{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JDFWXM5BJLFFNLFN5SQJT5LAOQ","short_pith_number":"pith:JDFWXM5B","schema_version":"1.0","canonical_sha256":"48cb6bb3a14aca56acadeca099f56074044e52752a0334090bf192463009ac89","source":{"kind":"arxiv","id":"2606.31856","version":1},"attestation_state":"computed","paper":{"title":"Low-dimensional topology of deep neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.GT"],"primary_cat":"cs.LG","authors_text":"Junyu Ren, Lek-Heng Lim","submitted_at":"2026-06-30T15:53:11Z","abstract_excerpt":"We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.e., $\\mathbb{R}^3$ as representation space. This allows us to track how a neural network changes low-dimensional topological invariants through its layers. Just about any topological structure may be simplified or even trivialized by simply increasing dimension; e.g., any knot is equivalent to an unknot in $\\mathbb{R}^4$. By restricting to $\\mathbb{R}^3$, we not only isolate the effects of activation and depth from that of width, we work in a space that lends itse"},"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":"2606.31856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T15:53:11Z","cross_cats_sorted":["math.GT"],"title_canon_sha256":"8fc4b03c05e6da40421c4a05bffc075d68f4594a94807c4cabb3c420a2673ef6","abstract_canon_sha256":"96b65983cd5ba5ee8b81d0d298305c41f110fbe9681e39ca12ee7991b8936752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:17.677921Z","signature_b64":"QImYKwZYLLuaDlYikkWn9BmA/YTLCX1QIZP5ddOxpmndauTKoGZS8Ar5pCvjAkKeg4wDliHOV8YN7eRsWN0fBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48cb6bb3a14aca56acadeca099f56074044e52752a0334090bf192463009ac89","last_reissued_at":"2026-07-01T01:18:17.677372Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:17.677372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-dimensional topology of deep neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.GT"],"primary_cat":"cs.LG","authors_text":"Junyu Ren, Lek-Heng Lim","submitted_at":"2026-06-30T15:53:11Z","abstract_excerpt":"We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.e., $\\mathbb{R}^3$ as representation space. This allows us to track how a neural network changes low-dimensional topological invariants through its layers. Just about any topological structure may be simplified or even trivialized by simply increasing dimension; e.g., any knot is equivalent to an unknot in $\\mathbb{R}^4$. By restricting to $\\mathbb{R}^3$, we not only isolate the effects of activation and depth from that of width, we work in a space that lends itse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31856","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/2606.31856/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":"2606.31856","created_at":"2026-07-01T01:18:17.677429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31856v1","created_at":"2026-07-01T01:18:17.677429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31856","created_at":"2026-07-01T01:18:17.677429+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDFWXM5BJLFF","created_at":"2026-07-01T01:18:17.677429+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDFWXM5BJLFFNLFN","created_at":"2026-07-01T01:18:17.677429+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDFWXM5B","created_at":"2026-07-01T01:18:17.677429+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/JDFWXM5BJLFFNLFN5SQJT5LAOQ","json":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ.json","graph_json":"https://pith.science/api/pith-number/JDFWXM5BJLFFNLFN5SQJT5LAOQ/graph.json","events_json":"https://pith.science/api/pith-number/JDFWXM5BJLFFNLFN5SQJT5LAOQ/events.json","paper":"https://pith.science/paper/JDFWXM5B"},"agent_actions":{"view_html":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ","download_json":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ.json","view_paper":"https://pith.science/paper/JDFWXM5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31856&json=true","fetch_graph":"https://pith.science/api/pith-number/JDFWXM5BJLFFNLFN5SQJT5LAOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JDFWXM5BJLFFNLFN5SQJT5LAOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ/action/storage_attestation","attest_author":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ/action/author_attestation","sign_citation":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ/action/citation_signature","submit_replication":"https://pith.science/pith/JDFWXM5BJLFFNLFN5SQJT5LAOQ/action/replication_record"}},"created_at":"2026-07-01T01:18:17.677429+00:00","updated_at":"2026-07-01T01:18:17.677429+00:00"}