{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CQI4C7EV763HIMYLGPJNF4CIOX","short_pith_number":"pith:CQI4C7EV","canonical_record":{"source":{"id":"2407.03993","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T15:13:59Z","cross_cats_sorted":[],"title_canon_sha256":"a69f09bde146cc77398a05f0995f850a8cf29268a96154eb32f812d69cecf433","abstract_canon_sha256":"f7ded1fa7b49d179144ff32827aca7e4c0e4f8534bb8cb76107919444fe73f0c"},"schema_version":"1.0"},"canonical_sha256":"1411c17c95ffb674330b33d2d2f04875eb42728a836682472b20e148e37b2832","source":{"kind":"arxiv","id":"2407.03993","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03993","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03993v2","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03993","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"CQI4C7EV763H","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"CQI4C7EV763HIMYL","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"CQI4C7EV","created_at":"2026-07-05T09:16:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CQI4C7EV763HIMYLGPJNF4CIOX","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03993","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T15:13:59Z","cross_cats_sorted":[],"title_canon_sha256":"a69f09bde146cc77398a05f0995f850a8cf29268a96154eb32f812d69cecf433","abstract_canon_sha256":"f7ded1fa7b49d179144ff32827aca7e4c0e4f8534bb8cb76107919444fe73f0c"},"schema_version":"1.0"},"canonical_sha256":"1411c17c95ffb674330b33d2d2f04875eb42728a836682472b20e148e37b2832","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:19.340422Z","signature_b64":"KrDoFMpuyUuIuLBewnGhYH2XNhioOrnMLC39XSjRRCeF/6Rm1QRGBIEqpbuu3wQHD6T4qj6Bbt8keWlQTuwrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1411c17c95ffb674330b33d2d2f04875eb42728a836682472b20e148e37b2832","last_reissued_at":"2026-07-05T09:16:19.339938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:19.339938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03993","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"80atQf1ENiHOXxwmGW7cW348st26j0OdtEa1Zyo8FinV3+wb6gIM3Jvv7JMI6VI2BW4+YPtnYGjyY/opcLloCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:20:30.951786Z"},"content_sha256":"4251654a89676030a731e5e9bcdad1d7ffd0f202c22dc3a517a57434d0be33fb","schema_version":"1.0","event_id":"sha256:4251654a89676030a731e5e9bcdad1d7ffd0f202c22dc3a517a57434d0be33fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CQI4C7EV763HIMYLGPJNF4CIOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Natural Language Counterfactual Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiaoqi Qiu, Xu Guo, Yongjie Wang, Yuhong Feng, Yu Yue, Zhiqi Shen, Zhiwei Zeng","submitted_at":"2024-07-04T15:13:59Z","abstract_excerpt":"Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's predictions by highlighting which words significantly influence the outcomes. Additionally, they can be used to detect model fairness issues and augment the training data to enhance the model's robustness. A substantial amount of research has been conducted to generate counterfactuals for various NLP tasks, employing different models and methodologies. With the ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03993","kind":"arxiv","version":2},"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/2407.03993/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cCVVjG/JVB5PG1P/wxy2RxUgM2i/iVAeQca1IldsJ5EaorO+FwSpJJHiG2bYCdCpkJdXlAOvjiSa2Jbq502Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:20:30.952325Z"},"content_sha256":"7c59a2395717720770bd9e8ac723a1cd000fd537b960fd37efd285a470e398a3","schema_version":"1.0","event_id":"sha256:7c59a2395717720770bd9e8ac723a1cd000fd537b960fd37efd285a470e398a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQI4C7EV763HIMYLGPJNF4CIOX/bundle.json","state_url":"https://pith.science/pith/CQI4C7EV763HIMYLGPJNF4CIOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQI4C7EV763HIMYLGPJNF4CIOX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T05:20:30Z","links":{"resolver":"https://pith.science/pith/CQI4C7EV763HIMYLGPJNF4CIOX","bundle":"https://pith.science/pith/CQI4C7EV763HIMYLGPJNF4CIOX/bundle.json","state":"https://pith.science/pith/CQI4C7EV763HIMYLGPJNF4CIOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQI4C7EV763HIMYLGPJNF4CIOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQI4C7EV763HIMYLGPJNF4CIOX","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":"f7ded1fa7b49d179144ff32827aca7e4c0e4f8534bb8cb76107919444fe73f0c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T15:13:59Z","title_canon_sha256":"a69f09bde146cc77398a05f0995f850a8cf29268a96154eb32f812d69cecf433"},"schema_version":"1.0","source":{"id":"2407.03993","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03993","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03993v2","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03993","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_12","alias_value":"CQI4C7EV763H","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_16","alias_value":"CQI4C7EV763HIMYL","created_at":"2026-07-05T09:16:19Z"},{"alias_kind":"pith_short_8","alias_value":"CQI4C7EV","created_at":"2026-07-05T09:16:19Z"}],"graph_snapshots":[{"event_id":"sha256:7c59a2395717720770bd9e8ac723a1cd000fd537b960fd37efd285a470e398a3","target":"graph","created_at":"2026-07-05T09:16:19Z","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/2407.03993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's predictions by highlighting which words significantly influence the outcomes. Additionally, they can be used to detect model fairness issues and augment the training data to enhance the model's robustness. A substantial amount of research has been conducted to generate counterfactuals for various NLP tasks, employing different models and methodologies. With the ra","authors_text":"Xiaoqi Qiu, Xu Guo, Yongjie Wang, Yuhong Feng, Yu Yue, Zhiqi Shen, Zhiwei Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T15:13:59Z","title":"A Survey on Natural Language Counterfactual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03993","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":"sha256:4251654a89676030a731e5e9bcdad1d7ffd0f202c22dc3a517a57434d0be33fb","target":"record","created_at":"2026-07-05T09:16:19Z","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":"f7ded1fa7b49d179144ff32827aca7e4c0e4f8534bb8cb76107919444fe73f0c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T15:13:59Z","title_canon_sha256":"a69f09bde146cc77398a05f0995f850a8cf29268a96154eb32f812d69cecf433"},"schema_version":"1.0","source":{"id":"2407.03993","kind":"arxiv","version":2}},"canonical_sha256":"1411c17c95ffb674330b33d2d2f04875eb42728a836682472b20e148e37b2832","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1411c17c95ffb674330b33d2d2f04875eb42728a836682472b20e148e37b2832","first_computed_at":"2026-07-05T09:16:19.339938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:19.339938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KrDoFMpuyUuIuLBewnGhYH2XNhioOrnMLC39XSjRRCeF/6Rm1QRGBIEqpbuu3wQHD6T4qj6Bbt8keWlQTuwrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:19.340422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03993","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4251654a89676030a731e5e9bcdad1d7ffd0f202c22dc3a517a57434d0be33fb","sha256:7c59a2395717720770bd9e8ac723a1cd000fd537b960fd37efd285a470e398a3"],"state_sha256":"ede86f20eefc79f0929f0177d445d865b6acc9c21586ec5ef4d6f4a2f4bbb76f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnfMOQKVTt8//MZUNw6YzwvpYcK4US0hi1jgu8dwcU6cRC1HPf95JrTvKaWfpNBxT9sdHX1UWX+NUbVtNV39AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:20:30.956184Z","bundle_sha256":"0dfccefc895ce134a1fb5cdbf5bbeb7d85a7c014f4b0481ee84f97675ab9335c"}}