{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HULIEMLYIUGJ3YFSCRUJ4CV7GG","short_pith_number":"pith:HULIEMLY","canonical_record":{"source":{"id":"2501.00777","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T09:00:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b643c1cf13b4df5c880f25dbace62c00b214bf8e70e06372b4a8197643af3ee","abstract_canon_sha256":"e7da29df21c51553388ff62ef76f83c61f4545191597d13e154d199e28b748de"},"schema_version":"1.0"},"canonical_sha256":"3d16823178450c9de0b214689e0abf31bb7365d8ccdf18a572f725a88ee85c38","source":{"kind":"arxiv","id":"2501.00777","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00777","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00777v3","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00777","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"HULIEMLYIUGJ","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"HULIEMLYIUGJ3YFS","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"HULIEMLY","created_at":"2026-07-05T11:11:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HULIEMLYIUGJ3YFSCRUJ4CV7GG","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00777","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T09:00:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b643c1cf13b4df5c880f25dbace62c00b214bf8e70e06372b4a8197643af3ee","abstract_canon_sha256":"e7da29df21c51553388ff62ef76f83c61f4545191597d13e154d199e28b748de"},"schema_version":"1.0"},"canonical_sha256":"3d16823178450c9de0b214689e0abf31bb7365d8ccdf18a572f725a88ee85c38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:21.311273Z","signature_b64":"eP0Y5vqqtWOQeSJu5rgcFMY0ZIx3iUz0kVI17owFCWJexZ8A0exH7dVAbNldqc2F03YbB8IK0bQmc5Gb0hjgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d16823178450c9de0b214689e0abf31bb7365d8ccdf18a572f725a88ee85c38","last_reissued_at":"2026-07-05T11:11:21.310787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:21.310787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00777","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yu4By8j9NUnR0qhuLb2ZMwFUIboiiRVa77azg4Hv/8wYb1wsTmfQozIam3PH1pzuLp2+UTwDeO59HFhx+9ttDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:23:11.921589Z"},"content_sha256":"443436c8f9359402021c52ba887d8838c61aff28e46060f81b7feba2f640ba7a","schema_version":"1.0","event_id":"sha256:443436c8f9359402021c52ba887d8838c61aff28e46060f81b7feba2f640ba7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HULIEMLYIUGJ3YFSCRUJ4CV7GG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Luis Felipe Villa-Arenas, Nils Feldhus, Qianli Wang, Sebastian M\\\"oller, Simon Ostermann, Vera Schmitt","submitted_at":"2025-01-01T09:00:10Z","abstract_excerpt":"Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand model behavior. The automated generation of counterfactual examples remains a challenging task even for large language models (LLMs), despite their impressive performance on many tasks. In this paper, we first introduce ZeroCF, a faithful approach for leveraging important words derived from feature attribution methods to generate counterfactual examples in a zero-shot setting. Second, we present a new framework, FitCF, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00777","kind":"arxiv","version":3},"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/2501.00777/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":"2026-07-05T11:11:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+C/VP6+1EvkgX2rUVG00LtA1v7oRZP2ZbisOV5DLcXttIsfrWtYgYb+TLhwpMNRurITt3TF9gcvdrpmh93aUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:23:11.922233Z"},"content_sha256":"44ba986269dc9834177ec8cab2db36e6cf70ba940a431f91b8f91491f3e26dd0","schema_version":"1.0","event_id":"sha256:44ba986269dc9834177ec8cab2db36e6cf70ba940a431f91b8f91491f3e26dd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG/bundle.json","state_url":"https://pith.science/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG/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":"2026-08-09T15:23:11Z","links":{"resolver":"https://pith.science/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG","bundle":"https://pith.science/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG/bundle.json","state":"https://pith.science/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HULIEMLYIUGJ3YFSCRUJ4CV7GG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HULIEMLYIUGJ3YFSCRUJ4CV7GG","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":"e7da29df21c51553388ff62ef76f83c61f4545191597d13e154d199e28b748de","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T09:00:10Z","title_canon_sha256":"7b643c1cf13b4df5c880f25dbace62c00b214bf8e70e06372b4a8197643af3ee"},"schema_version":"1.0","source":{"id":"2501.00777","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00777","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00777v3","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00777","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"HULIEMLYIUGJ","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"HULIEMLYIUGJ3YFS","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"HULIEMLY","created_at":"2026-07-05T11:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:44ba986269dc9834177ec8cab2db36e6cf70ba940a431f91b8f91491f3e26dd0","target":"graph","created_at":"2026-07-05T11:11:21Z","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/2501.00777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand model behavior. The automated generation of counterfactual examples remains a challenging task even for large language models (LLMs), despite their impressive performance on many tasks. In this paper, we first introduce ZeroCF, a faithful approach for leveraging important words derived from feature attribution methods to generate counterfactual examples in a zero-shot setting. Second, we present a new framework, FitCF, w","authors_text":"Luis Felipe Villa-Arenas, Nils Feldhus, Qianli Wang, Sebastian M\\\"oller, Simon Ostermann, Vera Schmitt","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T09:00:10Z","title":"FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00777","kind":"arxiv","version":3},"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":"sha256:443436c8f9359402021c52ba887d8838c61aff28e46060f81b7feba2f640ba7a","target":"record","created_at":"2026-07-05T11:11:21Z","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":"e7da29df21c51553388ff62ef76f83c61f4545191597d13e154d199e28b748de","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T09:00:10Z","title_canon_sha256":"7b643c1cf13b4df5c880f25dbace62c00b214bf8e70e06372b4a8197643af3ee"},"schema_version":"1.0","source":{"id":"2501.00777","kind":"arxiv","version":3}},"canonical_sha256":"3d16823178450c9de0b214689e0abf31bb7365d8ccdf18a572f725a88ee85c38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d16823178450c9de0b214689e0abf31bb7365d8ccdf18a572f725a88ee85c38","first_computed_at":"2026-07-05T11:11:21.310787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:21.310787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eP0Y5vqqtWOQeSJu5rgcFMY0ZIx3iUz0kVI17owFCWJexZ8A0exH7dVAbNldqc2F03YbB8IK0bQmc5Gb0hjgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:21.311273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00777","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:443436c8f9359402021c52ba887d8838c61aff28e46060f81b7feba2f640ba7a","sha256:44ba986269dc9834177ec8cab2db36e6cf70ba940a431f91b8f91491f3e26dd0"],"state_sha256":"c1a5b8eff3a77b00b47ceb01a1cede71627306a471b8abd6d892b3385f18f543"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6rmiCHmlAeQPRoegOXx4DTM3iXpQZ+HTGMS4za508nQn4U1ooXhawjMbyPkRyg5InMyebyJJlMlhv40GzYECCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:23:11.927333Z","bundle_sha256":"08610b334c687875e220576efb65223735071c62fc8449bbcbffab5507441991"}}