{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZBTZDYGOBANACRL4QKQJN4WFL6","short_pith_number":"pith:ZBTZDYGO","schema_version":"1.0","canonical_sha256":"c86791e0ce081a01457c82a096f2c55f9aeac77f2b1d61d219eb976914a2f213","source":{"kind":"arxiv","id":"1909.00668","version":1},"attestation_state":"computed","paper":{"title":"Logic and the $2$-Simplicial Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Murfet, Dmitry Doryn, James Clift, James Wallbridge","submitted_at":"2019-09-02T11:11:35Z","abstract_excerpt":"We introduce the $2$-simplicial Transformer, an extension of the Transformer which includes a form of higher-dimensional attention generalising the dot-product attention, and uses this attention to update entity representations with tensor products of value vectors. We show that this architecture is a useful inductive bias for logical reasoning in the context of deep reinforcement learning."},"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":"1909.00668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-02T11:11:35Z","cross_cats_sorted":["cs.LO","stat.ML"],"title_canon_sha256":"202937fbf663530f28a2ff2aefd7b4563ef27c7246a3581daa276f6b2b4610de","abstract_canon_sha256":"58aa0d21fadc5443fb3b47ab23adda0c4d29d11bc958aa197478735df043b255"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:19.442092Z","signature_b64":"lu2uHJiy41zDGN/GhFw6QIB2HyL4DMmGml9PXZ+oecZXXQ0mUIvCjlqOe5S6a0wdjBR5Wi8Gr4ueMks8wXcXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c86791e0ce081a01457c82a096f2c55f9aeac77f2b1d61d219eb976914a2f213","last_reissued_at":"2026-07-05T00:04:19.441620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:19.441620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logic and the $2$-Simplicial Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Murfet, Dmitry Doryn, James Clift, James Wallbridge","submitted_at":"2019-09-02T11:11:35Z","abstract_excerpt":"We introduce the $2$-simplicial Transformer, an extension of the Transformer which includes a form of higher-dimensional attention generalising the dot-product attention, and uses this attention to update entity representations with tensor products of value vectors. We show that this architecture is a useful inductive bias for logical reasoning in the context of deep reinforcement learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00668","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/1909.00668/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":"1909.00668","created_at":"2026-07-05T00:04:19.441677+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00668v1","created_at":"2026-07-05T00:04:19.441677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00668","created_at":"2026-07-05T00:04:19.441677+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBTZDYGOBANA","created_at":"2026-07-05T00:04:19.441677+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBTZDYGOBANACRL4","created_at":"2026-07-05T00:04:19.441677+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBTZDYGO","created_at":"2026-07-05T00:04:19.441677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28122","citing_title":"Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10905","citing_title":"TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10905","citing_title":"TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6","json":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6.json","graph_json":"https://pith.science/api/pith-number/ZBTZDYGOBANACRL4QKQJN4WFL6/graph.json","events_json":"https://pith.science/api/pith-number/ZBTZDYGOBANACRL4QKQJN4WFL6/events.json","paper":"https://pith.science/paper/ZBTZDYGO"},"agent_actions":{"view_html":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6","download_json":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6.json","view_paper":"https://pith.science/paper/ZBTZDYGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00668&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBTZDYGOBANACRL4QKQJN4WFL6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBTZDYGOBANACRL4QKQJN4WFL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6/action/storage_attestation","attest_author":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6/action/author_attestation","sign_citation":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6/action/citation_signature","submit_replication":"https://pith.science/pith/ZBTZDYGOBANACRL4QKQJN4WFL6/action/replication_record"}},"created_at":"2026-07-05T00:04:19.441677+00:00","updated_at":"2026-07-05T00:04:19.441677+00:00"}