{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VHS654F5UZJSYNU4J6ADWCJ2TP","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":"de8596122d181883f263459382a9cbfe7b7c536fe694b533fb7dc824210303a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-02T05:26:27Z","title_canon_sha256":"171ae1668844e97c224baccb0ebf122a3b242d5372b13bf34b28649ca424f32d"},"schema_version":"1.0","source":{"id":"2601.00575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.00575","created_at":"2026-05-27T01:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2601.00575v2","created_at":"2026-05-27T01:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.00575","created_at":"2026-05-27T01:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"VHS654F5UZJS","created_at":"2026-05-27T01:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"VHS654F5UZJSYNU4","created_at":"2026-05-27T01:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"VHS654F5","created_at":"2026-05-27T01:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:dd6d975a916a715861bc5581ba43ac6523bbbdb00cf68a8b8c9cdf8a27c4bb74","target":"graph","created_at":"2026-05-27T01:05:41Z","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/2601.00575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation, but efficiently creating new benchmarks to evaluate these capabilities remains a challenge. Traditional benchmark creation relies on manual human effort, which is expensive and time-consuming. Furthermore, existing benchmarks often contaminate LLM training data, necessitating novel and diverse benchmarks to accurately assess their genuine capabilities. This work introduces InfoSynth, a novel framework for automatically generating and evaluating reasoning benchmarks guided by information-th","authors_text":"Dawn Song, Ishir Garg, Neel Kolhe, Xuandong Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-02T05:26:27Z","title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.00575","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":"sha256:4da01270ae53b678634bdc980cc6246a024108d5b6114156ec8c88ddb2c1cf7e","target":"record","created_at":"2026-05-27T01:05:41Z","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":"de8596122d181883f263459382a9cbfe7b7c536fe694b533fb7dc824210303a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-02T05:26:27Z","title_canon_sha256":"171ae1668844e97c224baccb0ebf122a3b242d5372b13bf34b28649ca424f32d"},"schema_version":"1.0","source":{"id":"2601.00575","kind":"arxiv","version":2}},"canonical_sha256":"a9e5eef0bda6532c369c4f803b093a9beafb9e36a8c38eefc897dba7428b4018","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9e5eef0bda6532c369c4f803b093a9beafb9e36a8c38eefc897dba7428b4018","first_computed_at":"2026-05-27T01:05:41.917424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:41.917424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V+327b2/wCDHlss/5HCkZcSiemo8By5DfGr/7ZVrp/A3xduvQc773i/Le02lCV6ffHKTdpgcDIE8RBXaaHaRAQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:41.918173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.00575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4da01270ae53b678634bdc980cc6246a024108d5b6114156ec8c88ddb2c1cf7e","sha256:dd6d975a916a715861bc5581ba43ac6523bbbdb00cf68a8b8c9cdf8a27c4bb74"],"state_sha256":"6abac4a6bc23945ef93ca2166d07747d7263e52f86f9453de4e88403a616b34b"}