{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OWGCJXXATSFDHK7MYU6TV73KIP","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":"31def42bf02da1237d4feb79a5334410a86f50dd94cd5d20390e373533e28d4f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-29T07:45:56Z","title_canon_sha256":"01bf3bc4b8c7f90e640baa326b13d6273976a183a73da1ef90b744a3ce3bf493"},"schema_version":"1.0","source":{"id":"2207.14525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.14525","created_at":"2026-07-05T04:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"2207.14525v1","created_at":"2026-07-05T04:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14525","created_at":"2026-07-05T04:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"OWGCJXXATSFD","created_at":"2026-07-05T04:44:35Z"},{"alias_kind":"pith_short_16","alias_value":"OWGCJXXATSFDHK7M","created_at":"2026-07-05T04:44:35Z"},{"alias_kind":"pith_short_8","alias_value":"OWGCJXXA","created_at":"2026-07-05T04:44:35Z"}],"graph_snapshots":[{"event_id":"sha256:d2093703fd183729fb46694d90a580efbd4987d2952761c35963b844b4119eb8","target":"graph","created_at":"2026-07-05T04:44:35Z","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/2207.14525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much smaller amount of paired data, augmented with a curriculum learning algorithm to learn fine-grained vision-language alignments. TOnICS (Training with Ontology-Informed Contrastive Sampling) initially samples minibatches whose image-text pairs contain a wide variety of objects to learn object-level alignment, and progressively samples minibatches where all imag","authors_text":"Jesse Thomason, Tejas Srinivasan, Xiang Ren","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-29T07:45:56Z","title":"Curriculum Learning for Data-Efficient Vision-Language Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14525","kind":"arxiv","version":1},"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":"sha256:36e48df5a15dd83c2d7ae9b3bf3932ded6d99f0bf74bff252e364ae8f0a37bd6","target":"record","created_at":"2026-07-05T04:44:35Z","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":"31def42bf02da1237d4feb79a5334410a86f50dd94cd5d20390e373533e28d4f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-29T07:45:56Z","title_canon_sha256":"01bf3bc4b8c7f90e640baa326b13d6273976a183a73da1ef90b744a3ce3bf493"},"schema_version":"1.0","source":{"id":"2207.14525","kind":"arxiv","version":1}},"canonical_sha256":"758c24dee09c8a33abecc53d3aff6a43d25901997970aff099b3fa88f8da07e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"758c24dee09c8a33abecc53d3aff6a43d25901997970aff099b3fa88f8da07e5","first_computed_at":"2026-07-05T04:44:35.189790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:35.189790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D++ZCUIDYs5fzFqwUrS+Ke0I6XvVGrT467Tcpcw6VzsdgL8xMA132RyTjKnoyPpk4T9RDHabt1NO845fNtslDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:35.190136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.14525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36e48df5a15dd83c2d7ae9b3bf3932ded6d99f0bf74bff252e364ae8f0a37bd6","sha256:d2093703fd183729fb46694d90a580efbd4987d2952761c35963b844b4119eb8"],"state_sha256":"39bfc4df8da206c8d93dbe660cb949dff86764819c79be5362aa742dadb2a62d"}