{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OPFLAVIRAPXVGW62F7UHV6BLU6","short_pith_number":"pith:OPFLAVIR","canonical_record":{"source":{"id":"2606.27748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T06:08:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef4773eb7c31b7602fe1b56bb8e05bab5fefcec6cfdbfcf9bf144aafd4e26bc4","abstract_canon_sha256":"419c1375f35a00d5d089c87c6a2218606a9a21d6c124ff145757bd2cbd98b892"},"schema_version":"1.0"},"canonical_sha256":"73cab0551103ef535bda2fe87af82ba79baa82be3bb09927275abf5507d589db","source":{"kind":"arxiv","id":"2606.27748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27748","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27748v1","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27748","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"OPFLAVIRAPXV","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"OPFLAVIRAPXVGW62","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"OPFLAVIR","created_at":"2026-06-29T01:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OPFLAVIRAPXVGW62F7UHV6BLU6","target":"record","payload":{"canonical_record":{"source":{"id":"2606.27748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T06:08:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef4773eb7c31b7602fe1b56bb8e05bab5fefcec6cfdbfcf9bf144aafd4e26bc4","abstract_canon_sha256":"419c1375f35a00d5d089c87c6a2218606a9a21d6c124ff145757bd2cbd98b892"},"schema_version":"1.0"},"canonical_sha256":"73cab0551103ef535bda2fe87af82ba79baa82be3bb09927275abf5507d589db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:47.360549Z","signature_b64":"a3MYzw+L0jiBnrO6V6urv1XbjrBvgFMlL8oBGOBOjoMgD9VThEJCRXtcXfeDe9EA0xa8G5c4M1YiIOMyJtlBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73cab0551103ef535bda2fe87af82ba79baa82be3bb09927275abf5507d589db","last_reissued_at":"2026-06-29T01:14:47.360200Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:47.360200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.27748","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":"2026-06-29T01:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APph3xT5jWoaOf0UZ2xaYbMV90N7EuYgTQUcV2L+EeQ0e99HDQOsy6uZS7ylwmTiZRnF/0yNr+eYVyD2YzVBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:11:01.313696Z"},"content_sha256":"94fd0f130aaec19c92f63c445af5df36136ab4627369fa0870f6b2ccddb2ab22","schema_version":"1.0","event_id":"sha256:94fd0f130aaec19c92f63c445af5df36136ab4627369fa0870f6b2ccddb2ab22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OPFLAVIRAPXVGW62F7UHV6BLU6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flexformer: Flexible Linear Transformer with Learnable Attention Kernel","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Feng Zhou, Haoran Zhang","submitted_at":"2026-06-26T06:08:44Z","abstract_excerpt":"Transformer models rely on attention mechanism to capture long-range dependencies but suffer from quadratic complexity, limiting their scalability to long sequences. Kernel-based linear attention reduces this complexity but typically relies on fixed or weakly learnable kernels, restricting expressiveness and performance. In this work, we propose Flexformer, a flexible linear Transformer that learns attention kernels in a fully data-driven manner. Flexformer builds on random Fourier feature-based linear attention and treats spectral frequencies as trainable parameters, enabling the model to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27748","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/2606.27748/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":"2026-06-29T01:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6Xe+OxwxliNM3YvUh7g5zwZZX06e399B+b0TsUfgFP41b/P/X7MaJLkqoed2wsFXC2zj2sen+Mf5sbf8qi9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:11:01.314004Z"},"content_sha256":"37ed623caa72e2ae5b6f354d2b30d17a3ebafb34371c87481c0f64e37f83b93b","schema_version":"1.0","event_id":"sha256:37ed623caa72e2ae5b6f354d2b30d17a3ebafb34371c87481c0f64e37f83b93b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPFLAVIRAPXVGW62F7UHV6BLU6/bundle.json","state_url":"https://pith.science/pith/OPFLAVIRAPXVGW62F7UHV6BLU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPFLAVIRAPXVGW62F7UHV6BLU6/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":"2026-08-05T11:11:01Z","links":{"resolver":"https://pith.science/pith/OPFLAVIRAPXVGW62F7UHV6BLU6","bundle":"https://pith.science/pith/OPFLAVIRAPXVGW62F7UHV6BLU6/bundle.json","state":"https://pith.science/pith/OPFLAVIRAPXVGW62F7UHV6BLU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPFLAVIRAPXVGW62F7UHV6BLU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OPFLAVIRAPXVGW62F7UHV6BLU6","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":"419c1375f35a00d5d089c87c6a2218606a9a21d6c124ff145757bd2cbd98b892","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T06:08:44Z","title_canon_sha256":"ef4773eb7c31b7602fe1b56bb8e05bab5fefcec6cfdbfcf9bf144aafd4e26bc4"},"schema_version":"1.0","source":{"id":"2606.27748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27748","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27748v1","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27748","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"OPFLAVIRAPXV","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"OPFLAVIRAPXVGW62","created_at":"2026-06-29T01:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"OPFLAVIR","created_at":"2026-06-29T01:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:37ed623caa72e2ae5b6f354d2b30d17a3ebafb34371c87481c0f64e37f83b93b","target":"graph","created_at":"2026-06-29T01:14:47Z","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/2606.27748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models rely on attention mechanism to capture long-range dependencies but suffer from quadratic complexity, limiting their scalability to long sequences. Kernel-based linear attention reduces this complexity but typically relies on fixed or weakly learnable kernels, restricting expressiveness and performance. In this work, we propose Flexformer, a flexible linear Transformer that learns attention kernels in a fully data-driven manner. Flexformer builds on random Fourier feature-based linear attention and treats spectral frequencies as trainable parameters, enabling the model to lea","authors_text":"Feng Zhou, Haoran Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T06:08:44Z","title":"Flexformer: Flexible Linear Transformer with Learnable Attention Kernel"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27748","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":"sha256:94fd0f130aaec19c92f63c445af5df36136ab4627369fa0870f6b2ccddb2ab22","target":"record","created_at":"2026-06-29T01:14:47Z","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":"419c1375f35a00d5d089c87c6a2218606a9a21d6c124ff145757bd2cbd98b892","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T06:08:44Z","title_canon_sha256":"ef4773eb7c31b7602fe1b56bb8e05bab5fefcec6cfdbfcf9bf144aafd4e26bc4"},"schema_version":"1.0","source":{"id":"2606.27748","kind":"arxiv","version":1}},"canonical_sha256":"73cab0551103ef535bda2fe87af82ba79baa82be3bb09927275abf5507d589db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73cab0551103ef535bda2fe87af82ba79baa82be3bb09927275abf5507d589db","first_computed_at":"2026-06-29T01:14:47.360200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:47.360200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a3MYzw+L0jiBnrO6V6urv1XbjrBvgFMlL8oBGOBOjoMgD9VThEJCRXtcXfeDe9EA0xa8G5c4M1YiIOMyJtlBBQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:47.360549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94fd0f130aaec19c92f63c445af5df36136ab4627369fa0870f6b2ccddb2ab22","sha256:37ed623caa72e2ae5b6f354d2b30d17a3ebafb34371c87481c0f64e37f83b93b"],"state_sha256":"9223583cb8855bcbe3718f803bfa39e46a234876428e5e0cb320f6613afe38c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qK0V5rAKT0s+J/QeQJ1DM9ENNPbV3T8quSK3avWXr9M7XGuqh3M8eNvXTx4yqHe6d+jT7pgV3ory3x5UMVXQBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:11:01.317207Z","bundle_sha256":"d60ee9f1a45540236b5491115db7d8ca4dc87bac639dd8c551435faac46677af"}}