{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QHNIANUHIU6KS246F4CHRDE6KP","short_pith_number":"pith:QHNIANUH","schema_version":"1.0","canonical_sha256":"81da803687453ca96b9e2f04788c9e53dc373679f4a8f2b675578f7d0f48aa15","source":{"kind":"arxiv","id":"2607.04531","version":1},"attestation_state":"computed","paper":{"title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","eess.SP","math.NA"],"primary_cat":"cs.LG","authors_text":"Amir Hussain, Anis Hamadouche","submitted_at":"2026-07-05T22:25:52Z","abstract_excerpt":"Low-precision neural networks are attractive for resource-constrained hardware, but fixed-point arithmetic introduces failure modes that are often hidden by idealised quantisation models. In particular, two's-complement overflow wrapping can corrupt hidden activations by changing both their magnitude and sign, leading to unstable numerical error propagation and severe accuracy degradation. This paper proposes a Lyapunov-stabilised quantisation framework for low-precision neural networks operating under hardware-style wrapping arithmetic. The hidden-state energy is monitored through a layerwise"},"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":"2607.04531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T22:25:52Z","cross_cats_sorted":["cs.AI","cs.NA","eess.SP","math.NA"],"title_canon_sha256":"9561dcf8aeea82a1c04923ed6e6d15fd5b15eca0736aa95ab441362d142a8076","abstract_canon_sha256":"d2a71e7d3b2acb03e7e150699d01ba72279636a4967eb1e0da0ced2173e51fbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:23.443665Z","signature_b64":"Taz5CDSPZ1vr5FryeK6D2D3KIMwGs0wRLIhi42lvwc/SuBCkxqJLhqdQXb2kXnNk/oEm3gXM/Mcb22WOcMwNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81da803687453ca96b9e2f04788c9e53dc373679f4a8f2b675578f7d0f48aa15","last_reissued_at":"2026-07-07T02:19:23.442971Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:23.442971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NA","eess.SP","math.NA"],"primary_cat":"cs.LG","authors_text":"Amir Hussain, Anis Hamadouche","submitted_at":"2026-07-05T22:25:52Z","abstract_excerpt":"Low-precision neural networks are attractive for resource-constrained hardware, but fixed-point arithmetic introduces failure modes that are often hidden by idealised quantisation models. In particular, two's-complement overflow wrapping can corrupt hidden activations by changing both their magnitude and sign, leading to unstable numerical error propagation and severe accuracy degradation. This paper proposes a Lyapunov-stabilised quantisation framework for low-precision neural networks operating under hardware-style wrapping arithmetic. The hidden-state energy is monitored through a layerwise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04531","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/2607.04531/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":"2607.04531","created_at":"2026-07-07T02:19:23.443070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04531v1","created_at":"2026-07-07T02:19:23.443070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04531","created_at":"2026-07-07T02:19:23.443070+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHNIANUHIU6K","created_at":"2026-07-07T02:19:23.443070+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHNIANUHIU6KS246","created_at":"2026-07-07T02:19:23.443070+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHNIANUH","created_at":"2026-07-07T02:19:23.443070+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/QHNIANUHIU6KS246F4CHRDE6KP","json":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP.json","graph_json":"https://pith.science/api/pith-number/QHNIANUHIU6KS246F4CHRDE6KP/graph.json","events_json":"https://pith.science/api/pith-number/QHNIANUHIU6KS246F4CHRDE6KP/events.json","paper":"https://pith.science/paper/QHNIANUH"},"agent_actions":{"view_html":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP","download_json":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP.json","view_paper":"https://pith.science/paper/QHNIANUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04531&json=true","fetch_graph":"https://pith.science/api/pith-number/QHNIANUHIU6KS246F4CHRDE6KP/graph.json","fetch_events":"https://pith.science/api/pith-number/QHNIANUHIU6KS246F4CHRDE6KP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP/action/storage_attestation","attest_author":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP/action/author_attestation","sign_citation":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP/action/citation_signature","submit_replication":"https://pith.science/pith/QHNIANUHIU6KS246F4CHRDE6KP/action/replication_record"}},"created_at":"2026-07-07T02:19:23.443070+00:00","updated_at":"2026-07-07T02:19:23.443070+00:00"}