{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQVIRIK33QXSX34LIGUSIKHOPE","short_pith_number":"pith:VQVIRIK3","schema_version":"1.0","canonical_sha256":"ac2a88a15bdc2f2bef8b41a92428ee7915da15ae8a5f1b15f64237bef15a3519","source":{"kind":"arxiv","id":"2605.31367","version":1},"attestation_state":"computed","paper":{"title":"Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexandre Allauzen, Blaise Delattre, Erwan Fagnou, Paul Caillon","submitted_at":"2026-05-29T14:38:50Z","abstract_excerpt":"Token mixing layers play a key role in how language models can learn and generate long-range dependencies. Their efficiency relies on the necessary trade-off between decoding speed and the memory requirements, along with the cache size. Considering causal generation, this paper explores new trade-offs thanks to a unified framework which separates two crucial features: (i) the direct influence of inputs on outputs in one generation step; (ii) the recurrent propagation of information through past outputs. This framework encompasses major architectures such as attention and state-space models, bu"},"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":"2605.31367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T14:38:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ba78be0d7b65d558859133e23ddf65c8adbc1b3bd4e70357505c4f231efdd53f","abstract_canon_sha256":"1d27f5eb2de55b3b90e544f3962b0b1db50918d80c281ffa9a1ed71e0b60b771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:01.273169Z","signature_b64":"63oG4Maz/4hf3nSVNYbC/BZhASY6DmULFh8DiMYhKN0OFm8x0wxZif1XFnoVxp90k9E+mNlQGVN29yOYIeizAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2a88a15bdc2f2bef8b41a92428ee7915da15ae8a5f1b15f64237bef15a3519","last_reissued_at":"2026-06-01T02:04:01.272415Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:01.272415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexandre Allauzen, Blaise Delattre, Erwan Fagnou, Paul Caillon","submitted_at":"2026-05-29T14:38:50Z","abstract_excerpt":"Token mixing layers play a key role in how language models can learn and generate long-range dependencies. Their efficiency relies on the necessary trade-off between decoding speed and the memory requirements, along with the cache size. Considering causal generation, this paper explores new trade-offs thanks to a unified framework which separates two crucial features: (i) the direct influence of inputs on outputs in one generation step; (ii) the recurrent propagation of information through past outputs. This framework encompasses major architectures such as attention and state-space models, bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31367","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/2605.31367/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":"2605.31367","created_at":"2026-06-01T02:04:01.272518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31367v1","created_at":"2026-06-01T02:04:01.272518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31367","created_at":"2026-06-01T02:04:01.272518+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQVIRIK33QXS","created_at":"2026-06-01T02:04:01.272518+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQVIRIK33QXSX34L","created_at":"2026-06-01T02:04:01.272518+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQVIRIK3","created_at":"2026-06-01T02:04:01.272518+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/VQVIRIK33QXSX34LIGUSIKHOPE","json":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE.json","graph_json":"https://pith.science/api/pith-number/VQVIRIK33QXSX34LIGUSIKHOPE/graph.json","events_json":"https://pith.science/api/pith-number/VQVIRIK33QXSX34LIGUSIKHOPE/events.json","paper":"https://pith.science/paper/VQVIRIK3"},"agent_actions":{"view_html":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE","download_json":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE.json","view_paper":"https://pith.science/paper/VQVIRIK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31367&json=true","fetch_graph":"https://pith.science/api/pith-number/VQVIRIK33QXSX34LIGUSIKHOPE/graph.json","fetch_events":"https://pith.science/api/pith-number/VQVIRIK33QXSX34LIGUSIKHOPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE/action/storage_attestation","attest_author":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE/action/author_attestation","sign_citation":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE/action/citation_signature","submit_replication":"https://pith.science/pith/VQVIRIK33QXSX34LIGUSIKHOPE/action/replication_record"}},"created_at":"2026-06-01T02:04:01.272518+00:00","updated_at":"2026-06-01T02:04:01.272518+00:00"}