{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PSHDOZCNFUWBNF3GKYNET3VNK5","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":"df5e2dfc9191b8dfdb048af186afc26946fbecbc3881126978546c5d58f73d79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-03T09:02:06Z","title_canon_sha256":"5a0ae9ea8a104c6647579d66d0ce04e385d0cac6ba991709e8869fec556a2681"},"schema_version":"1.0","source":{"id":"2503.01319","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01319","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01319v1","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01319","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"PSHDOZCNFUWB","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"PSHDOZCNFUWBNF3G","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"PSHDOZCN","created_at":"2026-07-05T10:23:04Z"}],"graph_snapshots":[{"event_id":"sha256:7836dc3bb78d2fa16ab466ca7e1711f153789b3ecfb99051b526e1e34c2ccabc","target":"graph","created_at":"2026-07-05T10:23:04Z","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/2503.01319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Owing to the exceptional performance of Large Language Models (LLMs) in Natural Language Processing (NLP) tasks, LLM-based NLP software has rapidly gained traction across various domains, such as financial analysis and content moderation. However, these applications frequently exhibit robustness deficiencies, where slight perturbations in input (prompt+example) may lead to erroneous outputs. Current robustness testing methods face two main limitations: (1) low testing effectiveness, limiting the applicability of LLM-based software in safety-critical scenarios, and (2) insufficient naturalness ","authors_text":"Lei Xue, Mingxuan Xiao, Pengcheng Zhang, Shunhui Ji, Yan Xiao, Yunhe Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-03T09:02:06Z","title":"ABFS: Natural Robustness Testing for LLM-based NLP Software"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01319","kind":"arxiv","version":1},"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:bd67e7e44514e62f7948f360dc2c3473ee4c960560f7a80c0df50777fabe3827","target":"record","created_at":"2026-07-05T10:23:04Z","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":"df5e2dfc9191b8dfdb048af186afc26946fbecbc3881126978546c5d58f73d79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-03T09:02:06Z","title_canon_sha256":"5a0ae9ea8a104c6647579d66d0ce04e385d0cac6ba991709e8869fec556a2681"},"schema_version":"1.0","source":{"id":"2503.01319","kind":"arxiv","version":1}},"canonical_sha256":"7c8e37644d2d2c169766561a49eead576f7b431bdb43e3fc1e73c77126039680","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c8e37644d2d2c169766561a49eead576f7b431bdb43e3fc1e73c77126039680","first_computed_at":"2026-07-05T10:23:04.574527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:04.574527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4NTnDosJA3g7NShqorlgjwyyTRH/fIZt62p/IpZ86+wxeH61YykjUrWN9LpU01s204GV6S/M4Wnf0vT++nYEAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:04.575159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01319","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd67e7e44514e62f7948f360dc2c3473ee4c960560f7a80c0df50777fabe3827","sha256:7836dc3bb78d2fa16ab466ca7e1711f153789b3ecfb99051b526e1e34c2ccabc"],"state_sha256":"bac3f6eda3c1efd9fded5db88225efe70f6b3dab19a47a5370dcc1393f2ad23e"}