{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UBZLRB77P5L3SKPUCWTX7PURMR","short_pith_number":"pith:UBZLRB77","schema_version":"1.0","canonical_sha256":"a072b887ff7f57b929f415a77fbe9164664e2b49fd3ea461d401e63819e42181","source":{"kind":"arxiv","id":"2605.22651","version":1},"attestation_state":"computed","paper":{"title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyejin Go, Hyesong Choi, Semi Lee","submitted_at":"2026-05-21T15:55:15Z","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"},"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":"2605.22651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:55:15Z","cross_cats_sorted":[],"title_canon_sha256":"ceaa1cd5553674dd3d319ac9c26523d842d9fec233fc965412b75be4733b7948","abstract_canon_sha256":"b9c79c0319ae61e49eb8baefcae05bc2858b1b5105f43946b4505c25da9fa46e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:48.244965Z","signature_b64":"nKeUxDSgv0yVNV/5Cg3b26VTWC9nHefiIU0iaQ6rKFNZij5cLfc4AItWOF6jXSRU3SMg/GZZGMAdNj2/ZEi0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a072b887ff7f57b929f415a77fbe9164664e2b49fd3ea461d401e63819e42181","last_reissued_at":"2026-05-22T02:04:48.244102Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:48.244102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyejin Go, Hyesong Choi, Semi Lee","submitted_at":"2026-05-21T15:55:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22651","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.22651/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2605.22651","created_at":"2026-05-22T02:04:48.244262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22651v1","created_at":"2026-05-22T02:04:48.244262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22651","created_at":"2026-05-22T02:04:48.244262+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBZLRB77P5L3","created_at":"2026-05-22T02:04:48.244262+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBZLRB77P5L3SKPU","created_at":"2026-05-22T02:04:48.244262+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBZLRB77","created_at":"2026-05-22T02:04:48.244262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR","json":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR.json","graph_json":"https://pith.science/api/pith-number/UBZLRB77P5L3SKPUCWTX7PURMR/graph.json","events_json":"https://pith.science/api/pith-number/UBZLRB77P5L3SKPUCWTX7PURMR/events.json","paper":"https://pith.science/paper/UBZLRB77"},"agent_actions":{"view_html":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR","download_json":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR.json","view_paper":"https://pith.science/paper/UBZLRB77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22651&json=true","fetch_graph":"https://pith.science/api/pith-number/UBZLRB77P5L3SKPUCWTX7PURMR/graph.json","fetch_events":"https://pith.science/api/pith-number/UBZLRB77P5L3SKPUCWTX7PURMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR/action/storage_attestation","attest_author":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR/action/author_attestation","sign_citation":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR/action/citation_signature","submit_replication":"https://pith.science/pith/UBZLRB77P5L3SKPUCWTX7PURMR/action/replication_record"}},"created_at":"2026-05-22T02:04:48.244262+00:00","updated_at":"2026-05-22T02:04:48.244262+00:00"}