:983d7b62aff18cd2160b7fc69368e7d3cebc5d5412c23cea189f02f2cb62cb41","sha256:7a0b353bfd4ead13c4f6a3092903d7bd63f5336cf4033f68864abae38b75332d"],"state_sha256":"902625b35f84fcdfdc23735bc102e94292eb5950ee5353a37fe74a72b3a09736"}