{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PJQZNCAHDZ4VA32GXKVOXZDFHL","short_pith_number":"pith:PJQZNCAH","canonical_record":{"source":{"id":"2407.12504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"13944ba26cdf99fd2b978018e8189fc9d8140b67b3a5fda3e4eab7e1e584156d","abstract_canon_sha256":"2e988cc2800da8e277f1a4f9fd592d1c67d6c3c94f5bf181e62f334e67728fdd"},"schema_version":"1.0"},"canonical_sha256":"7a619688071e79506f46baaaebe4653acdb0e58a96fbacd0dd2b9b8e41d0e050","source":{"kind":"arxiv","id":"2407.12504","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12504","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12504v2","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12504","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"PJQZNCAHDZ4V","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"PJQZNCAHDZ4VA32G","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"PJQZNCAH","created_at":"2026-07-05T10:11:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PJQZNCAHDZ4VA32GXKVOXZDFHL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"13944ba26cdf99fd2b978018e8189fc9d8140b67b3a5fda3e4eab7e1e584156d","abstract_canon_sha256":"2e988cc2800da8e277f1a4f9fd592d1c67d6c3c94f5bf181e62f334e67728fdd"},"schema_version":"1.0"},"canonical_sha256":"7a619688071e79506f46baaaebe4653acdb0e58a96fbacd0dd2b9b8e41d0e050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:22.354982Z","signature_b64":"3tTs7FeSiSKfFwR/9XmUSEoHmUnTI845SP84uJ1j0GdyLaeC502ZDBAWdIM+u5JUTMYsWIwtJLGSE5KJldyfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a619688071e79506f46baaaebe4653acdb0e58a96fbacd0dd2b9b8e41d0e050","last_reissued_at":"2026-07-05T10:11:22.354446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:22.354446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12504","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOVjhx/M9I5v3lmU7E48Z6UUfGVDGrxUIthujtF0/LczbL0nox8xxuzHr7NNI0Vw2cl9t8QXmQ68CkNs14MPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:06:06.125083Z"},"content_sha256":"1b36d28e01489d12d8cbe4d200ee9445242ebfbf2e30793e6bfa519d2a4da94c","schema_version":"1.0","event_id":"sha256:1b36d28e01489d12d8cbe4d200ee9445242ebfbf2e30793e6bfa519d2a4da94c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PJQZNCAHDZ4VA32GXKVOXZDFHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Case2Code: Scalable Synthetic Data for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Demin Song, Hang Yan, Linyang Li, Peiji Li, Pengyu Wang, Qinyuan Cheng, Qipeng Guo, Shimin Li, Xiaonan Li, Xipeng Qiu, Xuanjing Huang, Yichuan Ma, Yunfan Shao","submitted_at":"2024-07-17T11:35:00Z","abstract_excerpt":"Large Language Models (LLMs) have shown outstanding breakthroughs in code generation. Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs, which can be challenging to scale due to the dependence on a teacher model and high generation costs. In this paper, we focus on synthesizing code data at scale and propose a \\textbf{Case2Code} task by exploiting the expressiveness and correctness of programs. \\textbf{Case2Code} is an inductive inference task that aims to infer underlying code implementations by observing input-output examples or program behaviors, B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12504","kind":"arxiv","version":2},"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/2407.12504/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":"2026-07-05T10:11:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eVT6HlwEQGWrTSsXr2vBL2UWuFIKbqqe8ZKILvSGki+MMIN/D/GbZI+MDKq9wX/kmbnMaV+Ysc3nwE2TuHSDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:06:06.125603Z"},"content_sha256":"0fea71fc6d5583aeabe54a1b328e790860ce5ad8c92b03491bd3b31a24281e2a","schema_version":"1.0","event_id":"sha256:0fea71fc6d5583aeabe54a1b328e790860ce5ad8c92b03491bd3b31a24281e2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL/bundle.json","state_url":"https://pith.science/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL/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":"2026-08-19T23:06:06Z","links":{"resolver":"https://pith.science/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL","bundle":"https://pith.science/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL/bundle.json","state":"https://pith.science/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJQZNCAHDZ4VA32GXKVOXZDFHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PJQZNCAHDZ4VA32GXKVOXZDFHL","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":"2e988cc2800da8e277f1a4f9fd592d1c67d6c3c94f5bf181e62f334e67728fdd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:35:00Z","title_canon_sha256":"13944ba26cdf99fd2b978018e8189fc9d8140b67b3a5fda3e4eab7e1e584156d"},"schema_version":"1.0","source":{"id":"2407.12504","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12504","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12504v2","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12504","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"PJQZNCAHDZ4V","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"PJQZNCAHDZ4VA32G","created_at":"2026-07-05T10:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"PJQZNCAH","created_at":"2026-07-05T10:11:22Z"}],"graph_snapshots":[{"event_id":"sha256:0fea71fc6d5583aeabe54a1b328e790860ce5ad8c92b03491bd3b31a24281e2a","target":"graph","created_at":"2026-07-05T10:11:22Z","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/2407.12504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown outstanding breakthroughs in code generation. Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs, which can be challenging to scale due to the dependence on a teacher model and high generation costs. In this paper, we focus on synthesizing code data at scale and propose a \\textbf{Case2Code} task by exploiting the expressiveness and correctness of programs. \\textbf{Case2Code} is an inductive inference task that aims to infer underlying code implementations by observing input-output examples or program behaviors, B","authors_text":"Dahua Lin, Demin Song, Hang Yan, Linyang Li, Peiji Li, Pengyu Wang, Qinyuan Cheng, Qipeng Guo, Shimin Li, Xiaonan Li, Xipeng Qiu, Xuanjing Huang, Yichuan Ma, Yunfan Shao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:35:00Z","title":"Case2Code: Scalable Synthetic Data for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12504","kind":"arxiv","version":2},"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":"sha256:1b36d28e01489d12d8cbe4d200ee9445242ebfbf2e30793e6bfa519d2a4da94c","target":"record","created_at":"2026-07-05T10:11:22Z","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":"2e988cc2800da8e277f1a4f9fd592d1c67d6c3c94f5bf181e62f334e67728fdd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:35:00Z","title_canon_sha256":"13944ba26cdf99fd2b978018e8189fc9d8140b67b3a5fda3e4eab7e1e584156d"},"schema_version":"1.0","source":{"id":"2407.12504","kind":"arxiv","version":2}},"canonical_sha256":"7a619688071e79506f46baaaebe4653acdb0e58a96fbacd0dd2b9b8e41d0e050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a619688071e79506f46baaaebe4653acdb0e58a96fbacd0dd2b9b8e41d0e050","first_computed_at":"2026-07-05T10:11:22.354446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:22.354446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3tTs7FeSiSKfFwR/9XmUSEoHmUnTI845SP84uJ1j0GdyLaeC502ZDBAWdIM+u5JUTMYsWIwtJLGSE5KJldyfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:22.354982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12504","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b36d28e01489d12d8cbe4d200ee9445242ebfbf2e30793e6bfa519d2a4da94c","sha256:0fea71fc6d5583aeabe54a1b328e790860ce5ad8c92b03491bd3b31a24281e2a"],"state_sha256":"30e9fb965c6a45d15bbae0f7dec8d244043e20d4d7a978624d31470966b97b82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BLIrZBsJ4kRSLgyNUcUnhO9bdetX8vnOP4p9/ql4K5TDcZeaytaVpqujlbU3KDW+UL8B2F8Lgh5ihAWhSKZfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:06:06.130864Z","bundle_sha256":"12713eed1a515e65a7981ca51fc8723c5faa5abbd6978c874d72ef2c95303a70"}}