{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UV3OZGZHROAE2PMTVQS6NWSHJB","short_pith_number":"pith:UV3OZGZH","canonical_record":{"source":{"id":"2505.09027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-13T23:47:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6430a3dd913ad6eb87d1851c0f67db96e5448f8d354d9ada2e363ea596c11d2","abstract_canon_sha256":"4c12011e727caad319623d6eb3a01ae7f38e0d4d954519686aa72433395d1fe5"},"schema_version":"1.0"},"canonical_sha256":"a576ec9b278b804d3d93ac25e6da4748659ae9e1f69288b8c65b5d7723b333e8","source":{"kind":"arxiv","id":"2505.09027","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09027","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09027v1","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09027","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"UV3OZGZHROAE","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"UV3OZGZHROAE2PMT","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"UV3OZGZH","created_at":"2026-07-05T11:02:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UV3OZGZHROAE2PMTVQS6NWSHJB","target":"record","payload":{"canonical_record":{"source":{"id":"2505.09027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-13T23:47:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6430a3dd913ad6eb87d1851c0f67db96e5448f8d354d9ada2e363ea596c11d2","abstract_canon_sha256":"4c12011e727caad319623d6eb3a01ae7f38e0d4d954519686aa72433395d1fe5"},"schema_version":"1.0"},"canonical_sha256":"a576ec9b278b804d3d93ac25e6da4748659ae9e1f69288b8c65b5d7723b333e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:49.075768Z","signature_b64":"vIh/H1Ohs8P8KQZblKLgMftcm4EBReLAGEhPBvKwL3eXM5aMdVxhlPbHafs4YUo+K7OKs0qbYsHDuCNdZEGSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a576ec9b278b804d3d93ac25e6da4748659ae9e1f69288b8c65b5d7723b333e8","last_reissued_at":"2026-07-05T11:02:49.075328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:49.075328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.09027","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLIr8wr30cgU/lxD2B4r9f8fWtcskq5CCTPuThBfBiuC1O1p33JBUxxPagVpr+eHJ3y+vWIDkifB7I4lyavsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:17.197956Z"},"content_sha256":"d3ac8d50d753256d82966320521c8946c9d40f2e29fcd17b1d44d3a3a3e6a5df","schema_version":"1.0","event_id":"sha256:d3ac8d50d753256d82966320521c8946c9d40f2e29fcd17b1d44d3a3a3e6a5df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UV3OZGZHROAE2PMTVQS6NWSHJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Yi Cui","submitted_at":"2025-05-13T23:47:12Z","abstract_excerpt":"We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks, where test cases serve as both prompt and verification for code generation. Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases, reflecting real-world software development practices. Comprising 1000 diverse challenges across 20 application domains, the benchmark evaluates LLMs on their ability to generate compact, functional code under the constra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09027","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/2505.09027/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":"2026-07-05T11:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGy/S2odQntzmJzb3KtbgyMSDFPMqqe3lFL6HrMuzQND423Lfn2wzg/W7mQrOKLKHzlzBno09PWXO5xxFXWTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:17.198448Z"},"content_sha256":"db576c7e7c98fec292cb2404eb98ddc47b464fffbd4ba5cdf1ad11cb87975980","schema_version":"1.0","event_id":"sha256:db576c7e7c98fec292cb2404eb98ddc47b464fffbd4ba5cdf1ad11cb87975980"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UV3OZGZHROAE2PMTVQS6NWSHJB/bundle.json","state_url":"https://pith.science/pith/UV3OZGZHROAE2PMTVQS6NWSHJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UV3OZGZHROAE2PMTVQS6NWSHJB/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":"2026-08-05T22:36:17Z","links":{"resolver":"https://pith.science/pith/UV3OZGZHROAE2PMTVQS6NWSHJB","bundle":"https://pith.science/pith/UV3OZGZHROAE2PMTVQS6NWSHJB/bundle.json","state":"https://pith.science/pith/UV3OZGZHROAE2PMTVQS6NWSHJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UV3OZGZHROAE2PMTVQS6NWSHJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UV3OZGZHROAE2PMTVQS6NWSHJB","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":"4c12011e727caad319623d6eb3a01ae7f38e0d4d954519686aa72433395d1fe5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-13T23:47:12Z","title_canon_sha256":"b6430a3dd913ad6eb87d1851c0f67db96e5448f8d354d9ada2e363ea596c11d2"},"schema_version":"1.0","source":{"id":"2505.09027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09027","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09027v1","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09027","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"UV3OZGZHROAE","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"UV3OZGZHROAE2PMT","created_at":"2026-07-05T11:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"UV3OZGZH","created_at":"2026-07-05T11:02:49Z"}],"graph_snapshots":[{"event_id":"sha256:db576c7e7c98fec292cb2404eb98ddc47b464fffbd4ba5cdf1ad11cb87975980","target":"graph","created_at":"2026-07-05T11:02:49Z","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/2505.09027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks, where test cases serve as both prompt and verification for code generation. Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases, reflecting real-world software development practices. Comprising 1000 diverse challenges across 20 application domains, the benchmark evaluates LLMs on their ability to generate compact, functional code under the constra","authors_text":"Yi Cui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-13T23:47:12Z","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09027","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:d3ac8d50d753256d82966320521c8946c9d40f2e29fcd17b1d44d3a3a3e6a5df","target":"record","created_at":"2026-07-05T11:02:49Z","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":"4c12011e727caad319623d6eb3a01ae7f38e0d4d954519686aa72433395d1fe5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-13T23:47:12Z","title_canon_sha256":"b6430a3dd913ad6eb87d1851c0f67db96e5448f8d354d9ada2e363ea596c11d2"},"schema_version":"1.0","source":{"id":"2505.09027","kind":"arxiv","version":1}},"canonical_sha256":"a576ec9b278b804d3d93ac25e6da4748659ae9e1f69288b8c65b5d7723b333e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a576ec9b278b804d3d93ac25e6da4748659ae9e1f69288b8c65b5d7723b333e8","first_computed_at":"2026-07-05T11:02:49.075328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:49.075328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vIh/H1Ohs8P8KQZblKLgMftcm4EBReLAGEhPBvKwL3eXM5aMdVxhlPbHafs4YUo+K7OKs0qbYsHDuCNdZEGSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:49.075768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3ac8d50d753256d82966320521c8946c9d40f2e29fcd17b1d44d3a3a3e6a5df","sha256:db576c7e7c98fec292cb2404eb98ddc47b464fffbd4ba5cdf1ad11cb87975980"],"state_sha256":"dfd5f66d5fa4b1bcee0b577ae71960f76721cbf66324cb9e782e40a82d4afe5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ULbYtz5c7jqjLN93DYTkeXyvoPyXIt8zOKPoHGihAPD7MehZtF9Nx4Ozq4sb1n0EpgyIgNzoM8N3ch7YHPGnDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:36:17.201701Z","bundle_sha256":"50a57b0a5bf8f029c3c926e08a3c065bdcc4bc23d5d7ad4f1535d4ca4fb6d672"}}