{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VHS654F5UZJSYNU4J6ADWCJ2TP","short_pith_number":"pith:VHS654F5","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"},"canonical_sha256":"a9e5eef0bda6532c369c4f803b093a9beafb9e36a8c38eefc897dba7428b4018","source":{"kind":"arxiv","id":"2601.00575","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VHS654F5UZJSYNU4J6ADWCJ2TP","target":"record","payload":{"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"},"canonical_sha256":"a9e5eef0bda6532c369c4f803b093a9beafb9e36a8c38eefc897dba7428b4018","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"},"source_kind":"arxiv","source_id":"2601.00575","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":"2026-05-27T01:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wiz0A0/rDR557HT/YMOry6H9Wq06k1qUzTA9NGpu8TvjbFT2Y3nje5XizbaXNDU43m07G0kNGFO8SHnHWUlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:32:50.848592Z"},"content_sha256":"4da01270ae53b678634bdc980cc6246a024108d5b6114156ec8c88ddb2c1cf7e","schema_version":"1.0","event_id":"sha256:4da01270ae53b678634bdc980cc6246a024108d5b6114156ec8c88ddb2c1cf7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VHS654F5UZJSYNU4J6ADWCJ2TP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BxntAiTvrrhQols4R5ECs89mRoshu23WHriRDvHuJsZbDy4aqZVRF78Q+2ihS78o+qa282e5xaj4ad4ON+AcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:32:50.848965Z"},"content_sha256":"dd6d975a916a715861bc5581ba43ac6523bbbdb00cf68a8b8c9cdf8a27c4bb74","schema_version":"1.0","event_id":"sha256:dd6d975a916a715861bc5581ba43ac6523bbbdb00cf68a8b8c9cdf8a27c4bb74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/bundle.json","state_url":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/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":"2026-06-02T21:32:50Z","links":{"resolver":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP","bundle":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/bundle.json","state":"https://pith.science/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHS654F5UZJSYNU4J6ADWCJ2TP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6KcqvxzELAj6R6/FTuir3grvNtBr7DUbLB926poQRSfnynXMqRTjNO4Pkd7ZEM9MCjIwk3kp7du/3tRR7z9OCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:32:50.851004Z","bundle_sha256":"e54b4d381dbc297dde5a9d697f4e29f5b6a5d598a5b213e10f37edbaa6ecb629"}}