{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K73RKSA3LW6AGJ25JP3O25EPYC","short_pith_number":"pith:K73RKSA3","schema_version":"1.0","canonical_sha256":"57f715481b5dbc03275d4bf6ed748fc0b1aad55bce5900aad347bd25bfb814f6","source":{"kind":"arxiv","id":"2405.04793","version":2},"attestation_state":"computed","paper":{"title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amrita Bhattacharjee, Huan Liu, Joshua Garland, Raha Moraffah","submitted_at":"2024-05-08T03:57:45Z","abstract_excerpt":"With the development and proliferation of large, complex, black-box models for solving many natural language processing (NLP) tasks, there is also an increasing necessity of methods to stress-test these models and provide some degree of interpretability or explainability. While counterfactual examples are useful in this regard, automated generation of counterfactuals is a data and resource intensive process. such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets, that may be infeasible to build in practice, especial"},"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":"2405.04793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-08T03:57:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"958a0c19353ba4caaa4ae6f4d8242eb4650739e926ec945404f280dd3ea1461c","abstract_canon_sha256":"3d2791498bf3edb7f3d5e424307d4d7884755464b388b14ebcbf906a7e40c06a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:07.857630Z","signature_b64":"5s3B9wtj0c66qHVqfusVyw5kiB0HzLvTmhrq8dmYD+r0zw7J77vg9NrZy9I9OEx9Ospm1N1PQlJFVLswNlvtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57f715481b5dbc03275d4bf6ed748fc0b1aad55bce5900aad347bd25bfb814f6","last_reissued_at":"2026-07-05T09:37:07.857117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:07.857117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amrita Bhattacharjee, Huan Liu, Joshua Garland, Raha Moraffah","submitted_at":"2024-05-08T03:57:45Z","abstract_excerpt":"With the development and proliferation of large, complex, black-box models for solving many natural language processing (NLP) tasks, there is also an increasing necessity of methods to stress-test these models and provide some degree of interpretability or explainability. While counterfactual examples are useful in this regard, automated generation of counterfactuals is a data and resource intensive process. such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets, that may be infeasible to build in practice, especial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04793","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/2405.04793/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":"2405.04793","created_at":"2026-07-05T09:37:07.857178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04793v2","created_at":"2026-07-05T09:37:07.857178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04793","created_at":"2026-07-05T09:37:07.857178+00:00"},{"alias_kind":"pith_short_12","alias_value":"K73RKSA3LW6A","created_at":"2026-07-05T09:37:07.857178+00:00"},{"alias_kind":"pith_short_16","alias_value":"K73RKSA3LW6AGJ25","created_at":"2026-07-05T09:37:07.857178+00:00"},{"alias_kind":"pith_short_8","alias_value":"K73RKSA3","created_at":"2026-07-05T09:37:07.857178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08696","citing_title":"Agentic Search for Counterfactual Recourse under Fixed LLM Budgets","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.06419","citing_title":"Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC","json":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC.json","graph_json":"https://pith.science/api/pith-number/K73RKSA3LW6AGJ25JP3O25EPYC/graph.json","events_json":"https://pith.science/api/pith-number/K73RKSA3LW6AGJ25JP3O25EPYC/events.json","paper":"https://pith.science/paper/K73RKSA3"},"agent_actions":{"view_html":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC","download_json":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC.json","view_paper":"https://pith.science/paper/K73RKSA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04793&json=true","fetch_graph":"https://pith.science/api/pith-number/K73RKSA3LW6AGJ25JP3O25EPYC/graph.json","fetch_events":"https://pith.science/api/pith-number/K73RKSA3LW6AGJ25JP3O25EPYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC/action/storage_attestation","attest_author":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC/action/author_attestation","sign_citation":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC/action/citation_signature","submit_replication":"https://pith.science/pith/K73RKSA3LW6AGJ25JP3O25EPYC/action/replication_record"}},"created_at":"2026-07-05T09:37:07.857178+00:00","updated_at":"2026-07-05T09:37:07.857178+00:00"}