{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P4EZHJKAAAM3V7KL4FJR2JYGVI","short_pith_number":"pith:P4EZHJKA","canonical_record":{"source":{"id":"2606.28430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-26T01:23:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"719101709903c77155bce21b43979db4d1e92209649e02bb6a6ccc8ccb1df1f2","abstract_canon_sha256":"386058d1a5efc2cc2e23274546bc85b081dd39d7aa3b6f8b8cc06751623bde67"},"schema_version":"1.0"},"canonical_sha256":"7f0993a5400019bafd4be1531d2706aa31d559b075496b3d91a60b905d30caa8","source":{"kind":"arxiv","id":"2606.28430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28430","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28430v1","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28430","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"P4EZHJKAAAM3","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"P4EZHJKAAAM3V7KL","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"P4EZHJKA","created_at":"2026-06-30T00:15:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P4EZHJKAAAM3V7KL4FJR2JYGVI","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-26T01:23:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"719101709903c77155bce21b43979db4d1e92209649e02bb6a6ccc8ccb1df1f2","abstract_canon_sha256":"386058d1a5efc2cc2e23274546bc85b081dd39d7aa3b6f8b8cc06751623bde67"},"schema_version":"1.0"},"canonical_sha256":"7f0993a5400019bafd4be1531d2706aa31d559b075496b3d91a60b905d30caa8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:13.841664Z","signature_b64":"vM2Z2td3TXwb/D9I0tvc+NeoDamMjZNFQMjvwOoC3FpGkjClU8cmBpgM5qH4T0Iz6tMXFk5bpafPtoNOPeZBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f0993a5400019bafd4be1531d2706aa31d559b075496b3d91a60b905d30caa8","last_reissued_at":"2026-06-30T00:15:13.841225Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:13.841225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28430","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":"2026-06-30T00:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rXFEZ8sjxpuHtzbjXx/a852JtX6iMdHC+aQbfx+JcZpCuuuWVsGWNOTZ0cVFLdgAV0nii8Dosqd+FvISYPJ+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T10:34:49.660112Z"},"content_sha256":"204ddd0bee64fb0f30395ee87f4947b6413353754900a152bb88583a5e0c81fe","schema_version":"1.0","event_id":"sha256:204ddd0bee64fb0f30395ee87f4947b6413353754900a152bb88583a5e0c81fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P4EZHJKAAAM3V7KL4FJR2JYGVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ben Kereopa-Yorke, Ben Schultz, Yanuo Ma","submitted_at":"2026-06-26T01:23:27Z","abstract_excerpt":"Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity problems, and a passing score may not show whether the requested task was delivered. We study both problems. In a controlled code-as-spec setup, two production Copilot CLI agents (claude-opus-4.7, gpt-5.5) re-implement a React Fluent-UI data table in Angular as a reusable library under a hidden 222-test Playwright oracle across 18 runs and three oracle-availability conditions. Alongside the score, we run a mechanical library audit and check each verdic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28430","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/2606.28430/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":"2026-06-30T00:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQetQWympsMmhWx3kSJP5/pleA0HE20x/cO690KGm1c7Pw9UgtdkiQyOGduCINsR7dDJTaDeJiLBxLrgE+9fBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T10:34:49.660503Z"},"content_sha256":"b6dfe2e37afcf5d7b72eb54283c6f99d0624993203661c225dd13beb7684a91c","schema_version":"1.0","event_id":"sha256:b6dfe2e37afcf5d7b72eb54283c6f99d0624993203661c225dd13beb7684a91c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI/bundle.json","state_url":"https://pith.science/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI/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":"2026-07-02T10:34:49Z","links":{"resolver":"https://pith.science/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI","bundle":"https://pith.science/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI/bundle.json","state":"https://pith.science/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4EZHJKAAAM3V7KL4FJR2JYGVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P4EZHJKAAAM3V7KL4FJR2JYGVI","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":"386058d1a5efc2cc2e23274546bc85b081dd39d7aa3b6f8b8cc06751623bde67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-26T01:23:27Z","title_canon_sha256":"719101709903c77155bce21b43979db4d1e92209649e02bb6a6ccc8ccb1df1f2"},"schema_version":"1.0","source":{"id":"2606.28430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28430","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28430v1","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28430","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"P4EZHJKAAAM3","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"P4EZHJKAAAM3V7KL","created_at":"2026-06-30T00:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"P4EZHJKA","created_at":"2026-06-30T00:15:13Z"}],"graph_snapshots":[{"event_id":"sha256:b6dfe2e37afcf5d7b72eb54283c6f99d0624993203661c225dd13beb7684a91c","target":"graph","created_at":"2026-06-30T00:15:13Z","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/2606.28430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity problems, and a passing score may not show whether the requested task was delivered. We study both problems. In a controlled code-as-spec setup, two production Copilot CLI agents (claude-opus-4.7, gpt-5.5) re-implement a React Fluent-UI data table in Angular as a reusable library under a hidden 222-test Playwright oracle across 18 runs and three oracle-availability conditions. Alongside the score, we run a mechanical library audit and check each verdic","authors_text":"Ben Kereopa-Yorke, Ben Schultz, Yanuo Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-26T01:23:27Z","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28430","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":"sha256:204ddd0bee64fb0f30395ee87f4947b6413353754900a152bb88583a5e0c81fe","target":"record","created_at":"2026-06-30T00:15:13Z","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":"386058d1a5efc2cc2e23274546bc85b081dd39d7aa3b6f8b8cc06751623bde67","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-26T01:23:27Z","title_canon_sha256":"719101709903c77155bce21b43979db4d1e92209649e02bb6a6ccc8ccb1df1f2"},"schema_version":"1.0","source":{"id":"2606.28430","kind":"arxiv","version":1}},"canonical_sha256":"7f0993a5400019bafd4be1531d2706aa31d559b075496b3d91a60b905d30caa8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f0993a5400019bafd4be1531d2706aa31d559b075496b3d91a60b905d30caa8","first_computed_at":"2026-06-30T00:15:13.841225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:13.841225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vM2Z2td3TXwb/D9I0tvc+NeoDamMjZNFQMjvwOoC3FpGkjClU8cmBpgM5qH4T0Iz6tMXFk5bpafPtoNOPeZBCg==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:13.841664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:204ddd0bee64fb0f30395ee87f4947b6413353754900a152bb88583a5e0c81fe","sha256:b6dfe2e37afcf5d7b72eb54283c6f99d0624993203661c225dd13beb7684a91c"],"state_sha256":"05f947bcd5b362555fa7a690012978d0837f3de7e971ca9aaf95cef2db8e567b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BIoZY73wDndzng+phw0v3zDWHwTVK1B9FneVlC/yQ/QNAB9zKbzrOirVIquXsbORwN6P0YKHLXKJkj1eAhz0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T10:34:49.662548Z","bundle_sha256":"03fc57a3066252a0d5c68bde137f4fd8866cf05f4079432975c97e49d0eafe6a"}}