{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A7TGI722PJ4ROWSHAZ2ZRBG6RM","short_pith_number":"pith:A7TGI722","schema_version":"1.0","canonical_sha256":"07e6647f5a7a79175a4706759884de8b3741863961537c45a998d22d05f0ea64","source":{"kind":"arxiv","id":"2501.19282","version":1},"attestation_state":"computed","paper":{"title":"Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Kunpeng Zhang, Shuai Wang, Xin Xia, Zongjie Li","submitted_at":"2025-01-31T16:45:16Z","abstract_excerpt":"Modern software often accepts inputs with highly complex grammars. Recent advances in large language models (LLMs) have shown that they can be used to synthesize high-quality natural language text and code that conforms to the grammar of a given input format. Nevertheless, LLMs are often incapable or too costly to generate non-textual outputs, such as images, videos, and PDF files. This limitation hinders the application of LLMs in grammar-aware fuzzing.\n  We present a novel approach to enabling grammar-aware fuzzing over non-textual inputs. We employ LLMs to synthesize and also mutate input g"},"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":"2501.19282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-01-31T16:45:16Z","cross_cats_sorted":[],"title_canon_sha256":"ae9c3f5631c11944386a412c13a886c1f93b017d3c820007b1e7cf34756936c4","abstract_canon_sha256":"93a27e278860234010698cc20e2e4daf2a14c418e9da2a4d60dcb753aff2ab17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:58.851860Z","signature_b64":"fe5o6wwYNnfnn1+hPDBvM9Ai5KBbOYhBZ9DmXmPFksvWVP4fpivuMFU8HGz3wjWdGK+8Auf9r3LN8aMe24z9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07e6647f5a7a79175a4706759884de8b3741863961537c45a998d22d05f0ea64","last_reissued_at":"2026-07-05T10:07:58.851328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:58.851328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Daoyuan Wu, Kunpeng Zhang, Shuai Wang, Xin Xia, Zongjie Li","submitted_at":"2025-01-31T16:45:16Z","abstract_excerpt":"Modern software often accepts inputs with highly complex grammars. Recent advances in large language models (LLMs) have shown that they can be used to synthesize high-quality natural language text and code that conforms to the grammar of a given input format. Nevertheless, LLMs are often incapable or too costly to generate non-textual outputs, such as images, videos, and PDF files. This limitation hinders the application of LLMs in grammar-aware fuzzing.\n  We present a novel approach to enabling grammar-aware fuzzing over non-textual inputs. We employ LLMs to synthesize and also mutate input g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19282","kind":"arxiv","version":1},"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/2501.19282/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":"2501.19282","created_at":"2026-07-05T10:07:58.851386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19282v1","created_at":"2026-07-05T10:07:58.851386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19282","created_at":"2026-07-05T10:07:58.851386+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7TGI722PJ4R","created_at":"2026-07-05T10:07:58.851386+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7TGI722PJ4ROWSH","created_at":"2026-07-05T10:07:58.851386+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7TGI722","created_at":"2026-07-05T10:07:58.851386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26539","citing_title":"FuzzPilot: Plateau-Triggered Recipe Validation for Structured Text Fuzzing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19201","citing_title":"Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM","json":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM.json","graph_json":"https://pith.science/api/pith-number/A7TGI722PJ4ROWSHAZ2ZRBG6RM/graph.json","events_json":"https://pith.science/api/pith-number/A7TGI722PJ4ROWSHAZ2ZRBG6RM/events.json","paper":"https://pith.science/paper/A7TGI722"},"agent_actions":{"view_html":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM","download_json":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM.json","view_paper":"https://pith.science/paper/A7TGI722","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19282&json=true","fetch_graph":"https://pith.science/api/pith-number/A7TGI722PJ4ROWSHAZ2ZRBG6RM/graph.json","fetch_events":"https://pith.science/api/pith-number/A7TGI722PJ4ROWSHAZ2ZRBG6RM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM/action/storage_attestation","attest_author":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM/action/author_attestation","sign_citation":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM/action/citation_signature","submit_replication":"https://pith.science/pith/A7TGI722PJ4ROWSHAZ2ZRBG6RM/action/replication_record"}},"created_at":"2026-07-05T10:07:58.851386+00:00","updated_at":"2026-07-05T10:07:58.851386+00:00"}