{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UVKZVCN36EPFDQUAM573B2IMDL","short_pith_number":"pith:UVKZVCN3","canonical_record":{"source":{"id":"2410.08105","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:53:10Z","cross_cats_sorted":[],"title_canon_sha256":"b7fb614b64a691dc43d195684b1ecf3937befdbf5106b4ae929dc2bb073b35ca","abstract_canon_sha256":"50d4b122f11fc099813bf0683c5ac8d65df673765e179e19dc659cd5c937083d"},"schema_version":"1.0"},"canonical_sha256":"a5559a89bbf11e51c280677fb0e90c1ad89f9f8bea5985e8fa2d5039bcaf7892","source":{"kind":"arxiv","id":"2410.08105","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08105","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08105v3","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08105","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"UVKZVCN36EPF","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"UVKZVCN36EPFDQUA","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"UVKZVCN3","created_at":"2026-07-05T10:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UVKZVCN36EPFDQUAM573B2IMDL","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08105","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:53:10Z","cross_cats_sorted":[],"title_canon_sha256":"b7fb614b64a691dc43d195684b1ecf3937befdbf5106b4ae929dc2bb073b35ca","abstract_canon_sha256":"50d4b122f11fc099813bf0683c5ac8d65df673765e179e19dc659cd5c937083d"},"schema_version":"1.0"},"canonical_sha256":"a5559a89bbf11e51c280677fb0e90c1ad89f9f8bea5985e8fa2d5039bcaf7892","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:38.239088Z","signature_b64":"w1U6IED/VkIGWeTF/IttgJfjOy4azBU6E0EV3mZfqQYXqYs001jkZLiV/YqnlKSjoB1m3WJiEU/uXCfoWiswCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5559a89bbf11e51c280677fb0e90c1ad89f9f8bea5985e8fa2d5039bcaf7892","last_reissued_at":"2026-07-05T10:45:38.238592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:38.238592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08105","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qmu7mr1PIuLuMdwXmhER3xietBTZ9guqyQx4qZ1qv31t6X/FNX3R1dklgZ+uvy8mFhQHJUyrpyGHyoYB2KaiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:33:22.252799Z"},"content_sha256":"9ac6fc77f10b5ede3e577bf6f08cdb760b48566475f59113f85dd17cbb4ccec4","schema_version":"1.0","event_id":"sha256:9ac6fc77f10b5ede3e577bf6f08cdb760b48566475f59113f85dd17cbb4ccec4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UVKZVCN36EPFDQUAM573B2IMDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Negrevergne, Gabriel Synnaeve, Jonas Gehring, Juliette Decugis, Kunhao Zheng, Taco Cohen","submitted_at":"2024-10-10T16:53:10Z","abstract_excerpt":"Prompting techniques such as chain-of-thought have established themselves as a popular vehicle for improving the outputs of large language models (LLMs). For code generation, however, their exact mechanics and efficacy are under-explored. We thus investigate the effects of a wide range of prompting strategies with a focus on automatic re-prompting over multiple turns and computational requirements. After systematically decomposing reasoning, instruction, and execution feedback prompts, we conduct an extensive grid search on the competitive programming benchmarks CodeContests and TACO for multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08105","kind":"arxiv","version":3},"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/2410.08105/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":"2026-07-05T10:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LxcSdVM118fQygX6jPYnaXQH4HM86koNGawJlkUceXACa0blqx55cWHfhNfkWdNMNoDMXpM20ey/Uf3MR/tTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:33:22.253304Z"},"content_sha256":"a955f2052f6cc9e8dfe709cc5d57c699a71db88e7a9e9cefd84f1b1a4ce241ae","schema_version":"1.0","event_id":"sha256:a955f2052f6cc9e8dfe709cc5d57c699a71db88e7a9e9cefd84f1b1a4ce241ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVKZVCN36EPFDQUAM573B2IMDL/bundle.json","state_url":"https://pith.science/pith/UVKZVCN36EPFDQUAM573B2IMDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVKZVCN36EPFDQUAM573B2IMDL/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":"2026-08-08T20:33:22Z","links":{"resolver":"https://pith.science/pith/UVKZVCN36EPFDQUAM573B2IMDL","bundle":"https://pith.science/pith/UVKZVCN36EPFDQUAM573B2IMDL/bundle.json","state":"https://pith.science/pith/UVKZVCN36EPFDQUAM573B2IMDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVKZVCN36EPFDQUAM573B2IMDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UVKZVCN36EPFDQUAM573B2IMDL","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":"50d4b122f11fc099813bf0683c5ac8d65df673765e179e19dc659cd5c937083d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:53:10Z","title_canon_sha256":"b7fb614b64a691dc43d195684b1ecf3937befdbf5106b4ae929dc2bb073b35ca"},"schema_version":"1.0","source":{"id":"2410.08105","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08105","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08105v3","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08105","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"UVKZVCN36EPF","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"UVKZVCN36EPFDQUA","created_at":"2026-07-05T10:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"UVKZVCN3","created_at":"2026-07-05T10:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:a955f2052f6cc9e8dfe709cc5d57c699a71db88e7a9e9cefd84f1b1a4ce241ae","target":"graph","created_at":"2026-07-05T10:45:38Z","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/2410.08105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompting techniques such as chain-of-thought have established themselves as a popular vehicle for improving the outputs of large language models (LLMs). For code generation, however, their exact mechanics and efficacy are under-explored. We thus investigate the effects of a wide range of prompting strategies with a focus on automatic re-prompting over multiple turns and computational requirements. After systematically decomposing reasoning, instruction, and execution feedback prompts, we conduct an extensive grid search on the competitive programming benchmarks CodeContests and TACO for multi","authors_text":"Benjamin Negrevergne, Gabriel Synnaeve, Jonas Gehring, Juliette Decugis, Kunhao Zheng, Taco Cohen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:53:10Z","title":"What Makes Large Language Models Reason in (Multi-Turn) Code Generation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08105","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":"sha256:9ac6fc77f10b5ede3e577bf6f08cdb760b48566475f59113f85dd17cbb4ccec4","target":"record","created_at":"2026-07-05T10:45:38Z","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":"50d4b122f11fc099813bf0683c5ac8d65df673765e179e19dc659cd5c937083d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:53:10Z","title_canon_sha256":"b7fb614b64a691dc43d195684b1ecf3937befdbf5106b4ae929dc2bb073b35ca"},"schema_version":"1.0","source":{"id":"2410.08105","kind":"arxiv","version":3}},"canonical_sha256":"a5559a89bbf11e51c280677fb0e90c1ad89f9f8bea5985e8fa2d5039bcaf7892","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5559a89bbf11e51c280677fb0e90c1ad89f9f8bea5985e8fa2d5039bcaf7892","first_computed_at":"2026-07-05T10:45:38.238592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:38.238592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w1U6IED/VkIGWeTF/IttgJfjOy4azBU6E0EV3mZfqQYXqYs001jkZLiV/YqnlKSjoB1m3WJiEU/uXCfoWiswCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:38.239088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08105","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ac6fc77f10b5ede3e577bf6f08cdb760b48566475f59113f85dd17cbb4ccec4","sha256:a955f2052f6cc9e8dfe709cc5d57c699a71db88e7a9e9cefd84f1b1a4ce241ae"],"state_sha256":"8059546d5e85453d6897be21b642d75ed46ae70ddfbd47a87d567aba8293f633"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SV13FiwZzlP3Jpq88O1Jb26Nt4qlInSnHzHd0PJeIBdYp5MblnB8oSQvfWrnWkF8hoMH9pA4QsCGRQKzldANBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:33:22.256980Z","bundle_sha256":"afe3771faf9a07c94b8f7d0d98d2529e44892b3f0a6174965ca158341330a5cb"}}