{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YTLF5DB72RQA7T47EMBDWJKNN3","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":"6805f4159c3f7aa776f1cd1fb6ebb3f237f5956a5c24449f46ee241c4b98803c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T05:23:22Z","title_canon_sha256":"84df72bdb618c0c908996228acfd2527ce9cf125d85b09f72c5f91a98444eb89"},"schema_version":"1.0","source":{"id":"2508.19578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19578","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19578v1","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19578","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"pith_short_12","alias_value":"YTLF5DB72RQA","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"pith_short_16","alias_value":"YTLF5DB72RQA7T47","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"pith_short_8","alias_value":"YTLF5DB7","created_at":"2026-07-05T12:00:14Z"}],"graph_snapshots":[{"event_id":"sha256:5a00d7b6c60218fc6eb602c4f0677a886b97eb40efa2a85e29fc95bb31041943","target":"graph","created_at":"2026-07-05T12:00:14Z","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/2508.19578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hwanjun Song, Hyangsuk Min, Jiaqi Deng, Kim Yul, Minjeong Ban, Nicole Hee-Yeon Kim, Taewon Yun, Yuho Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T05:23:22Z","title":"Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19578","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:a3aad47f9c3797055338ef6bc3a139cfa093d0d7f11c83eb5f5e00c7eed69641","target":"record","created_at":"2026-07-05T12:00:14Z","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":"6805f4159c3f7aa776f1cd1fb6ebb3f237f5956a5c24449f46ee241c4b98803c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T05:23:22Z","title_canon_sha256":"84df72bdb618c0c908996228acfd2527ce9cf125d85b09f72c5f91a98444eb89"},"schema_version":"1.0","source":{"id":"2508.19578","kind":"arxiv","version":1}},"canonical_sha256":"c4d65e8c3fd4600fcf9f23023b254d6ec3d4b7edc5eec9d5ed9089a6da31e56d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4d65e8c3fd4600fcf9f23023b254d6ec3d4b7edc5eec9d5ed9089a6da31e56d","first_computed_at":"2026-07-05T12:00:14.448060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:14.448060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wBppr1MXokzrqxnO0LkTOjI9vhzwn4BmUzcCB0EkrHyC/SyUSdqONpwmuSYco4GAsSWYVdgYKTF6hWyhfHr3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:14.448536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3aad47f9c3797055338ef6bc3a139cfa093d0d7f11c83eb5f5e00c7eed69641","sha256:5a00d7b6c60218fc6eb602c4f0677a886b97eb40efa2a85e29fc95bb31041943"],"state_sha256":"d63be12207bab8d87b97b1eb0d166c2af3b30d17b210e410fcae3ac356542217"}