{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJFHEDZ67ZT4BU37PDTXTAW3GL","short_pith_number":"pith:JJFHEDZ6","schema_version":"1.0","canonical_sha256":"4a4a720f3efe67c0d37f78e77982db32ddd2821fbe9f67a2e0df75dcec71f8db","source":{"kind":"arxiv","id":"2605.08171","version":2},"attestation_state":"computed","paper":{"title":"Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Block-circulant layers with FFT diagonalization make the population Hessian exactly the identity under pre-whitening while using one-Bth the parameters of a dense layer.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lurong Pan","submitted_at":"2026-05-04T23:43:09Z","abstract_excerpt":"Communication Dynamics Neural Networks (CDNNs) apply the circulant-spectral machinery of the Communication Dynamics framework to neural-network layer design. We introduce CDLinear, a block-circulant linear layer with block size B = 2l + 1 that uses 1/B the parameters of a dense layer with the same input and output dimensions. The construction gives an explicit Fourier-domain diagnostic for optimization: for mean-squared loss, the weight Hessian is diagonalized by the discrete Fourier transform, with eigenvalues determined directly by the Fourier spectrum of the input blocks. Under input pre-wh"},"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":"2605.08171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T23:43:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25731c91f095d62d79e002cecd272829678ad7403dd582acbe889ea1eae1fc5c","abstract_canon_sha256":"0ca56caa532581ed27cbfeb6b331f7eaec22a19a488124a6df3b303b62102080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:26.734846Z","signature_b64":"WqVhlkqFC7LSCWoeg3dF5o1ffBT44HL0wkF68TWRKoTGb2YNgCZSwmzlUdTCzld762aGI4NN7V7AjCr3ZRNiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a4a720f3efe67c0d37f78e77982db32ddd2821fbe9f67a2e0df75dcec71f8db","last_reissued_at":"2026-06-10T00:08:26.733774Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:26.733774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Block-circulant layers with FFT diagonalization make the population Hessian exactly the identity under pre-whitening while using one-Bth the parameters of a dense layer.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lurong Pan","submitted_at":"2026-05-04T23:43:09Z","abstract_excerpt":"Communication Dynamics Neural Networks (CDNNs) apply the circulant-spectral machinery of the Communication Dynamics framework to neural-network layer design. We introduce CDLinear, a block-circulant linear layer with block size B = 2l + 1 that uses 1/B the parameters of a dense layer with the same input and output dimensions. The construction gives an explicit Fourier-domain diagnostic for optimization: for mean-squared loss, the weight Hessian is diagonalized by the discrete Fourier transform, with eigenvalues determined directly by the Fourier spectrum of the input blocks. Under input pre-wh"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under input pre-whitening, the population Hessian condition number satisfies kappa = 1 exactly, with the empirical condition number bounded by 1+O(sqrt(B/N)) on N samples (Theorem 2). A CDLinear MLP at B = 4 achieves 97.50% +/- 0.23% test accuracy with 2,380 parameters versus 98.15% +/- 0.47% for a parameter-matched dense MLP at 8,970 parameters.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the block-circulant restriction with block size B = 2l+1 preserves sufficient expressivity for the target task and that input pre-whitening can be performed without destroying the data distribution or introducing new instabilities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CDLinear layers achieve population Hessian condition number exactly 1 under pre-whitening, deliver 3.8x parameter reduction versus dense layers at 0.65% accuracy cost, and show 310x better empirical conditioning on an MLP.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Block-circulant layers with FFT diagonalization make the population Hessian exactly the identity under pre-whitening while using one-Bth the parameters of a dense layer.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f48bf37ce82d213879d2d85f7076cd8a7ae478e601f66dfffbad7048c51ac426"},"source":{"id":"2605.08171","kind":"arxiv","version":2},"verdict":{"id":"8d6dafeb-35ab-455a-babc-bcf2481d61ad","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:26:28.750361Z","strongest_claim":"Under input pre-whitening, the population Hessian condition number satisfies kappa = 1 exactly, with the empirical condition number bounded by 1+O(sqrt(B/N)) on N samples (Theorem 2). A CDLinear MLP at B = 4 achieves 97.50% +/- 0.23% test accuracy with 2,380 parameters versus 98.15% +/- 0.47% for a parameter-matched dense MLP at 8,970 parameters.","one_line_summary":"CDLinear layers achieve population Hessian condition number exactly 1 under pre-whitening, deliver 3.8x parameter reduction versus dense layers at 0.65% accuracy cost, and show 310x better empirical conditioning on an MLP.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the block-circulant restriction with block size B = 2l+1 preserves sufficient expressivity for the target task and that input pre-whitening can be performed without destroying the data distribution or introducing new instabilities.","pith_extraction_headline":"Block-circulant layers with FFT diagonalization make the population Hessian exactly the identity under pre-whitening while using one-Bth the parameters of a dense layer."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08171/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T14:35:20.618513Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T01:31:21.799294Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:34:04.388591Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"dfb2928701ec0810a0b468560b6ad56dbd2344904a922df402e1a6926cf2822e"},"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":"2605.08171","created_at":"2026-06-10T00:08:26.733916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08171v2","created_at":"2026-06-10T00:08:26.733916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08171","created_at":"2026-06-10T00:08:26.733916+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJFHEDZ67ZT4","created_at":"2026-06-10T00:08:26.733916+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJFHEDZ67ZT4BU37","created_at":"2026-06-10T00:08:26.733916+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJFHEDZ6","created_at":"2026-06-10T00:08:26.733916+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/JJFHEDZ67ZT4BU37PDTXTAW3GL","json":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL.json","graph_json":"https://pith.science/api/pith-number/JJFHEDZ67ZT4BU37PDTXTAW3GL/graph.json","events_json":"https://pith.science/api/pith-number/JJFHEDZ67ZT4BU37PDTXTAW3GL/events.json","paper":"https://pith.science/paper/JJFHEDZ6"},"agent_actions":{"view_html":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL","download_json":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL.json","view_paper":"https://pith.science/paper/JJFHEDZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08171&json=true","fetch_graph":"https://pith.science/api/pith-number/JJFHEDZ67ZT4BU37PDTXTAW3GL/graph.json","fetch_events":"https://pith.science/api/pith-number/JJFHEDZ67ZT4BU37PDTXTAW3GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/action/storage_attestation","attest_author":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/action/author_attestation","sign_citation":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/action/citation_signature","submit_replication":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/action/replication_record"}},"created_at":"2026-06-10T00:08:26.733916+00:00","updated_at":"2026-06-10T00:08:26.733916+00:00"}