{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2XNFYL4CILHY6LNOHRHJDALYCX","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":"890a4ac60878a220de18fa02548ed53e0686c6853484a8c2144d4e1da646a59f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-13T03:13:21Z","title_canon_sha256":"b653c51a5922eb1712f13d8eed8a61b53783f45cce3db317f83dd804fd52ef37"},"schema_version":"1.0","source":{"id":"2607.11042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11042","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11042v1","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11042","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"2XNFYL4CILHY","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"2XNFYL4CILHY6LNO","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"2XNFYL4C","created_at":"2026-07-14T01:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:dad59ab5a4a9eb93eb3098da37e49baec9bca2e70854ea78dd146c509c84da20","target":"graph","created_at":"2026-07-14T01:22:13Z","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/2607.11042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used in agentic coding settings, where they can inspect files, execute commands, run tests, observe failures, and iteratively revise code. This shift raises a central evaluation question: can an agentic LLM generate an end-to-end software artifact that is both deployable and behaviorally correct under execution? Backend services provide a controlled but realistic substrate for this evaluation. Their APIs expose application-level executable semantics, and deployed behavior can be checked deterministically against an OpenAPI contract through black-bo","authors_text":"Dezhi Ran, Jialei Wei, Mengzhou Wu, Tao Xie, Wei Yang, Yuan Cao, Yuzhe Guo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-13T03:13:21Z","title":"BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11042","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":"sha256:3a84a62090105dd55e50b6f9d255d8d6c91f96e4b2eac3b845f6a6ec23c463d3","target":"record","created_at":"2026-07-14T01:22:13Z","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":"890a4ac60878a220de18fa02548ed53e0686c6853484a8c2144d4e1da646a59f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-13T03:13:21Z","title_canon_sha256":"b653c51a5922eb1712f13d8eed8a61b53783f45cce3db317f83dd804fd52ef37"},"schema_version":"1.0","source":{"id":"2607.11042","kind":"arxiv","version":1}},"canonical_sha256":"d5da5c2f8242cf8f2dae3c4e91817815c85c89c099a1c37cb71375c6abde2ea9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5da5c2f8242cf8f2dae3c4e91817815c85c89c099a1c37cb71375c6abde2ea9","first_computed_at":"2026-07-14T01:22:13.115755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:13.115755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z6TYsh5aEb5XKJXNiDz12zwalB80jWPG1IOqMl2ymFxdFo9j4W1i5LZWXnto0pbivi0hrjrUn9p4yYB1LcdSAw==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:13.116603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a84a62090105dd55e50b6f9d255d8d6c91f96e4b2eac3b845f6a6ec23c463d3","sha256:dad59ab5a4a9eb93eb3098da37e49baec9bca2e70854ea78dd146c509c84da20"],"state_sha256":"052ad4e9779291cd1c23c27611257e4de881b4ce4d98bb02216db6c5d6f9cd28"}