{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JUASKGXRELM4N6XN64WEYBC3W2","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":"f2dd7ba975d870b154f5962fd97cf70e03d02fae2e0df03047217e6773c3f65a","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:59:50Z","title_canon_sha256":"2d2ec5328690c9328fa8c7500594f91fde3b12306f78da8642a73a26f3110378"},"schema_version":"1.0","source":{"id":"2306.14898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14898","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14898v3","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14898","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"JUASKGXRELM4","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"JUASKGXRELM4N6XN","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"JUASKGXR","created_at":"2026-07-05T07:06:30Z"}],"graph_snapshots":[{"event_id":"sha256:7b7813de184b20db2d50372cf79a3bc59fb5e4f8f80a5952791cbea3e1ec0fba","target":"graph","created_at":"2026-07-05T07:06:30Z","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/2306.14898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding benchmarks mostly consider a static instruction-to-code sequence transduction process, which has the potential for error propagation and a disconnect between the generated code and its final execution environment. To address this gap, we introduce InterCode, a lightweight, flexible, and easy-to-use framework of interactive coding as a standard reinforcement le","authors_text":"Akshara Prabhakar, John Yang, Karthik Narasimhan, Shunyu Yao","cross_cats":["cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:59:50Z","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14898","kind":"arxiv","version":3},"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":"sha256:870fee5c2b3f22f46244f076f4254b1c16d7308773b39f4c2ad131c1fb084e11","target":"record","created_at":"2026-07-05T07:06:30Z","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":"f2dd7ba975d870b154f5962fd97cf70e03d02fae2e0df03047217e6773c3f65a","cross_cats_sorted":["cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:59:50Z","title_canon_sha256":"2d2ec5328690c9328fa8c7500594f91fde3b12306f78da8642a73a26f3110378"},"schema_version":"1.0","source":{"id":"2306.14898","kind":"arxiv","version":3}},"canonical_sha256":"4d01251af122d9c6faedf72c4c045bb6be753e9cecf415e263d04591d9fac174","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d01251af122d9c6faedf72c4c045bb6be753e9cecf415e263d04591d9fac174","first_computed_at":"2026-07-05T07:06:30.790745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:30.790745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WaFf1oDTKP6l0OLu/n/lAljNEZB2ge1Lx320oDX4/+W2ahaIIZpjg8EDRYhRhQZt57986tfgJKYTP8Fw3baRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:30.791253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:870fee5c2b3f22f46244f076f4254b1c16d7308773b39f4c2ad131c1fb084e11","sha256:7b7813de184b20db2d50372cf79a3bc59fb5e4f8f80a5952791cbea3e1ec0fba"],"state_sha256":"b96ac993869a5bc16153e6a4408d5977ed316b042d35677cabc1a393856cbaf8"}