{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B2XXM56WFLICB2SCVAV4YF4SEQ","short_pith_number":"pith:B2XXM56W","schema_version":"1.0","canonical_sha256":"0eaf7677d62ad020ea42a82bcc1792241b38c582b5b654aa2a5650ab85db38d7","source":{"kind":"arxiv","id":"2411.10565","version":3},"attestation_state":"computed","paper":{"title":"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chanchal K. Roy, Md. Abdul Awal, Mrigank Rochan","submitted_at":"2024-11-15T20:25:32Z","abstract_excerpt":"Large Language Model (LLM)-generated data is increasingly used in software analytics, but it is unclear how this data compares to human-written data, particularly when models are exposed to adversarial scenarios. Adversarial attacks can compromise the reliability and security of software systems, so understanding how LLM-generated data performs under these conditions, compared to human-written data, which serves as the benchmark for model performance, can provide valuable insights into whether LLM-generated data offers similar robustness and effectiveness. To address this gap, we systematicall"},"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":"2411.10565","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-15T20:25:32Z","cross_cats_sorted":[],"title_canon_sha256":"8b75c30fbbbcc23ba7343747ae8b232a6197d0dbace7c7f2534c8ab944c05fef","abstract_canon_sha256":"6a15eb0f49b3243c6cd78ae52879a5f307a7033af5a231bc4a2d174cfcbfa45e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:46.346479Z","signature_b64":"V8U0D/tk2l57L32VBSav4sups71uoMZXS5BRqHWqtCJEGF9V3hD1w6oJ3zwRpzVrTe73g+Ut6tiC6HXi4/UtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eaf7677d62ad020ea42a82bcc1792241b38c582b5b654aa2a5650ab85db38d7","last_reissued_at":"2026-07-05T10:58:46.345924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:46.345924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chanchal K. Roy, Md. Abdul Awal, Mrigank Rochan","submitted_at":"2024-11-15T20:25:32Z","abstract_excerpt":"Large Language Model (LLM)-generated data is increasingly used in software analytics, but it is unclear how this data compares to human-written data, particularly when models are exposed to adversarial scenarios. Adversarial attacks can compromise the reliability and security of software systems, so understanding how LLM-generated data performs under these conditions, compared to human-written data, which serves as the benchmark for model performance, can provide valuable insights into whether LLM-generated data offers similar robustness and effectiveness. To address this gap, we systematicall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10565","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/2411.10565/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":"2411.10565","created_at":"2026-07-05T10:58:46.345983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10565v3","created_at":"2026-07-05T10:58:46.345983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10565","created_at":"2026-07-05T10:58:46.345983+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2XXM56WFLIC","created_at":"2026-07-05T10:58:46.345983+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2XXM56WFLICB2SC","created_at":"2026-07-05T10:58:46.345983+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2XXM56W","created_at":"2026-07-05T10:58:46.345983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.03949","citing_title":"Model Compression vs. Adversarial Robustness: An Empirical Study on Language Models for Code","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ","json":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ.json","graph_json":"https://pith.science/api/pith-number/B2XXM56WFLICB2SCVAV4YF4SEQ/graph.json","events_json":"https://pith.science/api/pith-number/B2XXM56WFLICB2SCVAV4YF4SEQ/events.json","paper":"https://pith.science/paper/B2XXM56W"},"agent_actions":{"view_html":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ","download_json":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ.json","view_paper":"https://pith.science/paper/B2XXM56W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10565&json=true","fetch_graph":"https://pith.science/api/pith-number/B2XXM56WFLICB2SCVAV4YF4SEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/B2XXM56WFLICB2SCVAV4YF4SEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ/action/storage_attestation","attest_author":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ/action/author_attestation","sign_citation":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ/action/citation_signature","submit_replication":"https://pith.science/pith/B2XXM56WFLICB2SCVAV4YF4SEQ/action/replication_record"}},"created_at":"2026-07-05T10:58:46.345983+00:00","updated_at":"2026-07-05T10:58:46.345983+00:00"}