{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LSD2X252L6WV7DRWNYTHOEX7MI","short_pith_number":"pith:LSD2X252","canonical_record":{"source":{"id":"2605.14489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T07:28:11Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"f1933359cc85b0c19940d8c7acd55e832d6db5c697b49aadfc9f7facd260cb3d","abstract_canon_sha256":"9f10647708b472ee71a1581797cf4cfa9952d32476484265695c471b65feffd2"},"schema_version":"1.0"},"canonical_sha256":"5c87abebba5fad5f8e366e267712ff6231d6cb267eae2e193d6b4792dd0a0e82","source":{"kind":"arxiv","id":"2605.14489","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14489","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14489v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14489","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"LSD2X252L6WV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LSD2X252L6WV7DRW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LSD2X252","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LSD2X252L6WV7DRWNYTHOEX7MI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T07:28:11Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"f1933359cc85b0c19940d8c7acd55e832d6db5c697b49aadfc9f7facd260cb3d","abstract_canon_sha256":"9f10647708b472ee71a1581797cf4cfa9952d32476484265695c471b65feffd2"},"schema_version":"1.0"},"canonical_sha256":"5c87abebba5fad5f8e366e267712ff6231d6cb267eae2e193d6b4792dd0a0e82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.453618Z","signature_b64":"tpXLVgsz0Q6iE3mBACyGChsCwYJv1RwGkUCsVa2j4gUxPAN/676r8ip9pG/gEDnSYmCv7Z4zgsE7efTrVnZZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c87abebba5fad5f8e366e267712ff6231d6cb267eae2e193d6b4792dd0a0e82","last_reissued_at":"2026-05-17T23:39:06.452878Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.452878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14489","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oPT50uiYd2m7DHmrMBB5o+t9f0KGhrWfmv4qbaIdXTarbTWBOLZ/KnQwQgq2UXfjMYuAAAvoJWmkMzVaweDhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:26:16.673072Z"},"content_sha256":"54923afbb722dcbe33bc47e264bae11ee9dff0da5f6a77758fca1a71910333b3","schema_version":"1.0","event_id":"sha256:54923afbb722dcbe33bc47e264bae11ee9dff0da5f6a77758fca1a71910333b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LSD2X252L6WV7DRWNYTHOEX7MI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Novel Schur-Decomposition-Based Weight Projection Method for Stable State-Space Neural-Network Architectures","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Projecting the quasi-triangular factor from the real Schur decomposition of the state matrix onto its nearest stable peer keeps discrete-time state-space neural-network layers asymptotically stable during training.","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Fredy Ruiz, Lasse Lensu, Sergio Vanegas","submitted_at":"2026-05-14T07:28:11Z","abstract_excerpt":"Building black-box models for dynamical systems from data is a challenging problem in machine learning, especially when asymptotic stability guarantees are required. In this paper, we introduce a novel stability-ensuring and backpropagation-compatible projection scheme based on the Schur decomposition for the state matrix of linear discrete-time state-space layers, as well as an alternative pre-factorized formulation of the methodology. The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stab"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stable dynamics with minimal overparameterization.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That repeatedly projecting the state matrix during training does not materially distort the optimization landscape or introduce bias that prevents reaching accurate models on real-world data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A real Schur decomposition projection maps the state matrix of discrete-time state-space layers onto its nearest stable counterpart, delivering accuracy comparable to prior stable identification methods with fewer weights.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Projecting the quasi-triangular factor from the real Schur decomposition of the state matrix onto its nearest stable peer keeps discrete-time state-space neural-network layers asymptotically stable during training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"59c2ece815cb79e0214cc2bb919513e08f63d86964d413104663ef831d0ba165"},"source":{"id":"2605.14489","kind":"arxiv","version":1},"verdict":{"id":"0f7f7b73-610c-404f-bca2-71244bc725af","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:33:53.095596Z","strongest_claim":"The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stable dynamics with minimal overparameterization.","one_line_summary":"A real Schur decomposition projection maps the state matrix of discrete-time state-space layers onto its nearest stable counterpart, delivering accuracy comparable to prior stable identification methods with fewer weights.