{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VHS654F5UZJSYNU4J6ADWCJ2TP","short_pith_number":"pith:VHS654F5","schema_version":"1.0","canonical_sha256":"a9e5eef0bda6532c369c4f803b093a9beafb9e36a8c38eefc897dba7428b4018","source":{"kind":"arxiv","id":"2601.00575","version":2},"attestation_state":"computed","paper":{"title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dawn Song, Ishir Garg, Neel Kolhe, Xuandong Zhao","submitted_at":"2026-01-02T05:26:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.00575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-02T05:26:27Z","cross_cats_sorted":[],"title_canon_sha256":"171ae1668844e97c224baccb0ebf122a3b242d5372b13bf34b28649ca424f32d","abstract_canon_sha256":"de8596122d181883f263459382a9cbfe7b7c536fe694b533fb7dc824210303a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:41.918173Z","signature_b64":"V+327b2/wCDHlss/5HCkZcSiemo8By5DfGr/7ZVrp/A3xduvQc773i/Le02lCV6ffHKTdpgcDIE8RBXaaHaRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e5eef0bda6532c369c4f803b093a9beafb9e36a8c38eefc897dba7428b4018","last_reissued_at":"2026-05-27T01:05:41.917424Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:41.917424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfoSynth: Information-Guided Benchmark Synthesis for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dawn Song, Ishir Garg, Neel Kolhe, Xuandong Zhao","submitted_at":"2026-01-02T05:26:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.00575","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/2601.00575/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.00575","created_at":"2026-05-27T01:05:41.917541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.00575v2","created_at":"2026-05-27T01:05:41.917541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.00575","created_at":"2026-05-27T01:05:41.917541+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHS654F5UZJS","created_at":"2026-05-27T01:05:41.917541+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHS654F5UZJSYNU4","created_at":"2026-05-27T01:05:41.917541+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHS654F5","created_at":"2026-05-27T01:05:41.917541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.05289","citing_title":"FLARE: Agentic Coverage-Guided Fuzzing for LLM-Based Multi-Agent Systems","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP","json":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP.json","graph_json":"https://pith.science/api/pith-number/VHS654F5UZJSYNU4J6ADWCJ2TP/graph.json","events_json":"https://pith.science/api/pith-number/VHS654F5UZJSYNU4J6ADWCJ2TP/events.json","paper":"https://pith.science/paper/VHS654F5"},"agent_actions":{"view_html":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP","download_json":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP.json","view_paper":"https://pith.science/paper/VHS654F5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.00575&json=true","fetch_graph":"https://pith.science/api/pith-number/VHS654F5UZJSYNU4J6ADWCJ2TP/graph.json","fetch_events":"https://pith.science/api/pith-number/VHS654F5UZJSYNU4J6ADWCJ2TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/action/storage_attestation","attest_author":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/action/author_attestation","sign_citation":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/action/citation_signature","submit_replication":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/action/replication_record"}},"created_at":"2026-05-27T01:05:41.917541+00:00","updated_at":"2026-05-27T01:05:41.917541+00:00"}