{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EY3CHX2TU3WKII2LGXWROXH4KB","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":"5099bc20e262ccb800096c5f70aa3e33b6faea3c6520f8a9796477124d3b00ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T16:52:02Z","title_canon_sha256":"b6857c46578383139f94d85494e1098d500ffd4c154373b7921e74dcc98a8683"},"schema_version":"1.0","source":{"id":"2502.18326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18326","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18326v1","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18326","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"EY3CHX2TU3WK","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"EY3CHX2TU3WKII2L","created_at":"2026-07-05T10:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"EY3CHX2T","created_at":"2026-07-05T10:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:3f59ba10961122dbe8ca7782aaccb22854c877f6c5651f5a9ac853cc95ac2e4a","target":"graph","created_at":"2026-07-05T10:19:52Z","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/2502.18326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the success conditions for compositional generalization of CLIP models on real-world data through performance prediction. Prior work shows that CLIP requires exponentially more pretraining data for linear performance gains on individual concepts. This sample-inefficient scaling could be mitigated if CLIP systematically understood new inputs as compositions of learned components, allowing rare observation to be mapped to common concepts. To explore CLIP's compositional generalization ability, we filter retrieval corpora for samples with object combinations not present in the pret","authors_text":"Ameya Prabhu, Matthias Bethge, Thadd\\\"aus Wiedemer, Wieland Brendel, Yash Sharma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T16:52:02Z","title":"Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18326","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":"sha256:1f77847fff3ed1379ee2ff4aa02ca9340baac5ee6dbb4d24490a6c0e3f70c032","target":"record","created_at":"2026-07-05T10:19:52Z","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":"5099bc20e262ccb800096c5f70aa3e33b6faea3c6520f8a9796477124d3b00ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T16:52:02Z","title_canon_sha256":"b6857c46578383139f94d85494e1098d500ffd4c154373b7921e74dcc98a8683"},"schema_version":"1.0","source":{"id":"2502.18326","kind":"arxiv","version":1}},"canonical_sha256":"263623df53a6eca4234b35ed175cfc506fc51bbde44f086e3683d47a9aa0a77a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"263623df53a6eca4234b35ed175cfc506fc51bbde44f086e3683d47a9aa0a77a","first_computed_at":"2026-07-05T10:19:52.252694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:52.252694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Us7u467NwIIbLD5HwxeN1BOmzbLmFotfKA3U/8cod6A4hXq1AWpzyFxcLrgSlSGvW3LjoJBeqe67SNcAa013DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:52.253193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f77847fff3ed1379ee2ff4aa02ca9340baac5ee6dbb4d24490a6c0e3f70c032","sha256:3f59ba10961122dbe8ca7782aaccb22854c877f6c5651f5a9ac853cc95ac2e4a"],"state_sha256":"b5888ba259515b8d0bfed251009e97a0aa75a11bd79e91478415bdf01a4f57f1"}