{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4YFXFEJTUPH3QCFJBGKBHYHAF5","short_pith_number":"pith:4YFXFEJT","canonical_record":{"source":{"id":"2502.14678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:09:55Z","cross_cats_sorted":[],"title_canon_sha256":"6159de472dadafdf389a442661006c2dd3be13089b20d014b5c18b16fcf48c06","abstract_canon_sha256":"c8db1c285a81761aae18bf5fb7a6eb1a18fdf59f9cc8d71627ffb297402e2a37"},"schema_version":"1.0"},"canonical_sha256":"e60b729133a3cfb808a9099413e0e02f6e03aadae92399d72d2a949bab6aa9f3","source":{"kind":"arxiv","id":"2502.14678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14678","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14678v1","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14678","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"4YFXFEJTUPH3","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"4YFXFEJTUPH3QCFJ","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"4YFXFEJT","created_at":"2026-07-05T10:17:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4YFXFEJTUPH3QCFJBGKBHYHAF5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:09:55Z","cross_cats_sorted":[],"title_canon_sha256":"6159de472dadafdf389a442661006c2dd3be13089b20d014b5c18b16fcf48c06","abstract_canon_sha256":"c8db1c285a81761aae18bf5fb7a6eb1a18fdf59f9cc8d71627ffb297402e2a37"},"schema_version":"1.0"},"canonical_sha256":"e60b729133a3cfb808a9099413e0e02f6e03aadae92399d72d2a949bab6aa9f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:30.990050Z","signature_b64":"d7id1GAg/Q4tKlLL5v0Lqukf4BWVQcfWO37H98s2gTM1u9lZcfY0jWwTBv67qRG9j9lDqIRHlEU62SshUSOmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e60b729133a3cfb808a9099413e0e02f6e03aadae92399d72d2a949bab6aa9f3","last_reissued_at":"2026-07-05T10:17:30.989610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:30.989610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14678","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":"2026-07-05T10:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ooQdkWmr6USKJW+t0Aa6vVxjFZOKaXfysCpdnUKVoniCYdjyx1HwgAC0FxgkHnfeYkFcsHjvD4/9S0Fuoj9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:20:02.572390Z"},"content_sha256":"b7af6171c0ee1c7e32ca912a0e67b1ba48b90177d0f942284c099c566aef77bd","schema_version":"1.0","event_id":"sha256:b7af6171c0ee1c7e32ca912a0e67b1ba48b90177d0f942284c099c566aef77bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4YFXFEJTUPH3QCFJBGKBHYHAF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Get Your LLM to Generate Challenging Problems for Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arkil Patel, Dzmitry Bahdanau, Siva Reddy","submitted_at":"2025-02-20T16:09:55Z","abstract_excerpt":"The pace of evolution of Large Language Models (LLMs) necessitates new approaches for rigorous and comprehensive evaluation. Traditional human annotation is increasingly impracticable due to the complexities and costs involved in generating high-quality, challenging problems. In this work, we introduce CHASE, a unified framework to synthetically generate challenging problems using LLMs without human involvement. For a given task, our approach builds a hard problem in a bottom-up manner from simpler components. Moreover, our framework decomposes the generation process into independently verifia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14678","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/2502.14678/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":"2026-07-05T10:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yw7tKMIGc4pzTc6DFcYH/7BMYPB+xv4NCoQVAY29IbD9HCoQX4eCZqLsL4pRgCmQOysPFWdIZYbq5QkPx8pBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:20:02.574563Z"},"content_sha256":"1b3ea6be2779a0d7d00825d8561103c2609e7757eb34bf73c95d4d9c4631456a","schema_version":"1.0","event_id":"sha256:1b3ea6be2779a0d7d00825d8561103c2609e7757eb34bf73c95d4d9c4631456a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5/bundle.json","state_url":"https://pith.science/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5/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":"2026-08-10T14:20:02Z","links":{"resolver":"https://pith.science/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5","bundle":"https://pith.science/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5/bundle.json","state":"https://pith.science/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YFXFEJTUPH3QCFJBGKBHYHAF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4YFXFEJTUPH3QCFJBGKBHYHAF5","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":"c8db1c285a81761aae18bf5fb7a6eb1a18fdf59f9cc8d71627ffb297402e2a37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:09:55Z","title_canon_sha256":"6159de472dadafdf389a442661006c2dd3be13089b20d014b5c18b16fcf48c06"},"schema_version":"1.0","source":{"id":"2502.14678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14678","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14678v1","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14678","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"4YFXFEJTUPH3","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"4YFXFEJTUPH3QCFJ","created_at":"2026-07-05T10:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"4YFXFEJT","created_at":"2026-07-05T10:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:1b3ea6be2779a0d7d00825d8561103c2609e7757eb34bf73c95d4d9c4631456a","target":"graph","created_at":"2026-07-05T10:17:30Z","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/2502.14678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pace of evolution of Large Language Models (LLMs) necessitates new approaches for rigorous and comprehensive evaluation. Traditional human annotation is increasingly impracticable due to the complexities and costs involved in generating high-quality, challenging problems. In this work, we introduce CHASE, a unified framework to synthetically generate challenging problems using LLMs without human involvement. For a given task, our approach builds a hard problem in a bottom-up manner from simpler components. Moreover, our framework decomposes the generation process into independently verifia","authors_text":"Arkil Patel, Dzmitry Bahdanau, Siva Reddy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:09:55Z","title":"How to Get Your LLM to Generate Challenging Problems for Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14678","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:b7af6171c0ee1c7e32ca912a0e67b1ba48b90177d0f942284c099c566aef77bd","target":"record","created_at":"2026-07-05T10:17:30Z","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":"c8db1c285a81761aae18bf5fb7a6eb1a18fdf59f9cc8d71627ffb297402e2a37","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:09:55Z","title_canon_sha256":"6159de472dadafdf389a442661006c2dd3be13089b20d014b5c18b16fcf48c06"},"schema_version":"1.0","source":{"id":"2502.14678","kind":"arxiv","version":1}},"canonical_sha256":"e60b729133a3cfb808a9099413e0e02f6e03aadae92399d72d2a949bab6aa9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e60b729133a3cfb808a9099413e0e02f6e03aadae92399d72d2a949bab6aa9f3","first_computed_at":"2026-07-05T10:17:30.989610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:30.989610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d7id1GAg/Q4tKlLL5v0Lqukf4BWVQcfWO37H98s2gTM1u9lZcfY0jWwTBv67qRG9j9lDqIRHlEU62SshUSOmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:30.990050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7af6171c0ee1c7e32ca912a0e67b1ba48b90177d0f942284c099c566aef77bd","sha256:1b3ea6be2779a0d7d00825d8561103c2609e7757eb34bf73c95d4d9c4631456a"],"state_sha256":"e0d836b849b4ce338569b6c796a14b81ef44fd367919aedd2c3a5605220e7d4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hH+2ZK2CDKLhS8LPQJgfDL1RnmHGdixIX1kHgKb1mMIi9X8zwYsk0kg9GrReXkk6OtFN+5Rg+XgTAqDprv2NBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:20:02.579164Z","bundle_sha256":"6dc16db7a507f9e0e1e6627a5769431babfac0116ba4c305d6578504b6262cf2"}}