{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UBZLRB77P5L3SKPUCWTX7PURMR","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":"b9c79c0319ae61e49eb8baefcae05bc2858b1b5105f43946b4505c25da9fa46e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:55:15Z","title_canon_sha256":"ceaa1cd5553674dd3d319ac9c26523d842d9fec233fc965412b75be4733b7948"},"schema_version":"1.0","source":{"id":"2605.22651","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22651","created_at":"2026-05-22T02:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22651v1","created_at":"2026-05-22T02:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22651","created_at":"2026-05-22T02:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"UBZLRB77P5L3","created_at":"2026-05-22T02:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"UBZLRB77P5L3SKPU","created_at":"2026-05-22T02:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"UBZLRB77","created_at":"2026-05-22T02:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:e9be4d04288de1029da22fcabc19fe1974319fa6b8603f549040d6b938d832a3","target":"graph","created_at":"2026-05-22T02:04:48Z","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/2605.22651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP-style contrastive pretraining typically curates web-scale image-text pairs using sample-level filtering signals, often based on pair-level alignment. We show that this signal saturates: once coarse mismatches are removed, stricter global filtering no longer tracks the compositional supervision provided by the retained captions. The reason is structural - a global score conflates whether a pair is broadly plausible with whether the individual object, attribute, and relation phrases inside the caption materially support the image-text match. The latter is what compositional generalization d","authors_text":"Hyejin Go, Hyesong Choi, Semi Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:55:15Z","title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22651","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:fec97798a0fcfb48e5c4be596f661c1e93b306c130bb98c6e0c20c227c1bbed6","target":"record","created_at":"2026-05-22T02:04:48Z","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":"b9c79c0319ae61e49eb8baefcae05bc2858b1b5105f43946b4505c25da9fa46e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:55:15Z","title_canon_sha256":"ceaa1cd5553674dd3d319ac9c26523d842d9fec233fc965412b75be4733b7948"},"schema_version":"1.0","source":{"id":"2605.22651","kind":"arxiv","version":1}},"canonical_sha256":"a072b887ff7f57b929f415a77fbe9164664e2b49fd3ea461d401e63819e42181","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a072b887ff7f57b929f415a77fbe9164664e2b49fd3ea461d401e63819e42181","first_computed_at":"2026-05-22T02:04:48.244102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:48.244102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nKeUxDSgv0yVNV/5Cg3b26VTWC9nHefiIU0iaQ6rKFNZij5cLfc4AItWOF6jXSRU3SMg/GZZGMAdNj2/ZEi0Dw==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:48.244965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22651","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fec97798a0fcfb48e5c4be596f661c1e93b306c130bb98c6e0c20c227c1bbed6","sha256:e9be4d04288de1029da22fcabc19fe1974319fa6b8603f549040d6b938d832a3"],"state_sha256":"1c8d87d2781f53c62d391cdf6870fbf77973ec8ad318d0e9f0267d8b454bed29"}