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That repeatedly projecting the state matrix during training does not materially distort the optimization landscape or introduce bias that prevents reaching accurate models on real-world data.","pith_extraction_headline":"Projecting the quasi-triangular factor from the real Schur decomposition of the state matrix onto its nearest stable peer keeps discrete-time state-space neural-network layers asymptotically stable during training."},"references":{"count":80,"sample":[{"doi":"","year":2002,"title":"Model reduction via balanced realizations: an extension and frequency weighting techniques.IEEE Transactions on Automatic Control, 33(7):687–692, 2002","work_id":"f1833826-61c3-4552-a1d6-e198a7ecbed6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Efficiently Modeling Long Sequences with Structured State Spaces","work_id":"4150b761-b8bf-4d9b-a2f8-cb2d1b73d378","ref_index":2,"cited_arxiv_id":"2111.00396","is_internal_anchor":true},{"doi":"","year":2022,"title":"Simplified State Space Layers for Sequence Modeling","work_id":"d4f90830-6ceb-4c9e-b206-eb32ac063f45","ref_index":3,"cited_arxiv_id":"2208.04933","is_internal_anchor":true},{"doi":"","year":2023,"title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","work_id":"4ee75248-1199-492c-a52f-6661e0f4adff","ref_index":4,"cited_arxiv_id":"2312.00752","is_internal_anchor":true},{"doi":"","year":2020,"title":"Hippo: Recurrent memory with optimal polynomial projections.Advances in neural information processing systems, 33:1474–1487, 2020","work_id":"0d6d46ae-5de3-4ecb-aa6f-923be89ee19a","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":80,"snapshot_sha256":"49a1d9a66f11aaebc5177e4a538166b3bff65c2342bf694ddfb513d92b874ade","internal_anchors":4},"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":"0f7f7b73-610c-404f-bca2-71244bc725af"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BHGSq6KqSDN/qt2klI84KEi2IOoqa1OoqJFWf0w9EDKnBhw5oOIJ0d/NunxTO9ioqjsdAVp02A90rNT27tHWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T08:26:16.674273Z"},"content_sha256":"31d647679736239a9b13814d394793dd67465e4e92e39a07ad3cad1a8346848b","schema_version":"1.0","event_id":"sha256:31d647679736239a9b13814d394793dd67465e4e92e39a07ad3cad1a8346848b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LSD2X252L6WV7DRWNYTHOEX7MI/bundle.json","state_url":"https://pith.science/pith/LSD2X252L6WV7DRWNYTHOEX7MI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LSD2X252L6WV7DRWNYTHOEX7MI/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":"2026-06-10T08:26:16Z","links":{"resolver":"https://pith.science/pith/LSD2X252L6WV7DRWNYTHOEX7MI","bundle":"https://pith.science/pith/LSD2X252L6WV7DRWNYTHOEX7MI/bundle.json","state":"https://pith.science/pith/LSD2X252L6WV7DRWNYTHOEX7MI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LSD2X252L6WV7DRWNYTHOEX7MI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LSD2X252L6WV7DRWNYTHOEX7MI","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":"9f10647708b472ee71a1581797cf4cfa9952d32476484265695c471b65feffd2","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T07:28:11Z","title_canon_sha256":"f1933359cc85b0c19940d8c7acd55e832d6db5c697b49aadfc9f7facd260cb3d"},"schema_version":"1.0","source":{"id":"2605.14489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14489","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14489v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14489","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"LSD2X252L6WV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LSD2X252L6WV7DRW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LSD2X252","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:31d647679736239a9b13814d394793dd67465e4e92e39a07ad3cad1a8346848b","target":"graph","created_at":"2026-05-17T23:39:06Z","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":"The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stable dynamics with minimal overparameterization."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That repeatedly projecting the state matrix during training does not materially distort the optimization landscape or introduce bias that prevents reaching accurate models on real-world data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A real Schur decomposition projection maps the state matrix of discrete-time state-space layers onto its nearest stable counterpart, delivering accuracy comparable to prior stable identification methods with fewer weights."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Projecting the quasi-triangular factor from the real Schur decomposition of the state matrix onto its nearest stable peer keeps discrete-time state-space neural-network layers asymptotically stable during training."