{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTLF5DB72RQA7T47EMBDWJKNN3","short_pith_number":"pith:YTLF5DB7","schema_version":"1.0","canonical_sha256":"c4d65e8c3fd4600fcf9f23023b254d6ec3d4b7edc5eec9d5ed9089a6da31e56d","source":{"kind":"arxiv","id":"2508.19578","version":1},"attestation_state":"computed","paper":{"title":"Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hwanjun Song, Hyangsuk Min, Jiaqi Deng, Kim Yul, Minjeong Ban, Nicole Hee-Yeon Kim, Taewon Yun, Yuho Lee","submitted_at":"2025-08-27T05:23:22Z","abstract_excerpt":"We introduce HAMLET, a holistic and automated framework for evaluating the long-context comprehension of large language models (LLMs). HAMLET structures source texts into a three-level key-fact hierarchy at root-, branch-, and leaf-levels, and employs query-focused summarization to evaluate how well models recall and faithfully represent information at each level. To validate the reliability of our fully automated pipeline, we conduct a systematic human study, showing that our automatic evaluation achieves over 90% agreement with expert human judgments, while reducing the cost by up to 25 time"},"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":"2508.19578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T05:23:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84df72bdb618c0c908996228acfd2527ce9cf125d85b09f72c5f91a98444eb89","abstract_canon_sha256":"6805f4159c3f7aa776f1cd1fb6ebb3f237f5956a5c24449f46ee241c4b98803c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:14.448536Z","signature_b64":"wBppr1MXokzrqxnO0LkTOjI9vhzwn4BmUzcCB0EkrHyC/SyUSdqONpwmuSYco4GAsSWYVdgYKTF6hWyhfHr3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d65e8c3fd4600fcf9f23023b254d6ec3d4b7edc5eec9d5ed9089a6da31e56d","last_reissued_at":"2026-07-05T12:00:14.448060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:14.448060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hwanjun Song, Hyangsuk Min, Jiaqi Deng, Kim Yul, Minjeong Ban, Nicole Hee-Yeon Kim, Taewon Yun, Yuho Lee","submitted_at":"2025-08-27T05:23:22Z","abstract_excerpt":"We introduce HAMLET, a holistic and automated framework for evaluating the long-context comprehension of large language models (LLMs). HAMLET structures source texts into a three-level key-fact hierarchy at root-, branch-, and leaf-levels, and employs query-focused summarization to evaluate how well models recall and faithfully represent information at each level. To validate the reliability of our fully automated pipeline, we conduct a systematic human study, showing that our automatic evaluation achieves over 90% agreement with expert human judgments, while reducing the cost by up to 25 time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19578","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/2508.19578/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":"2508.19578","created_at":"2026-07-05T12:00:14.448115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19578v1","created_at":"2026-07-05T12:00:14.448115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19578","created_at":"2026-07-05T12:00:14.448115+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTLF5DB72RQA","created_at":"2026-07-05T12:00:14.448115+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTLF5DB72RQA7T47","created_at":"2026-07-05T12:00:14.448115+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTLF5DB7","created_at":"2026-07-05T12:00:14.448115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3","json":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3.json","graph_json":"https://pith.science/api/pith-number/YTLF5DB72RQA7T47EMBDWJKNN3/graph.json","events_json":"https://pith.science/api/pith-number/YTLF5DB72RQA7T47EMBDWJKNN3/events.json","paper":"https://pith.science/paper/YTLF5DB7"},"agent_actions":{"view_html":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3","download_json":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3.json","view_paper":"https://pith.science/paper/YTLF5DB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19578&json=true","fetch_graph":"https://pith.science/api/pith-number/YTLF5DB72RQA7T47EMBDWJKNN3/graph.json","fetch_events":"https://pith.science/api/pith-number/YTLF5DB72RQA7T47EMBDWJKNN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3/action/storage_attestation","attest_author":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3/action/author_attestation","sign_citation":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3/action/citation_signature","submit_replication":"https://pith.science/pith/YTLF5DB72RQA7T47EMBDWJKNN3/action/replication_record"}},"created_at":"2026-07-05T12:00:14.448115+00:00","updated_at":"2026-07-05T12:00:14.448115+00:00"}