{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JJFHEDZ67ZT4BU37PDTXTAW3GL","short_pith_number":"pith:JJFHEDZ6","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"},"canonical_sha256":"4a4a720f3efe67c0d37f78e77982db32ddd2821fbe9f67a2e0df75dcec71f8db","source":{"kind":"arxiv","id":"2605.08171","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08171","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08171v2","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08171","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"JJFHEDZ67ZT4","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"JJFHEDZ67ZT4BU37","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"JJFHEDZ6","created_at":"2026-06-10T00:08:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JJFHEDZ67ZT4BU37PDTXTAW3GL","target":"record","payload":{"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"},"canonical_sha256":"4a4a720f3efe67c0d37f78e77982db32ddd2821fbe9f67a2e0df75dcec71f8db","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"},"source_kind":"arxiv","source_id":"2605.08171","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T00:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0uft+ODMmZqgTpfF89/q7sSJlPVrEz9uF/mnhZSuoCdVZL+dgKddv5Rl+b7U9NGeVPCwaVeqmSssf0xzlq1oDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T20:47:47.730155Z"},"content_sha256":"2dee1e5421f3cf7bdec8e6fa700a99bf159882d28b710d22e97a3551df7b382c","schema_version":"1.0","event_id":"sha256:2dee1e5421f3cf7bdec8e6fa700a99bf159882d28b710d22e97a3551df7b382c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JJFHEDZ67ZT4BU37PDTXTAW3GL","target":"graph","payload":{"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"},"verdict_id":"8d6dafeb-35ab-455a-babc-bcf2481d61ad"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T00:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pe7Bkxo3r8Bk7JDL3lPyIq9AoEs8QnHF8PsTvMuBvDoxn2yTY/2YVhifHVBLWxy6RpOmPaLJ+aw0malQKAieAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T20:47:47.730648Z"},"content_sha256":"ec8e6a7fb321d6c7dcaa151378a8cfe09c2024ba0544132ceb1cfc72a57a08f6","schema_version":"1.0","event_id":"sha256:ec8e6a7fb321d6c7dcaa151378a8cfe09c2024ba0544132ceb1cfc72a57a08f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/bundle.json","state_url":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T20:47:47Z","links":{"resolver":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL","bundle":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/bundle.json","state":"https://pith.science/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJFHEDZ67ZT4BU37PDTXTAW3GL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJFHEDZ67ZT4BU37PDTXTAW3GL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0ca56caa532581ed27cbfeb6b331f7eaec22a19a488124a6df3b303b62102080","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T23:43:09Z","title_canon_sha256":"25731c91f095d62d79e002cecd272829678ad7403dd582acbe889ea1eae1fc5c"},"schema_version":"1.0","source":{"id":"2605.08171","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08171","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08171v2","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08171","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"JJFHEDZ67ZT4","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"JJFHEDZ67ZT4BU37","created_at":"2026-06-10T00:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"JJFHEDZ6","created_at":"2026-06-10T00:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:ec8e6a7fb321d6c7dcaa151378a8cfe09c2024ba0544132ceb1cfc72a57a08f6","target":"graph","created_at":"2026-06-10T00:08:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"f48bf37ce82d213879d2d85f7076cd8a7ae478e601f66dfffbad7048c51ac426"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.08171/integrity.json","findings":[],"snapshot_sha256":"dfb2928701ec0810a0b468560b6ad56dbd2344904a922df402e1a6926cf2822e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lurong Pan","cross_cats":["cs.AI"],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T23:43:09Z","title":"Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08171","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T01:26:28.750361Z","id":"8d6dafeb-35ab-455a-babc-bcf2481d61ad","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"8d6dafeb-35ab-455a-babc-bcf2481d61ad"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2dee1e5421f3cf7bdec8e6fa700a99bf159882d28b710d22e97a3551df7b382c","target":"record","created_at":"2026-06-10T00:08:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0ca56caa532581ed27cbfeb6b331f7eaec22a19a488124a6df3b303b62102080","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T23:43:09Z","title_canon_sha256":"25731c91f095d62d79e002cecd272829678ad7403dd582acbe889ea1eae1fc5c"},"schema_version":"1.0","source":{"id":"2605.08171","kind":"arxiv","version":2}},"canonical_sha256":"4a4a720f3efe67c0d37f78e77982db32ddd2821fbe9f67a2e0df75dcec71f8db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a4a720f3efe67c0d37f78e77982db32ddd2821fbe9f67a2e0df75dcec71f8db","first_computed_at":"2026-06-10T00:08:26.733774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:26.733774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WqVhlkqFC7LSCWoeg3dF5o1ffBT44HL0wkF68TWRKoTGb2YNgCZSwmzlUdTCzld762aGI4NN7V7AjCr3ZRNiDQ==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:26.734846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08171","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dee1e5421f3cf7bdec8e6fa700a99bf159882d28b710d22e97a3551df7b382c","sha256:ec8e6a7fb321d6c7dcaa151378a8cfe09c2024ba0544132ceb1cfc72a57a08f6"],"state_sha256":"e4258b55189eef34a3628fca5b0a353690ffe839b3b478557cd949805ade6e7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRgHZYf8ZZUDX7B0jyYk5br9TlHiuPLVwpr5Skrig587Hb2orPFHB9dZtoShIGCBBCupCQpvHfyAuYbrtRL6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T20:47:47.732798Z","bundle_sha256":"2cafad9ccd60ebc6ffdad121c5fa918e053e4707a4d3f4363f29900f447c9115"}}