{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XT2RTVAOHRYMZ6LMNTNXMLWO3H","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":"c5bd999a3af6224979c88496a2ec755a639daa1d79c6df86998231afa9d272c0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-16T16:07:18Z","title_canon_sha256":"754be365bc76a6918be3fcdc36aa9ec467bd916fe2046bb1e27a17f6b91ef301"},"schema_version":"1.0","source":{"id":"2504.12365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12365","created_at":"2026-07-05T10:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12365v1","created_at":"2026-07-05T10:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12365","created_at":"2026-07-05T10:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"XT2RTVAOHRYM","created_at":"2026-07-05T10:50:14Z"},{"alias_kind":"pith_short_16","alias_value":"XT2RTVAOHRYMZ6LM","created_at":"2026-07-05T10:50:14Z"},{"alias_kind":"pith_short_8","alias_value":"XT2RTVAO","created_at":"2026-07-05T10:50:14Z"}],"graph_snapshots":[{"event_id":"sha256:ca90856bf14e7955950920a0d8578c1425f594dc0166870fb69493848ab43e67","target":"graph","created_at":"2026-07-05T10:50:14Z","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/2504.12365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present a benchmark that consists of Jupyter notebooks development trajectories and allows measuring how large language models (LLMs) can leverage runtime information for predicting code output and code generation. We demonstrate that the current generation of LLMs performs poorly on these tasks and argue that there exists a significantly understudied domain in the development of code-based models, which involves incorporating the runtime context.","authors_text":"Konstantin Grotov, Sergey Titov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-16T16:07:18Z","title":"Themisto: Jupyter-Based Runtime Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12365","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":"sha256:47e47ac689447b7130fea8cfbd4f005acd33f1da6aa83cdcab929a753167d1de","target":"record","created_at":"2026-07-05T10:50:14Z","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":"c5bd999a3af6224979c88496a2ec755a639daa1d79c6df86998231afa9d272c0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-16T16:07:18Z","title_canon_sha256":"754be365bc76a6918be3fcdc36aa9ec467bd916fe2046bb1e27a17f6b91ef301"},"schema_version":"1.0","source":{"id":"2504.12365","kind":"arxiv","version":1}},"canonical_sha256":"bcf519d40e3c70ccf96c6cdb762eced9d94994836148823ed41a83dbdaa24c29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcf519d40e3c70ccf96c6cdb762eced9d94994836148823ed41a83dbdaa24c29","first_computed_at":"2026-07-05T10:50:14.945046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:14.945046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UTiCkZZ3dUeLqZC60m/y/TmfDT74GTFUu+uUA6PP8iXs52Mqce7/6HeFmxXCVY7yZFW6IgYB9O+YiSKXJlTpBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:14.945575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47e47ac689447b7130fea8cfbd4f005acd33f1da6aa83cdcab929a753167d1de","sha256:ca90856bf14e7955950920a0d8578c1425f594dc0166870fb69493848ab43e67"],"state_sha256":"d97820dfbcf45f868ad72f9fcba1a4fce775b1a4fd423d293722fec8488abcc9"}