{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BCQJ5AZU5NJYK7B3ZQORJ5XMQE","short_pith_number":"pith:BCQJ5AZU","schema_version":"1.0","canonical_sha256":"08a09e8334eb53857c3bcc1d14f6ec812a5dd2edd44c6443b8f1b153c55ba0dd","source":{"kind":"arxiv","id":"2404.11624","version":1},"attestation_state":"computed","paper":{"title":"Token Space: A Category Theory Framework for AI Computations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.GM","authors_text":"Wuming Pan","submitted_at":"2024-04-11T15:56:06Z","abstract_excerpt":"This paper introduces the Token Space framework, a novel mathematical construct designed to enhance the interpretability and effectiveness of deep learning models through the application of category theory. By establishing a categorical structure at the Token level, we provide a new lens through which AI computations can be understood, emphasizing the relationships between tokens, such as grouping, order, and parameter types. We explore the foundational methodologies of the Token Space, detailing its construction, the role of construction operators and initial categories, and its application i"},"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":"2404.11624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.GM","submitted_at":"2024-04-11T15:56:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b4a8543c3aaf9d415eea59f6760517f65b63e9802e03a1ab53201a96af34846","abstract_canon_sha256":"336e565c9773166154fdc1c086cfad1a40ee3a3ae6f78c0ad9346cbd288e9f4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:13.708026Z","signature_b64":"wgH4hLJkeAyYtiBwz7mOkMyX0I3u7H4uau7v2um2fWNEKopAVL8WW9bvHj5F9syQcLCATVwl3y9fiKRnoAJWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08a09e8334eb53857c3bcc1d14f6ec812a5dd2edd44c6443b8f1b153c55ba0dd","last_reissued_at":"2026-07-05T08:09:13.707626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:13.707626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Token Space: A Category Theory Framework for AI Computations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.GM","authors_text":"Wuming Pan","submitted_at":"2024-04-11T15:56:06Z","abstract_excerpt":"This paper introduces the Token Space framework, a novel mathematical construct designed to enhance the interpretability and effectiveness of deep learning models through the application of category theory. By establishing a categorical structure at the Token level, we provide a new lens through which AI computations can be understood, emphasizing the relationships between tokens, such as grouping, order, and parameter types. We explore the foundational methodologies of the Token Space, detailing its construction, the role of construction operators and initial categories, and its application i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11624","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/2404.11624/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":"2404.11624","created_at":"2026-07-05T08:09:13.707682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11624v1","created_at":"2026-07-05T08:09:13.707682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11624","created_at":"2026-07-05T08:09:13.707682+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCQJ5AZU5NJY","created_at":"2026-07-05T08:09:13.707682+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCQJ5AZU5NJYK7B3","created_at":"2026-07-05T08:09:13.707682+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCQJ5AZU","created_at":"2026-07-05T08:09:13.707682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17500","citing_title":"The Discovery Engine: A Framework for AI-Driven Synthesis and Navigation of Scientific Knowledge Landscapes","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE","json":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE.json","graph_json":"https://pith.science/api/pith-number/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/graph.json","events_json":"https://pith.science/api/pith-number/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/events.json","paper":"https://pith.science/paper/BCQJ5AZU"},"agent_actions":{"view_html":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE","download_json":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE.json","view_paper":"https://pith.science/paper/BCQJ5AZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11624&json=true","fetch_graph":"https://pith.science/api/pith-number/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/graph.json","fetch_events":"https://pith.science/api/pith-number/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/action/storage_attestation","attest_author":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/action/author_attestation","sign_citation":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/action/citation_signature","submit_replication":"https://pith.science/pith/BCQJ5AZU5NJYK7B3ZQORJ5XMQE/action/replication_record"}},"created_at":"2026-07-05T08:09:13.707682+00:00","updated_at":"2026-07-05T08:09:13.707682+00:00"}