{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T3IGRLS3BGJ3CVCX4BO7CUJP7D","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":"9940b335e755a44805f4225e15c59d6b655e967b00374834b195355afc1e73e8","cross_cats_sorted":["cs.AI","cs.DM","math.CA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-07T03:51:57Z","title_canon_sha256":"e8597fec481ada6913ed147f94420ebe3dab9bf165da97c0524cf36d9a95d181"},"schema_version":"1.0","source":{"id":"2510.05554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05554","created_at":"2026-07-31T01:08:51Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05554v2","created_at":"2026-07-31T01:08:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05554","created_at":"2026-07-31T01:08:51Z"},{"alias_kind":"pith_short_12","alias_value":"T3IGRLS3BGJ3","created_at":"2026-07-31T01:08:51Z"},{"alias_kind":"pith_short_16","alias_value":"T3IGRLS3BGJ3CVCX","created_at":"2026-07-31T01:08:51Z"},{"alias_kind":"pith_short_8","alias_value":"T3IGRLS3","created_at":"2026-07-31T01:08:51Z"}],"graph_snapshots":[{"event_id":"sha256:b6634ca64764e2e2dabf92573ed461c72941887dc4e89638e2ff2b75a0e50594","target":"graph","created_at":"2026-07-31T01:08:51Z","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/2510.05554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length $n$ increases, causing tokens to cluster excessively, a phenomenon known as rank-collapse. While $\\textit{attention scaling}$ effectively addresses this deficiency by rescaling attention scores with a polylogarithmic factor $\\beta_n$, theoretical justification for this approach remains lacking.\n  We analyze a simplified yet tractable model that magnifies the effect of attention scaling. In this model, attention exhibits a phase t","authors_text":"Philippe Rigollet, Shi Chen, Yury Polyanskiy, Zhengjiang Lin","cross_cats":["cs.AI","cs.DM","math.CA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-07T03:51:57Z","title":"Critical attention scaling in long-context transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05554","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":"sha256:0ec305b52a1a65d40c59696d18eaf0463d7762df8274d179ce66b2daf7545485","target":"record","created_at":"2026-07-31T01:08:51Z","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":"9940b335e755a44805f4225e15c59d6b655e967b00374834b195355afc1e73e8","cross_cats_sorted":["cs.AI","cs.DM","math.CA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-07T03:51:57Z","title_canon_sha256":"e8597fec481ada6913ed147f94420ebe3dab9bf165da97c0524cf36d9a95d181"},"schema_version":"1.0","source":{"id":"2510.05554","kind":"arxiv","version":2}},"canonical_sha256":"9ed068ae5b0993b15457e05df1512ff8ffd0b5fc6524c68cd8260997dcd467f9","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ed068ae5b0993b15457e05df1512ff8ffd0b5fc6524c68cd8260997dcd467f9","first_computed_at":"2026-07-31T01:08:51.370122Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:08:51.370122Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2510.05554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ec305b52a1a65d40c59696d18eaf0463d7762df8274d179ce66b2daf7545485","sha256:b6634ca64764e2e2dabf92573ed461c72941887dc4e89638e2ff2b75a0e50594"],"state_sha256":"a4cd10e86d447928d8850c68a1a43e5e2a25eed20f4b9cc3e69d5691915063ae"}