{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5IADEXEYLAKQOT7ZLKA4DPZEOJ","short_pith_number":"pith:5IADEXEY","canonical_record":{"source":{"id":"2408.00019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-30T18:49:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9fadfdbfcd5c98e3ccb3c767a6b94f931fcbe5eea7549995c84ee0b1f9ae4712","abstract_canon_sha256":"96a63f80260c861b82ef81de0dd69091b955e0210b04fdbc9cf869b762f25a9b"},"schema_version":"1.0"},"canonical_sha256":"ea00325c985815074ff95a81c1bf24727487bc27d9348cefd30204a7cf963c0d","source":{"kind":"arxiv","id":"2408.00019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00019","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00019v1","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00019","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"5IADEXEYLAKQ","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"pith_short_16","alias_value":"5IADEXEYLAKQOT7Z","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"pith_short_8","alias_value":"5IADEXEY","created_at":"2026-07-05T08:50:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5IADEXEYLAKQOT7ZLKA4DPZEOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.00019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-30T18:49:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9fadfdbfcd5c98e3ccb3c767a6b94f931fcbe5eea7549995c84ee0b1f9ae4712","abstract_canon_sha256":"96a63f80260c861b82ef81de0dd69091b955e0210b04fdbc9cf869b762f25a9b"},"schema_version":"1.0"},"canonical_sha256":"ea00325c985815074ff95a81c1bf24727487bc27d9348cefd30204a7cf963c0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:44.179739Z","signature_b64":"qhykse1jjUu1X/jISjaEd/RxHbC4wwttK7CZJ4zWYt3aaKTdq7iy0+IJxXRel4EjexWSxdx7yxfzTYJg7mkvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea00325c985815074ff95a81c1bf24727487bc27d9348cefd30204a7cf963c0d","last_reissued_at":"2026-07-05T08:50:44.179371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:44.179371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.00019","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":"2026-07-05T08:50:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1vxqcHj1HAB3EFW8FTInVegdmT2EkUQsoMM/g9R2sr1sph+9h8KK0ftuQ/7ZB3tNKicXVJGFbQO2jltQ6VRzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:31:01.015185Z"},"content_sha256":"c9c09ade3e78385c8e9e97a8c18791dbee0d3421f120000d709ed9d17b4ba4d2","schema_version":"1.0","event_id":"sha256:c9c09ade3e78385c8e9e97a8c18791dbee0d3421f120000d709ed9d17b4ba4d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5IADEXEYLAKQOT7ZLKA4DPZEOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WebApp1K: A Practical Code-Generation Benchmark for Web App Development","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Yi Cui","submitted_at":"2024-07-30T18:49:26Z","abstract_excerpt":"We introduce WebApp1K, a practical code-generation benchmark to measure LLM ability to develop web apps. This benchmark aims to calibrate LLM output and aid the models to progressively improve code correctness and functionality. The benchmark is lightweight and easy to run. We present the initial version of WebApp1K, and share our findings of running the benchmark against the latest frontier LLMs. First, open source LLMs deliver impressive performance, closely trailing behind GPT-4o and Claude 3.5. Second, model size has strong correlation with code correctness. Third, no prompting techniques "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00019","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/2408.00019/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":"2026-07-05T08:50:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/hnH4I3JdQKLcpuOz7ewrCCUC1C40gFnj5TKEwkr41FXuxtKbeyq4WDe4QyWtYZr2Z+drBz1etbHWWNjYBQUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:31:01.016080Z"},"content_sha256":"42883cc6fbd38ecf119b9e1b861ca810946e1bdee53ca189d71cca500681b409","schema_version":"1.0","event_id":"sha256:42883cc6fbd38ecf119b9e1b861ca810946e1bdee53ca189d71cca500681b409"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ/bundle.json","state_url":"https://pith.science/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ/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":"2026-08-07T23:31:01Z","links":{"resolver":"https://pith.science/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ","bundle":"https://pith.science/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ/bundle.json","state":"https://pith.science/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IADEXEYLAKQOT7ZLKA4DPZEOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5IADEXEYLAKQOT7ZLKA4DPZEOJ","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":"96a63f80260c861b82ef81de0dd69091b955e0210b04fdbc9cf869b762f25a9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-30T18:49:26Z","title_canon_sha256":"9fadfdbfcd5c98e3ccb3c767a6b94f931fcbe5eea7549995c84ee0b1f9ae4712"},"schema_version":"1.0","source":{"id":"2408.00019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00019","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00019v1","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00019","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"5IADEXEYLAKQ","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"pith_short_16","alias_value":"5IADEXEYLAKQOT7Z","created_at":"2026-07-05T08:50:44Z"},{"alias_kind":"pith_short_8","alias_value":"5IADEXEY","created_at":"2026-07-05T08:50:44Z"}],"graph_snapshots":[{"event_id":"sha256:42883cc6fbd38ecf119b9e1b861ca810946e1bdee53ca189d71cca500681b409","target":"graph","created_at":"2026-07-05T08:50:44Z","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/2408.00019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce WebApp1K, a practical code-generation benchmark to measure LLM ability to develop web apps. This benchmark aims to calibrate LLM output and aid the models to progressively improve code correctness and functionality. The benchmark is lightweight and easy to run. We present the initial version of WebApp1K, and share our findings of running the benchmark against the latest frontier LLMs. First, open source LLMs deliver impressive performance, closely trailing behind GPT-4o and Claude 3.5. Second, model size has strong correlation with code correctness. Third, no prompting techniques ","authors_text":"Yi Cui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-30T18:49:26Z","title":"WebApp1K: A Practical Code-Generation Benchmark for Web App Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00019","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:c9c09ade3e78385c8e9e97a8c18791dbee0d3421f120000d709ed9d17b4ba4d2","target":"record","created_at":"2026-07-05T08:50:44Z","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":"96a63f80260c861b82ef81de0dd69091b955e0210b04fdbc9cf869b762f25a9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-30T18:49:26Z","title_canon_sha256":"9fadfdbfcd5c98e3ccb3c767a6b94f931fcbe5eea7549995c84ee0b1f9ae4712"},"schema_version":"1.0","source":{"id":"2408.00019","kind":"arxiv","version":1}},"canonical_sha256":"ea00325c985815074ff95a81c1bf24727487bc27d9348cefd30204a7cf963c0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea00325c985815074ff95a81c1bf24727487bc27d9348cefd30204a7cf963c0d","first_computed_at":"2026-07-05T08:50:44.179371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:44.179371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qhykse1jjUu1X/jISjaEd/RxHbC4wwttK7CZJ4zWYt3aaKTdq7iy0+IJxXRel4EjexWSxdx7yxfzTYJg7mkvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:44.179739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9c09ade3e78385c8e9e97a8c18791dbee0d3421f120000d709ed9d17b4ba4d2","sha256:42883cc6fbd38ecf119b9e1b861ca810946e1bdee53ca189d71cca500681b409"],"state_sha256":"a935d44ec20453c2b93d283d2f7bc6f149e28069172b8f6f149b0c74894ab7ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HSVcCpENYcrtZnrt5Jg5b46i98CzxXKFnK+xysqCABR5alvs/v8EAhYZsZ7wxiPHyDGVezZftZGLizLWuDlCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:31:01.029794Z","bundle_sha256":"f264c1456faca9ba27c85b3973e9ffaf28e51ec782364c37e4c1aa51bcae021c"}}