{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DMFM5PS5KZSTDL3W5PZ3UXDNKM","short_pith_number":"pith:DMFM5PS5","schema_version":"1.0","canonical_sha256":"1b0acebe5d566531af76ebf3ba5c6d53364799f45aa2e706745bf1c784738d33","source":{"kind":"arxiv","id":"2605.15514","version":1},"attestation_state":"computed","paper":{"title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"RoPE-based attention loses locality bias and token relevance consistency as context length grows, with failure probability approaching 0.5.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aram Galstyan, Eliu A Huerta, Hao Peng, Minyang Tian, Phillip Harris, Srikanth Ronanki, Subendhu Rongali, Yufeng Du","submitted_at":"2026-05-15T01:16:16Z","abstract_excerpt":"We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specific content of the context and depends only on its length. We prove that as context length increases, RoPE-based attention becomes unpredictable and loses two properties that are central to its effectiveness. First, it loses its locality bias: RoPE is no more likely to favor nearer positions than substantially farther ones. Second, it loses consistency in token relevance: a key vector that receives a higher attention s"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T01:16:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1e6babc51c35f5873e9ea13697cfd84dec7866f14de727051ee852cf1cbb42aa","abstract_canon_sha256":"310a4e2e0e2c9f087f8e9d1a8afe364b09bee276480ed57e149f56fabbfc59eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:02.610781Z","signature_b64":"3NJyNy2aysvNxV0m2guO9igQtzkdYfm3bWrUPb60Y5nENTwZNRtj+avjRgdgC51C/NX0yIMiM/fQ1oSRWPLVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b0acebe5d566531af76ebf3ba5c6d53364799f45aa2e706745bf1c784738d33","last_reissued_at":"2026-05-20T00:01:02.609785Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:02.609785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"RoPE-based attention loses locality bias and token relevance consistency as context length grows, with failure probability approaching 0.5.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aram Galstyan, Eliu A Huerta, Hao Peng, Minyang Tian, Phillip Harris, Srikanth Ronanki, Subendhu Rongali, Yufeng Du","submitted_at":"2026-05-15T01:16:16Z","abstract_excerpt":"We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specific content of the context and depends only on its length. We prove that as context length increases, RoPE-based attention becomes unpredictable and loses two properties that are central to its effectiveness. First, it loses its locality bias: RoPE is no more likely to favor nearer positions than substantially farther ones. Second, it loses consistency in token relevance: a key vector that receives a higher attention s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We prove that as context length increases, RoPE-based attention becomes unpredictable and loses its locality bias and consistency in token relevance, with the probability of failure approaching 0.5.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The theoretical analysis abstracts away from the specific content of the context and depends only on its length.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Proves that RoPE attention loses locality bias and token distinction in long contexts, approaching random behavior independent of content.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RoPE-based attention loses locality bias and token relevance consistency as context length grows, with failure probability approaching 0.5.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b6baae0e772faef81fc052e87cc2c52be3a23dad539069ac6baa7526a0eaa034"},"source":{"id":"2605.15514","kind":"arxiv","version":1},"verdict":{"id":"24f6a120-bea3-469a-ac35-f047796697a4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:29:44.440825Z","strongest_claim":"We prove that as context length increases, RoPE-based attention becomes unpredictable and loses its locality bias and consistency in token relevance, with the probability of failure approaching 0.5.","one_line_summary":"Proves that RoPE attention loses locality bias and token distinction in long contexts, approaching random behavior independent of content.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The theoretical analysis abstracts away from the specific content of the context and depends only on its length.","pith_extraction_headline":"RoPE-based attention loses locality bias and token relevance consistency as context length grows, with failure probability approaching 0.5."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15514/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:17.893729Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:40:36.322934Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T14:51:54.755432Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.053291Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.847002Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.385938Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.633228Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bc7cfd4c2122fea322863127a0fa9246126f23702411932a9c86123cf8db369c"},"references":{"count":55,"sample":[{"doi":"","year":2021,"title":"RoFormer: Enhanced Transformer with Rotary Position Embedding , author=. 2021 , eprint=","work_id":"5fc636be-88c8-4c86-a321-9d1b76f63f13","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context , author=. 2024 , eprint=","work_id":"11af042d-6a6a-489e-9608-119eb98fa8f6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Proceedings of the 41st International Conference on Machine Learning , articleno =","work_id":"98fe2912-080b-4d44-bb7c-7737e89f9d0b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"2026 , institution =","work_id":"d1f73ff4-2701-4e73-acc7-f3f9f51430c6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"International Conference on Learning Representations , year=","work_id":"ba153a1a-8735-43e0-a86c-f7c5a0b27705","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":55,"snapshot_sha256":"bf670194bf65bec3d315f50c230105ed6ae2bf9f6aa5d7c32ff0cbb5806bb531","internal_anchors":2},"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":"2605.15514","created_at":"2026-05-20T00:01:02.609940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15514v1","created_at":"2026-05-20T00:01:02.609940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15514","created_at":"2026-05-20T00:01:02.609940+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMFM5PS5KZST","created_at":"2026-05-20T00:01:02.609940+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMFM5PS5KZSTDL3W","created_at":"2026-05-20T00:01:02.609940+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMFM5PS5","created_at":"2026-05-20T00:01:02.609940+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/DMFM5PS5KZSTDL3W5PZ3UXDNKM","json":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM.json","graph_json":"https://pith.science/api/pith-number/DMFM5PS5KZSTDL3W5PZ3UXDNKM/graph.json","events_json":"https://pith.science/api/pith-number/DMFM5PS5KZSTDL3W5PZ3UXDNKM/events.json","paper":"https://pith.science/paper/DMFM5PS5"},"agent_actions":{"view_html":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM","download_json":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM.json","view_paper":"https://pith.science/paper/DMFM5PS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15514&json=true","fetch_graph":"https://pith.science/api/pith-number/DMFM5PS5KZSTDL3W5PZ3UXDNKM/graph.json","fetch_events":"https://pith.science/api/pith-number/DMFM5PS5KZSTDL3W5PZ3UXDNKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM/action/storage_attestation","attest_author":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM/action/author_attestation","sign_citation":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM/action/citation_signature","submit_replication":"https://pith.science/pith/DMFM5PS5KZSTDL3W5PZ3UXDNKM/action/replication_record"}},"created_at":"2026-05-20T00:01:02.609940+00:00","updated_at":"2026-05-20T00:01:02.609940+00:00"}