{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CL7REY4RMEJGFKWTE3FCTRSIK","short_pith_number":"pith:6CL7REY4","schema_version":"1.0","canonical_sha256":"f097f8931c8b089315569936514e3242b7c583606038236f6ae0b17ae4b5dc32","source":{"kind":"arxiv","id":"2406.00704","version":2},"attestation_state":"computed","paper":{"title":"An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Halvor S. Sm{\\o}rvik, Ole-Christoffer Granmo, Ylva Gr{\\o}nnings{\\ae}ter","submitted_at":"2024-06-02T10:52:48Z","abstract_excerpt":"The Tsetlin Machine (TM) has achieved competitive results on several image classification benchmarks, including MNIST, K-MNIST, F-MNIST, and CIFAR-2. However, color image classification is arguably still in its infancy for TMs, with CIFAR-10 being a focal point for tracking progress. Over the past few years, TM's CIFAR-10 accuracy has increased from around 61% in 2020 to 75.1% in 2023 with the introduction of Drop Clause. In this paper, we leverage the recently proposed TM Composites architecture and introduce a range of TM Specialists that use various image processing techniques. These includ"},"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":"2406.00704","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-02T10:52:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"14c2d454399f3671c328ec4ba6944690f1f2fce05a5d407661050fc010717f46","abstract_canon_sha256":"3aacbdc6732dcd8fac8d5d854f0cbbe0a66555e5f93c5967e4225519f75e93ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:44.363310Z","signature_b64":"iv8k1hbKW81ypxbujVri2WHC0u0XjMzD7gINrSVIvR1WpcBtjHmwR3YN/N1e8XmTbgGr58MzURE96e2fwPeDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f097f8931c8b089315569936514e3242b7c583606038236f6ae0b17ae4b5dc32","last_reissued_at":"2026-07-05T10:09:44.362872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:44.362872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Halvor S. Sm{\\o}rvik, Ole-Christoffer Granmo, Ylva Gr{\\o}nnings{\\ae}ter","submitted_at":"2024-06-02T10:52:48Z","abstract_excerpt":"The Tsetlin Machine (TM) has achieved competitive results on several image classification benchmarks, including MNIST, K-MNIST, F-MNIST, and CIFAR-2. However, color image classification is arguably still in its infancy for TMs, with CIFAR-10 being a focal point for tracking progress. Over the past few years, TM's CIFAR-10 accuracy has increased from around 61% in 2020 to 75.1% in 2023 with the introduction of Drop Clause. In this paper, we leverage the recently proposed TM Composites architecture and introduce a range of TM Specialists that use various image processing techniques. These includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00704","kind":"arxiv","version":2},"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/2406.00704/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":"2406.00704","created_at":"2026-07-05T10:09:44.362929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00704v2","created_at":"2026-07-05T10:09:44.362929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00704","created_at":"2026-07-05T10:09:44.362929+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CL7REY4RMEJ","created_at":"2026-07-05T10:09:44.362929+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CL7REY4RMEJGFKW","created_at":"2026-07-05T10:09:44.362929+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CL7REY4","created_at":"2026-07-05T10:09:44.362929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16386","citing_title":"Omni TM-AE: A Scalable and Interpretable Embedding Model Using the Full Tsetlin Machine State Space","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK","json":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK.json","graph_json":"https://pith.science/api/pith-number/6CL7REY4RMEJGFKWTE3FCTRSIK/graph.json","events_json":"https://pith.science/api/pith-number/6CL7REY4RMEJGFKWTE3FCTRSIK/events.json","paper":"https://pith.science/paper/6CL7REY4"},"agent_actions":{"view_html":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK","download_json":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK.json","view_paper":"https://pith.science/paper/6CL7REY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00704&json=true","fetch_graph":"https://pith.science/api/pith-number/6CL7REY4RMEJGFKWTE3FCTRSIK/graph.json","fetch_events":"https://pith.science/api/pith-number/6CL7REY4RMEJGFKWTE3FCTRSIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK/action/storage_attestation","attest_author":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK/action/author_attestation","sign_citation":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK/action/citation_signature","submit_replication":"https://pith.science/pith/6CL7REY4RMEJGFKWTE3FCTRSIK/action/replication_record"}},"created_at":"2026-07-05T10:09:44.362929+00:00","updated_at":"2026-07-05T10:09:44.362929+00:00"}