{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MR63CYQZK7NA2JLW56UZHVFR7T","short_pith_number":"pith:MR63CYQZ","schema_version":"1.0","canonical_sha256":"647db1621957da0d2576efa993d4b1fce7d670b354de7596fcbf913858220eb9","source":{"kind":"arxiv","id":"2605.27259","version":1},"attestation_state":"computed","paper":{"title":"Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sridhar Mahadevan","submitted_at":"2026-05-26T16:36:59Z","abstract_excerpt":"We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: standard attention is the singleton-neighborhood case, Geometric Transformer style incidence mixing is a sparse edge-restricted case, and KET is the higher-order simplicial case. This lens also clarifies a bridge to diffusion-style completion. When the extension operator acts on detached predictive carriers instead of teacher-forced hidden states, it becomes a va"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.27259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T16:36:59Z","cross_cats_sorted":[],"title_canon_sha256":"b6055aa8c7ae1373da8843861a77040bffe7e07724db541f6d56bb15296ed28c","abstract_canon_sha256":"edf1c2fb22612249c668780f296884899752a354eb832e5a01c2f63ec75356d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:08.781273Z","signature_b64":"IsVwV2ofhjPbBRWgqzPZQy+zZytA8eX/MpyNs4G9PvcPswP8NHGAHYZJNANeg3RdBmGjzKTb852fijJRppMlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"647db1621957da0d2576efa993d4b1fce7d670b354de7596fcbf913858220eb9","last_reissued_at":"2026-05-27T02:06:08.780769Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:08.780769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sridhar Mahadevan","submitted_at":"2026-05-26T16:36:59Z","abstract_excerpt":"We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: standard attention is the singleton-neighborhood case, Geometric Transformer style incidence mixing is a sparse edge-restricted case, and KET is the higher-order simplicial case. This lens also clarifies a bridge to diffusion-style completion. When the extension operator acts on detached predictive carriers instead of teacher-forced hidden states, it becomes a va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27259","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/2605.27259/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27259","created_at":"2026-05-27T02:06:08.780840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27259v1","created_at":"2026-05-27T02:06:08.780840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27259","created_at":"2026-05-27T02:06:08.780840+00:00"},{"alias_kind":"pith_short_12","alias_value":"MR63CYQZK7NA","created_at":"2026-05-27T02:06:08.780840+00:00"},{"alias_kind":"pith_short_16","alias_value":"MR63CYQZK7NA2JLW","created_at":"2026-05-27T02:06:08.780840+00:00"},{"alias_kind":"pith_short_8","alias_value":"MR63CYQZ","created_at":"2026-05-27T02:06:08.780840+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/MR63CYQZK7NA2JLW56UZHVFR7T","json":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T.json","graph_json":"https://pith.science/api/pith-number/MR63CYQZK7NA2JLW56UZHVFR7T/graph.json","events_json":"https://pith.science/api/pith-number/MR63CYQZK7NA2JLW56UZHVFR7T/events.json","paper":"https://pith.science/paper/MR63CYQZ"},"agent_actions":{"view_html":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T","download_json":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T.json","view_paper":"https://pith.science/paper/MR63CYQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27259&json=true","fetch_graph":"https://pith.science/api/pith-number/MR63CYQZK7NA2JLW56UZHVFR7T/graph.json","fetch_events":"https://pith.science/api/pith-number/MR63CYQZK7NA2JLW56UZHVFR7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T/action/storage_attestation","attest_author":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T/action/author_attestation","sign_citation":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T/action/citation_signature","submit_replication":"https://pith.science/pith/MR63CYQZK7NA2JLW56UZHVFR7T/action/replication_record"}},"created_at":"2026-05-27T02:06:08.780840+00:00","updated_at":"2026-05-27T02:06:08.780840+00:00"}