{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJ4MW7BA7CZCKWSQ5HNYC3A77T","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":"d01755ad5d664ed5b59d846e1609f4cc8706734d2904e8b518cde1443a799e2e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T11:53:35Z","title_canon_sha256":"efd891f5da99d56810a9ec26297334f0e8698368ebd7b07d44af29adb04bc74b"},"schema_version":"1.0","source":{"id":"2407.01601","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01601","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01601v2","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01601","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"pith_short_12","alias_value":"KJ4MW7BA7CZC","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"pith_short_16","alias_value":"KJ4MW7BA7CZCKWSQ","created_at":"2026-07-05T08:39:36Z"},{"alias_kind":"pith_short_8","alias_value":"KJ4MW7BA","created_at":"2026-07-05T08:39:36Z"}],"graph_snapshots":[{"event_id":"sha256:d0f1572dfb7f2181b99488bee1ac287157fb8209274fd3fe129ad6b8a170559a","target":"graph","created_at":"2026-07-05T08:39:36Z","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/2407.01601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of large models based on the Transformer architecture, researchers have observed an anomalous phenomenon in the Attention mechanism--there is a very high attention on the first element, which is prevalent across Transformer-based models. It is crucial to understand it for the development of techniques focusing on attention distribution, such as Key-Value (KV) Cache compression and infinite extrapolation; however, the latent cause leaves to be unknown. In this paper, we analyze such a phenomenon from the perspective of waiver phenomenon, which involves reducing the internal valu","authors_text":"Haoyu Deng, Jifang Hu, Jinrong Jiang, Lian Zhao, Linghan Zheng, Penghao Jiang, Qiuzhuang Sun, Ruiqing Yan, Xingbo Du, Yuhang Shao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T11:53:35Z","title":"Unveiling and Controlling Anomalous Attention Distribution in Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01601","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:ed4244cb51ff92b0ef08d50492d1f1c68f2a88763a4585b864085c2b3a2ef727","target":"record","created_at":"2026-07-05T08:39:36Z","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":"d01755ad5d664ed5b59d846e1609f4cc8706734d2904e8b518cde1443a799e2e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T11:53:35Z","title_canon_sha256":"efd891f5da99d56810a9ec26297334f0e8698368ebd7b07d44af29adb04bc74b"},"schema_version":"1.0","source":{"id":"2407.01601","kind":"arxiv","version":2}},"canonical_sha256":"5278cb7c20f8b2255a50e9db816c1ffcce22e5428478424c922327f8934a9833","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5278cb7c20f8b2255a50e9db816c1ffcce22e5428478424c922327f8934a9833","first_computed_at":"2026-07-05T08:39:36.695371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:36.695371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rqPLujI0z8nmvt7GTTOsIAOmD9e/zJIX0jU0U0JogmwmGRJCyoY/Dfu8MatjiphbNUbIJ9F3sk9aWCu757JjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:36.695809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01601","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed4244cb51ff92b0ef08d50492d1f1c68f2a88763a4585b864085c2b3a2ef727","sha256:d0f1572dfb7f2181b99488bee1ac287157fb8209274fd3fe129ad6b8a170559a"],"state_sha256":"2d3637f465748646a4216c9a7adad635839d61bbf89643d36e58365bf78d5773"}