{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IGAPJOB4SQ2WXLZXZP7TJBVSTJ","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":"a5a5b3c1aebae7f708d3f5ade5d5b662fe43817c5991842339432e2101721e1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T17:45:38Z","title_canon_sha256":"d1bb2b8dbd19d383406430b5d903058f326c6b4768e5913f416d4c902e6b38e5"},"schema_version":"1.0","source":{"id":"2210.04873","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04873","created_at":"2026-07-05T05:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04873v2","created_at":"2026-07-05T05:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04873","created_at":"2026-07-05T05:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"IGAPJOB4SQ2W","created_at":"2026-07-05T05:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"IGAPJOB4SQ2WXLZX","created_at":"2026-07-05T05:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"IGAPJOB4","created_at":"2026-07-05T05:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:00f6c22f6041cef6f16e3c031d2f6251e130da47e6065bc67eeb740ffc1bb528","target":"graph","created_at":"2026-07-05T05:12:16Z","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/2210.04873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on generating counterfactuals only considered restricted classes of perturbations, limiting their effectiveness. We present COunterfactual Generation via Retrieval and Editing (CORE), a retrieval-augmented generation framework for creating diverse counterfactual perturbations for CDA. For each training example, CORE first performs a dense retrieval over a task-related u","authors_text":"Bhargavi Paranjape, Hannaneh Hajishirzi, Luke Zettlemoyer, Tanay Dixit","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T17:45:38Z","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04873","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:d23cc93ee21fc391fbcdb20e4d97ea1e50ec45fe45f0440f399a2948725668a6","target":"record","created_at":"2026-07-05T05:12:16Z","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":"a5a5b3c1aebae7f708d3f5ade5d5b662fe43817c5991842339432e2101721e1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T17:45:38Z","title_canon_sha256":"d1bb2b8dbd19d383406430b5d903058f326c6b4768e5913f416d4c902e6b38e5"},"schema_version":"1.0","source":{"id":"2210.04873","kind":"arxiv","version":2}},"canonical_sha256":"4180f4b83c94356baf37cbff3486b29a6c4db4033dfe8b7851bec888f5a48c87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4180f4b83c94356baf37cbff3486b29a6c4db4033dfe8b7851bec888f5a48c87","first_computed_at":"2026-07-05T05:12:16.500814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:16.500814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ywwZHWATDGEIbRbG2dRsFkyLAevFYP1ph1k5CwO9cR0yo4S4Rbq040d9dd7TlfKZIdxQpBsebOjbVLF0vXrAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:16.501211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04873","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d23cc93ee21fc391fbcdb20e4d97ea1e50ec45fe45f0440f399a2948725668a6","sha256:00f6c22f6041cef6f16e3c031d2f6251e130da47e6065bc67eeb740ffc1bb528"],"state_sha256":"17cc360b99210e7d3ee3451108e37d33e87947b9334dcb76df1df2ba3d177809"}