}],"snapshot_sha256":"59c2ece815cb79e0214cc2bb919513e08f63d86964d413104663ef831d0ba165"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Building black-box models for dynamical systems from data is a challenging problem in machine learning, especially when asymptotic stability guarantees are required. In this paper, we introduce a novel stability-ensuring and backpropagation-compatible projection scheme based on the Schur decomposition for the state matrix of linear discrete-time state-space layers, as well as an alternative pre-factorized formulation of the methodology. The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stab","authors_text":"Fredy Ruiz, Lasse Lensu, Sergio Vanegas","cross_cats":["cs.SY","eess.SY"],"headline":"Projecting the quasi-triangular factor from the real Schur decomposition of the state matrix onto its nearest stable peer keeps discrete-time state-space neural-network layers asymptotically stable during training.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T07:28:11Z","title":"A Novel Schur-Decomposition-Based Weight Projection Method for Stable State-Space Neural-Network Architectures"},"references":{"count":80,"internal_anchors":4,"resolved_work":80,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Model reduction via balanced realizations: an extension and frequency weighting techniques.IEEE Transactions on Automatic Control, 33(7):687–692, 2002","work_id":"f1833826-61c3-4552-a1d6-e198a7ecbed6","year":2002},{"cited_arxiv_id":"2111.00396","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Efficiently Modeling Long Sequences with Structured State Spaces","work_id":"4150b761-b8bf-4d9b-a2f8-cb2d1b73d378","year":2021},{"cited_arxiv_id":"2208.04933","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Simplified State Space Layers for Sequence Modeling","work_id":"d4f90830-6ceb-4c9e-b206-eb32ac063f45","year":2022},{"cited_arxiv_id":"2312.00752","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","work_id":"4ee75248-1199-492c-a52f-6661e0f4adff","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Hippo: Recurrent memory with optimal polynomial projections.Advances in neural information processing systems, 33:1474–1487, 2020","work_id":"0d6d46ae-5de3-4ecb-aa6f-923be89ee19a","year":2020}],"snapshot_sha256":"49a1d9a66f11aaebc5177e4a538166b3bff65c2342bf694ddfb513d92b874ade"},"source":{"id":"2605.14489","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:33:53.095596Z","id":"0f7f7b73-610c-404f-bca2-71244bc725af","model_set":{"reader":"grok-4.3"},"one_line_summary":"A real Schur decomposition projection maps the state matrix of discrete-time state-space layers onto its nearest stable counterpart, delivering accuracy comparable to prior stable identification methods with fewer weights.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Projecting the quasi-triangular factor from the real Schur decomposition of the state matrix onto its nearest stable peer keeps discrete-time state-space neural-network layers asymptotically stable during training.","strongest_claim":"The proposed methods dynamically project the quasi-triangular factor of the state matrix's real Schur decomposition onto its nearest stable peer, ensuring stable dynamics with minimal overparameterization.","weakest_assumption":"That repeatedly projecting the state matrix during training does not materially distort the optimization landscape or introduce bias that prevents reaching accurate models on real-world data."}},"verdict_id":"0f7f7b73-610c-404f-bca2-71244bc725af"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:54923afbb722dcbe33bc47e264bae11ee9dff0da5f6a77758fca1a71910333b3","target":"record","created_at":"2026-05-17T23:39:06Z","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":"9f10647708b472ee71a1581797cf4cfa9952d32476484265695c471b65feffd2","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T07:28:11Z","title_canon_sha256":"f1933359cc85b0c19940d8c7acd55e832d6db5c697b49aadfc9f7facd260cb3d"},"schema_version":"1.0","source":{"id":"2605.14489","kind":"arxiv","version":1}},"canonical_sha256":"5c87abebba5fad5f8e366e267712ff6231d6cb267eae2e193d6b4792dd0a0e82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c87abebba5fad5f8e366e267712ff6231d6cb267eae2e193d6b4792dd0a0e82","first_computed_at":"2026-05-17T23:39:06.452878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.452878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tpXLVgsz0Q6iE3mBACyGChsCwYJv1RwGkUCsVa2j4gUxPAN/676r8ip9pG/gEDnSYmCv7Z4zgsE7efTrVnZZAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.453618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14489","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54923afbb722dcbe33bc47e264bae11ee9dff0da5f6a77758fca1a71910333b3","sha256:31d647679736239a9b13814d394793dd67465e4e92e39a07ad3cad1a8346848b"],"state_sha256":"a43932e711e85f3bda38cdb9ae6f489a8f7dc5360430743aafabcf6316071672"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/xfQOBt8LgCwN3PLcIEAh5hYrp4CFhTzzml/dDfLj3xK9+KXr5Ey4WqzWXTvZhE8dbyTkVj7R2oJ3XhgrmMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T08:26:16.679675Z","bundle_sha256":"e9d8810e55f814f519860f4ba542a07d3e25b1810b023cc4484d441fa7033494"}}