{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LZ3D3G46VLETAWS6EXEPKPGQD6","short_pith_number":"pith:LZ3D3G46","schema_version":"1.0","canonical_sha256":"5e763d9b9eaac9305a5e25c8f53cd01fa6b455df36ea251d7facbc29d4bf7732","source":{"kind":"arxiv","id":"2605.12697","version":1},"attestation_state":"computed","paper":{"title":"A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The critical inverse-temperature scale for self-attention concentration is fixed by an upper-tail accumulation scale derived from the gap-counting function of each attention row.","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Ryo Karakida, Tomohiro Hayase","submitted_at":"2026-05-12T19:48:36Z","abstract_excerpt":"Length-dependent logit rescaling is widely used to stabilize long-context self-attention, but existing analyses and methods suggest conflicting inverse-temperature laws for the context length $n$, ranging from $(\\log n)^{1/2}$ to $\\log n$ and $(\\log n)^2$. We provide a general theory showing that the desirable scale is determined by the gap-counting function $N_n$ of each attention row. Counting how many competitors lie within each gap from the maximum, we define an upper-tail accumulation scale and prove that it gives the critical inverse-temperature scale for softmax concentration: below thi"},"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":true},"canonical_record":{"source":{"id":"2605.12697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-12T19:48:36Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"e7e7361a6b0dd8924ec2cb1a074f514b5271392991d61c7399ec9260db43d215","abstract_canon_sha256":"c8eee8d2dfea4f8b5dcebcadbf84a54bb0b23d3731d813dcc701e3dc1b3884d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:49.754197Z","signature_b64":"BZDeJL62Fz6lGE2kGWotgg8+4+NaBpXyulbLLoJgk+fUwQz7LdiGNARdf1NrszGJIj/86dZA5GGV7DkH1hXoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e763d9b9eaac9305a5e25c8f53cd01fa6b455df36ea251d7facbc29d4bf7732","last_reissued_at":"2026-05-18T03:09:49.753423Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:49.753423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The critical inverse-temperature scale for self-attention concentration is fixed by an upper-tail accumulation scale derived from the gap-counting function of each attention row.","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Ryo Karakida, Tomohiro Hayase","submitted_at":"2026-05-12T19:48:36Z","abstract_excerpt":"Length-dependent logit rescaling is widely used to stabilize long-context self-attention, but existing analyses and methods suggest conflicting inverse-temperature laws for the context length $n$, ranging from $(\\log n)^{1/2}$ to $\\log n$ and $(\\log n)^2$. We provide a general theory showing that the desirable scale is determined by the gap-counting function $N_n$ of each attention row. Counting how many competitors lie within each gap from the maximum, we define an upper-tail accumulation scale and prove that it gives the critical inverse-temperature scale for softmax concentration: below thi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we define an upper-tail accumulation scale and prove that it gives the critical inverse-temperature scale for softmax concentration: below this scale, the top competitors remain unseparated, whereas above it, the attention entropy collapses.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the gap-counting function N_n of each attention row fully determines the critical scale and that the attention-score distributions admit well-defined successive gaps from the maximum.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The upper-tail accumulation scale derived from the gap-counting function N_n sets the critical inverse temperature for softmax attention concentration, unifying prior conflicting laws as special cases of different N_n.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The critical inverse-temperature scale for self-attention concentration is fixed by an upper-tail accumulation scale derived from the gap-counting function of each attention row.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"af513fa9b8c116bca3bf7ede604e09971e8c2013a855088d9e39b9f009f27f80"},"source":{"id":"2605.12697","kind":"arxiv","version":1},"verdict":{"id":"8cc0e077-44f0-4d3f-aca3-acba8844ef1e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:50:11.335422Z","strongest_claim":"we define an upper-tail accumulation scale and prove that it gives the critical inverse-temperature scale for softmax concentration: below this scale, the top competitors remain unseparated, whereas above it, the attention entropy collapses.","one_line_summary":"The upper-tail accumulation scale derived from the gap-counting function N_n sets the critical inverse temperature for softmax attention concentration, unifying prior conflicting laws as special cases of different N_n.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the gap-counting function N_n of each attention row fully determines the critical scale and that the attention-score distributions admit well-defined successive gaps from the maximum.","pith_extraction_headline":"The critical inverse-temperature scale for self-attention concentration is fixed by an upper-tail accumulation scale derived from the gap-counting function of each attention row."},"references":{"count":32,"sample":[{"doi":"","year":2017,"title":"Attention is all you need","work_id":"4c6ff6f5-f994-47e1-b9da-213c378d21b8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Infinite attention: NNGP and NTK for deep attention networks","work_id":"5edec609-57d6-4fff-a106-35d1df33eb4b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Infinite limits of multi-head transformer dynamics","work_id":"455a8000-ba63-4352-a5f6-6c98bb18e2d6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Infinite-width limit of a single attention layer: Analysis via tensor programs","work_id":"5998f624-fb37-489c-a484-ada3b2168e32","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"A mathematical perspective on transformers","work_id":"d081e886-f9fa-4d25-9355-b6f6d2e2af62","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"e0407cc42983bdab86c360498ce54eddd54b63baa391db3ca6e5cd661a1b5a3c","internal_anchors":3},"formal_canon":{"evidence_count":3,"snapshot_sha256":"dab92689155357b0c3c51b06698660927100bb511d22f38635a9f2d1129f175c"},"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":"2605.12697","created_at":"2026-05-18T03:09:49.753555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12697v1","created_at":"2026-05-18T03:09:49.753555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12697","created_at":"2026-05-18T03:09:49.753555+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZ3D3G46VLET","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZ3D3G46VLETAWS6","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZ3D3G46","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6","json":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6.json","graph_json":"https://pith.science/api/pith-number/LZ3D3G46VLETAWS6EXEPKPGQD6/graph.json","events_json":"https://pith.science/api/pith-number/LZ3D3G46VLETAWS6EXEPKPGQD6/events.json","paper":"https://pith.science/paper/LZ3D3G46"},"agent_actions":{"view_html":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6","download_json":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6.json","view_paper":"https://pith.science/paper/LZ3D3G46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12697&json=true","fetch_graph":"https://pith.science/api/pith-number/LZ3D3G46VLETAWS6EXEPKPGQD6/graph.json","fetch_events":"https://pith.science/api/pith-number/LZ3D3G46VLETAWS6EXEPKPGQD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6/action/storage_attestation","attest_author":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6/action/author_attestation","sign_citation":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6/action/citation_signature","submit_replication":"https://pith.science/pith/LZ3D3G46VLETAWS6EXEPKPGQD6/action/replication_record"}},"created_at":"2026-05-18T03:09:49.753555+00:00","updated_at":"2026-05-18T03:09:49.753555+00:00"}