{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3W5OQ2UEB42V6DSPM4ZCQXHPSJ","short_pith_number":"pith:3W5OQ2UE","canonical_record":{"source":{"id":"2505.13972","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"85bffeb3ea76b8efc60c359f35574aa38d7f082c630879d2e83ea9a339e4112b","abstract_canon_sha256":"5d29a688d0f57c35289b07e92c33be1b6d9b3048f2eb18cebfe28db34e6b49b0"},"schema_version":"1.0"},"canonical_sha256":"ddbae86a840f355f0e4f6732285cef92792ace0b0b5164ef4c0061a7bb441da5","source":{"kind":"arxiv","id":"2505.13972","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13972","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13972v3","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13972","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"3W5OQ2UEB42V","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"3W5OQ2UEB42V6DSP","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"3W5OQ2UE","created_at":"2026-07-05T12:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3W5OQ2UEB42V6DSPM4ZCQXHPSJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13972","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"85bffeb3ea76b8efc60c359f35574aa38d7f082c630879d2e83ea9a339e4112b","abstract_canon_sha256":"5d29a688d0f57c35289b07e92c33be1b6d9b3048f2eb18cebfe28db34e6b49b0"},"schema_version":"1.0"},"canonical_sha256":"ddbae86a840f355f0e4f6732285cef92792ace0b0b5164ef4c0061a7bb441da5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:01.305478Z","signature_b64":"vKyLWt3cIHTZa8FUh0lEU2n3kKwtxY9FbyHh2GFihmL5+w3FRpA+c4PElPBHAabinEgkh1QfPS5caFh1bZq1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddbae86a840f355f0e4f6732285cef92792ace0b0b5164ef4c0061a7bb441da5","last_reissued_at":"2026-07-05T12:00:01.305023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:01.305023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13972","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":"2026-07-05T12:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qC1t7mBYaKp6VcyVYj+gZU7W7aYRVTq314Y+sE3CQaFv0uXw1vzylQdtQW+yzq0l3OSZQIzAQreWUhyD5lOcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:21:01.740460Z"},"content_sha256":"cc8bc61344f2bddf8a57af02726a53e3d04f9762b68420d762b0ca9d31fda25c","schema_version":"1.0","event_id":"sha256:cc8bc61344f2bddf8a57af02726a53e3d04f9762b68420d762b0ca9d31fda25c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3W5OQ2UEB42V6DSPM4ZCQXHPSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christin Seifert, Luis Felipe Villa-Arenas, Nils Feldhus, Qianli Wang, Sebastian M\\\"oller, Van Bach Nguyen, Vera Schmitt","submitted_at":"2025-05-20T06:12:17Z","abstract_excerpt":"Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the selection of the judge model used to evaluate label flipping, the primary metric for assessing the validity of generated counterfactuals for CDA, yields inconsistent results. To decipher this, we define four types of relationships between the counterfactual generator and judge models: being the same model, belonging to the same model family, being independent models, and having an distillation relationship. Through ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13972","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/2505.13972/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":"2026-07-05T12:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TjhaWxc/yJfVYzIW9oYD3uat33zCz7RrInqvyuY4olrjHAewiiEMV0dv6K/6jDA/48PgG0NKpDDMULRRnVC9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:21:01.740960Z"},"content_sha256":"bc3318d3a5bfe57e2021670cab58cdbccdcd921081e40d682d26f8ad79cbb96e","schema_version":"1.0","event_id":"sha256:bc3318d3a5bfe57e2021670cab58cdbccdcd921081e40d682d26f8ad79cbb96e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ/bundle.json","state_url":"https://pith.science/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ/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":"2026-08-09T09:21:01Z","links":{"resolver":"https://pith.science/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ","bundle":"https://pith.science/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ/bundle.json","state":"https://pith.science/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3W5OQ2UEB42V6DSPM4ZCQXHPSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3W5OQ2UEB42V6DSPM4ZCQXHPSJ","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":"5d29a688d0f57c35289b07e92c33be1b6d9b3048f2eb18cebfe28db34e6b49b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:17Z","title_canon_sha256":"85bffeb3ea76b8efc60c359f35574aa38d7f082c630879d2e83ea9a339e4112b"},"schema_version":"1.0","source":{"id":"2505.13972","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13972","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13972v3","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13972","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"3W5OQ2UEB42V","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"3W5OQ2UEB42V6DSP","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"3W5OQ2UE","created_at":"2026-07-05T12:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:bc3318d3a5bfe57e2021670cab58cdbccdcd921081e40d682d26f8ad79cbb96e","target":"graph","created_at":"2026-07-05T12:00:01Z","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/2505.13972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the selection of the judge model used to evaluate label flipping, the primary metric for assessing the validity of generated counterfactuals for CDA, yields inconsistent results. To decipher this, we define four types of relationships between the counterfactual generator and judge models: being the same model, belonging to the same model family, being independent models, and having an distillation relationship. Through ex","authors_text":"Christin Seifert, Luis Felipe Villa-Arenas, Nils Feldhus, Qianli Wang, Sebastian M\\\"oller, Van Bach Nguyen, Vera Schmitt","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:17Z","title":"Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13972","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:cc8bc61344f2bddf8a57af02726a53e3d04f9762b68420d762b0ca9d31fda25c","target":"record","created_at":"2026-07-05T12:00:01Z","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":"5d29a688d0f57c35289b07e92c33be1b6d9b3048f2eb18cebfe28db34e6b49b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T06:12:17Z","title_canon_sha256":"85bffeb3ea76b8efc60c359f35574aa38d7f082c630879d2e83ea9a339e4112b"},"schema_version":"1.0","source":{"id":"2505.13972","kind":"arxiv","version":3}},"canonical_sha256":"ddbae86a840f355f0e4f6732285cef92792ace0b0b5164ef4c0061a7bb441da5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddbae86a840f355f0e4f6732285cef92792ace0b0b5164ef4c0061a7bb441da5","first_computed_at":"2026-07-05T12:00:01.305023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:01.305023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vKyLWt3cIHTZa8FUh0lEU2n3kKwtxY9FbyHh2GFihmL5+w3FRpA+c4PElPBHAabinEgkh1QfPS5caFh1bZq1Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:01.305478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13972","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc8bc61344f2bddf8a57af02726a53e3d04f9762b68420d762b0ca9d31fda25c","sha256:bc3318d3a5bfe57e2021670cab58cdbccdcd921081e40d682d26f8ad79cbb96e"],"state_sha256":"41d4ee8f5640cb0a2cf814190db6acd620c11dfe144cdcf3fdde0650d9da2df3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+IyGZ8OPu/ZqM2WdC5aHjo2JcoDZhvxZ9Rn062/d0z2/06CUWWmkIXQ/BuUYNZvmcNnpLYQc42WtaDfReehDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:21:01.745165Z","bundle_sha256":"7817d29deff91d0c5fadc4d1266dec24b404e99fbce527e349f2ecdc29985e69"}}