{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HD4RXF725JG4IRGIM6A7L44IS4","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":"70dd267adba85bdfd320d3385cc6f2f77eea004f0696a653b659a04207e61ac7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T09:39:28Z","title_canon_sha256":"8ef50b278a04c7c854e23faecafed8933a611c3f7a62033f0e54877377852279"},"schema_version":"1.0","source":{"id":"2410.23771","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23771","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23771v5","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23771","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"HD4RXF725JG4","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"HD4RXF725JG4IRGI","created_at":"2026-07-05T11:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"HD4RXF72","created_at":"2026-07-05T11:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:8bd3b5c8da7522957279c109e9305913db03ad8ea6d7ba59a51121bc2063a124","target":"graph","created_at":"2026-07-05T11:43:58Z","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/2410.23771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this limitation has remained unclear. In this work, we provide a comprehensive explanation for this issue. We find that PPL overlooks key tokens, which are essential for long-context understanding, by averag","authors_text":"Bolin Ding, Chenheng Zhang, Jinyang Gao, Lizhe Fang, Stefanie Jegelka, Yifei Wang, Yisen Wang, Zhaoyang Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T09:39:28Z","title":"What is Wrong with Perplexity for Long-context Language Modeling?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23771","kind":"arxiv","version":5},"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":"sha256:521fd1a0d9e8a345d7900c66fb396d8bad35ec12e98c4b75ba71da77ba2a2b6e","target":"record","created_at":"2026-07-05T11:43:58Z","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":"70dd267adba85bdfd320d3385cc6f2f77eea004f0696a653b659a04207e61ac7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T09:39:28Z","title_canon_sha256":"8ef50b278a04c7c854e23faecafed8933a611c3f7a62033f0e54877377852279"},"schema_version":"1.0","source":{"id":"2410.23771","kind":"arxiv","version":5}},"canonical_sha256":"38f91b97faea4dc444c86781f5f388971d1d83a2452eb4760cd3c8c4d402bec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38f91b97faea4dc444c86781f5f388971d1d83a2452eb4760cd3c8c4d402bec1","first_computed_at":"2026-07-05T11:43:58.209613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:58.209613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6pmLYSOuGF5ENkmuu9uHZJG5eq5qSGIdrNYbss/u/3uQePtEBjhnIsMI8skD91R6TpB8XNPOPTVrg6VlGmACCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:58.210099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23771","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:521fd1a0d9e8a345d7900c66fb396d8bad35ec12e98c4b75ba71da77ba2a2b6e","sha256:8bd3b5c8da7522957279c109e9305913db03ad8ea6d7ba59a51121bc2063a124"],"state_sha256":"346f4c40263b8bfbf8eed1d87abccd815409acc9e4e37b24f32365acc0817122"}