{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GGXWJGXD32DDTNVODJ7K5X2G7Z","short_pith_number":"pith:GGXWJGXD","canonical_record":{"source":{"id":"2607.19104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-21T13:46:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eca7642c1b6ba56778bfb175c842e9edad5931997e6c714da8225ee593d28eb0","abstract_canon_sha256":"328c0ec0e1ffe3ba80f4a3b42f84deb3eb620946bf7c0b3956ae8ede249a6312"},"schema_version":"1.0"},"canonical_sha256":"31af649ae3de8639b6ae1a7eaedf46fe4def965a1df8c5cde6c76a98dd590fe8","source":{"kind":"arxiv","id":"2607.19104","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19104","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19104v1","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19104","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"GGXWJGXD32DD","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"GGXWJGXD32DDTNVO","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"GGXWJGXD","created_at":"2026-07-22T01:24:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GGXWJGXD32DDTNVODJ7K5X2G7Z","target":"record","payload":{"canonical_record":{"source":{"id":"2607.19104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-21T13:46:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eca7642c1b6ba56778bfb175c842e9edad5931997e6c714da8225ee593d28eb0","abstract_canon_sha256":"328c0ec0e1ffe3ba80f4a3b42f84deb3eb620946bf7c0b3956ae8ede249a6312"},"schema_version":"1.0"},"canonical_sha256":"31af649ae3de8639b6ae1a7eaedf46fe4def965a1df8c5cde6c76a98dd590fe8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:08.845189Z","signature_b64":"8rdfxIdREUOfKjKa0VOGEwPj1ZdJHWT0s18M6nw/QQRtufOEV4gl+ckO5DU0Sqpn9PypB02QMcHDn8qff7vHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31af649ae3de8639b6ae1a7eaedf46fe4def965a1df8c5cde6c76a98dd590fe8","last_reissued_at":"2026-07-22T01:24:08.844385Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:08.844385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.19104","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":"2026-07-22T01:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FnXZNGqIcArRsb+rzrw3a4Sbva4+r895iRwJS03bW0WOpoFxMZUrSs+q5ThhX+c/cLAnByHaxyT7sjTuP4ICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:54:08.076379Z"},"content_sha256":"5450a69b4595b956b6d6cc4970750634c22001874ae9f8ee4cc674f2405c9edb","schema_version":"1.0","event_id":"sha256:5450a69b4595b956b6d6cc4970750634c22001874ae9f8ee4cc674f2405c9edb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GGXWJGXD32DDTNVODJ7K5X2G7Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"David Lo, Gou Tan, Jieke Shi, Jonathan Pan, Swee Liang Wong, Weifeng Sun, Ye Fan, Yuan Yidi, Yuchen Chen","submitted_at":"2026-07-21T13:46:52Z","abstract_excerpt":"Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limited in scale, domain coverage, or executable verification, leaving the true gap between current LLMs and reliable scientific code generators inadequately assessed. To address these limitations, we present SciCodePile, the largest scientific code corpus to date, constructed from 37,737 public repositories and collectively comprising 128GB of code that spans multiple computational science disciplines. From this corpus, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19104","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/2607.19104/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":"2026-07-22T01:24:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sf0WhgdT/YCAJook/DDVo/ntHRp8eNwI5kXPqC2djsmouqSrsvGYZJ1u/3ly1HP1A1TnI4hUqqIY1yadN2rRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:54:08.076871Z"},"content_sha256":"33724549185ba97e00144c843f9892e738a3763cf056f738e74166bcaa1eab90","schema_version":"1.0","event_id":"sha256:33724549185ba97e00144c843f9892e738a3763cf056f738e74166bcaa1eab90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z/bundle.json","state_url":"https://pith.science/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z/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":"2026-08-04T04:54:08Z","links":{"resolver":"https://pith.science/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z","bundle":"https://pith.science/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z/bundle.json","state":"https://pith.science/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGXWJGXD32DDTNVODJ7K5X2G7Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GGXWJGXD32DDTNVODJ7K5X2G7Z","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":"328c0ec0e1ffe3ba80f4a3b42f84deb3eb620946bf7c0b3956ae8ede249a6312","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-21T13:46:52Z","title_canon_sha256":"eca7642c1b6ba56778bfb175c842e9edad5931997e6c714da8225ee593d28eb0"},"schema_version":"1.0","source":{"id":"2607.19104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19104","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19104v1","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19104","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"pith_short_12","alias_value":"GGXWJGXD32DD","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"pith_short_16","alias_value":"GGXWJGXD32DDTNVO","created_at":"2026-07-22T01:24:08Z"},{"alias_kind":"pith_short_8","alias_value":"GGXWJGXD","created_at":"2026-07-22T01:24:08Z"}],"graph_snapshots":[{"event_id":"sha256:33724549185ba97e00144c843f9892e738a3763cf056f738e74166bcaa1eab90","target":"graph","created_at":"2026-07-22T01:24:08Z","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/2607.19104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel at general-purpose code generation, yet how well they handle scientific code remains an open question. Existing datasets and benchmarks are limited in scale, domain coverage, or executable verification, leaving the true gap between current LLMs and reliable scientific code generators inadequately assessed. To address these limitations, we present SciCodePile, the largest scientific code corpus to date, constructed from 37,737 public repositories and collectively comprising 128GB of code that spans multiple computational science disciplines. From this corpus, ","authors_text":"David Lo, Gou Tan, Jieke Shi, Jonathan Pan, Swee Liang Wong, Weifeng Sun, Ye Fan, Yuan Yidi, Yuchen Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-21T13:46:52Z","title":"SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19104","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":"sha256:5450a69b4595b956b6d6cc4970750634c22001874ae9f8ee4cc674f2405c9edb","target":"record","created_at":"2026-07-22T01:24:08Z","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":"328c0ec0e1ffe3ba80f4a3b42f84deb3eb620946bf7c0b3956ae8ede249a6312","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-21T13:46:52Z","title_canon_sha256":"eca7642c1b6ba56778bfb175c842e9edad5931997e6c714da8225ee593d28eb0"},"schema_version":"1.0","source":{"id":"2607.19104","kind":"arxiv","version":1}},"canonical_sha256":"31af649ae3de8639b6ae1a7eaedf46fe4def965a1df8c5cde6c76a98dd590fe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31af649ae3de8639b6ae1a7eaedf46fe4def965a1df8c5cde6c76a98dd590fe8","first_computed_at":"2026-07-22T01:24:08.844385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:08.844385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8rdfxIdREUOfKjKa0VOGEwPj1ZdJHWT0s18M6nw/QQRtufOEV4gl+ckO5DU0Sqpn9PypB02QMcHDn8qff7vHAA==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:08.845189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5450a69b4595b956b6d6cc4970750634c22001874ae9f8ee4cc674f2405c9edb","sha256:33724549185ba97e00144c843f9892e738a3763cf056f738e74166bcaa1eab90"],"state_sha256":"9d0d651993140818e2558a9049dc8d3c07c33570f811f832247ec0953fc1a6b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFAo9AQge2kUWQjXrDVc5EjdxJkI5XC6uDMEtvHDafWfrrfM4TxvpOAhLzsa/WUvumZvSBLMOyQ5jES6TOagDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:54:08.080581Z","bundle_sha256":"2e72924fe689e8ffb6ff7ef099384be61ad8eb8df2a5cdd47f980f0d3f14bca7"}}