{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RJ5532KHUPBCBBRQKNML7NW4HA","short_pith_number":"pith:RJ5532KH","canonical_record":{"source":{"id":"2507.03340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T06:59:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0a062e6a00d74d563b8f7135c74086377309209ff8a1e6b6aa44ef6861914c4","abstract_canon_sha256":"9fa0f9187cbc89025a7c14274dfbaea3e9f7602b5b789817209f41a8365f6fe7"},"schema_version":"1.0"},"canonical_sha256":"8a7bdde947a3c22086305358bfb6dc381091be13f5a5b3642e28e7274bb7d4d0","source":{"kind":"arxiv","id":"2507.03340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03340","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03340v1","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03340","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"pith_short_12","alias_value":"RJ5532KHUPBC","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"pith_short_16","alias_value":"RJ5532KHUPBCBBRQ","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"pith_short_8","alias_value":"RJ5532KH","created_at":"2026-07-05T11:31:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RJ5532KHUPBCBBRQKNML7NW4HA","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T06:59:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0a062e6a00d74d563b8f7135c74086377309209ff8a1e6b6aa44ef6861914c4","abstract_canon_sha256":"9fa0f9187cbc89025a7c14274dfbaea3e9f7602b5b789817209f41a8365f6fe7"},"schema_version":"1.0"},"canonical_sha256":"8a7bdde947a3c22086305358bfb6dc381091be13f5a5b3642e28e7274bb7d4d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:57.492926Z","signature_b64":"l00+EFemJTAzZjviZL8pRgkGv4ygGVb7ip06gp4nmn/bobHhDredsWjHNh67Qyf5tErahpOH9aB9aVneSmklDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7bdde947a3c22086305358bfb6dc381091be13f5a5b3642e28e7274bb7d4d0","last_reissued_at":"2026-07-05T11:31:57.492148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:57.492148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03340","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoVb9QdtWeyCT/nCzGR1GttsjaVmixM/9F/Chualqa6j+KCMatD1sOq00qwN7no+olDkyPprxWkyJ/7I9PjvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:49:38.458901Z"},"content_sha256":"49c7d0d9240e78e949a41604ade3315cd19e1c1ea901cba2a85c77d44d1baa8a","schema_version":"1.0","event_id":"sha256:49c7d0d9240e78e949a41604ade3315cd19e1c1ea901cba2a85c77d44d1baa8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RJ5532KHUPBCBBRQKNML7NW4HA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Naoki Nishikawa, Rei Higuchi, Taiji Suzuki","submitted_at":"2025-07-04T06:59:17Z","abstract_excerpt":"Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear attention. However, a critical challenge remains: how to choose the feature dimension that governs the approximation quality. Existing methods fix this dimension uniformly across all attention layers, overlooking the diverse roles and complexities of them. In this paper, we propose a principled method to automatically determine the feature dimension in linear at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03340","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.03340/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXQJtOlKY35/Tc5BZXv7VqAWcbGvZUqRcqDxz2JivdHWgi+ZWQF1otYZtKZoUFgR9hYRYjlKgVPBt+PCzxwSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:49:38.459869Z"},"content_sha256":"1e0170e974afeb69e25efdb32fb34e6c0b36eede574bce14acb46d96ffaac751","schema_version":"1.0","event_id":"sha256:1e0170e974afeb69e25efdb32fb34e6c0b36eede574bce14acb46d96ffaac751"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJ5532KHUPBCBBRQKNML7NW4HA/bundle.json","state_url":"https://pith.science/pith/RJ5532KHUPBCBBRQKNML7NW4HA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJ5532KHUPBCBBRQKNML7NW4HA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:49:38Z","links":{"resolver":"https://pith.science/pith/RJ5532KHUPBCBBRQKNML7NW4HA","bundle":"https://pith.science/pith/RJ5532KHUPBCBBRQKNML7NW4HA/bundle.json","state":"https://pith.science/pith/RJ5532KHUPBCBBRQKNML7NW4HA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJ5532KHUPBCBBRQKNML7NW4HA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RJ5532KHUPBCBBRQKNML7NW4HA","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":"9fa0f9187cbc89025a7c14274dfbaea3e9f7602b5b789817209f41a8365f6fe7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T06:59:17Z","title_canon_sha256":"a0a062e6a00d74d563b8f7135c74086377309209ff8a1e6b6aa44ef6861914c4"},"schema_version":"1.0","source":{"id":"2507.03340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03340","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03340v1","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03340","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"pith_short_12","alias_value":"RJ5532KHUPBC","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"pith_short_16","alias_value":"RJ5532KHUPBCBBRQ","created_at":"2026-07-05T11:31:57Z"},{"alias_kind":"pith_short_8","alias_value":"RJ5532KH","created_at":"2026-07-05T11:31:57Z"}],"graph_snapshots":[{"event_id":"sha256:1e0170e974afeb69e25efdb32fb34e6c0b36eede574bce14acb46d96ffaac751","target":"graph","created_at":"2026-07-05T11:31:57Z","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/2507.03340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear attention. However, a critical challenge remains: how to choose the feature dimension that governs the approximation quality. Existing methods fix this dimension uniformly across all attention layers, overlooking the diverse roles and complexities of them. In this paper, we propose a principled method to automatically determine the feature dimension in linear at","authors_text":"Naoki Nishikawa, Rei Higuchi, Taiji Suzuki","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T06:59:17Z","title":"Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03340","kind":"arxiv","version":1},"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":"sha256:49c7d0d9240e78e949a41604ade3315cd19e1c1ea901cba2a85c77d44d1baa8a","target":"record","created_at":"2026-07-05T11:31:57Z","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":"9fa0f9187cbc89025a7c14274dfbaea3e9f7602b5b789817209f41a8365f6fe7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T06:59:17Z","title_canon_sha256":"a0a062e6a00d74d563b8f7135c74086377309209ff8a1e6b6aa44ef6861914c4"},"schema_version":"1.0","source":{"id":"2507.03340","kind":"arxiv","version":1}},"canonical_sha256":"8a7bdde947a3c22086305358bfb6dc381091be13f5a5b3642e28e7274bb7d4d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a7bdde947a3c22086305358bfb6dc381091be13f5a5b3642e28e7274bb7d4d0","first_computed_at":"2026-07-05T11:31:57.492148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:57.492148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l00+EFemJTAzZjviZL8pRgkGv4ygGVb7ip06gp4nmn/bobHhDredsWjHNh67Qyf5tErahpOH9aB9aVneSmklDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:57.492926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49c7d0d9240e78e949a41604ade3315cd19e1c1ea901cba2a85c77d44d1baa8a","sha256:1e0170e974afeb69e25efdb32fb34e6c0b36eede574bce14acb46d96ffaac751"],"state_sha256":"38a29877ef9f3a4ec8235ccea506b47fb0432428a84bb8b196b8dbeadb7e4a34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vlWPbjquL+WX/ojr5Bt20PAH61BH0enRr6aGLSVpf5ZfC6woeGSkSyKmJ5u0/1dZaMT1E4rjz4+lSu8BYWJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:49:38.466351Z","bundle_sha256":"1c609acc3858200b9d85ba67a72bac2acf4a1615e086b5835a1862eccd18ba6a"}}