{"as_of":"2026-08-24T00:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cb4e57c3b3be5c97a608574c7cf617810663811fff4e4b57837289fe55bf8980","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T17:52:29.131365Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-30T23:38:38.609093Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2607.04531","snapshot_observed_at":"2026-07-30T23:38:38.609093Z","title":"Lyapunov-guided training for hardware-safe neural networks under fixed-point arithmetic","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.23390","last_updated":"2026-07-25T23:29:23Z","snapshot_observed_at":"2026-08-21T11:34:53.661621Z","submitted_at":"2026-07-25T23:29:23Z","title":"When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation","version":1},"reference_index":144,"source":"arxiv_source","source_observed_at":"2026-07-30T23:38:38.609093Z"},"links":{"cited_paper":"/paper/2607.04531","citing_paper":"/paper/2607.23390"},"observation_digest":"sha256:e3b9051bbbac4ea6b3e33b6c906a8f4aae5796623fb00a49af6da44be02ca330","observation_id":"5e97fe39-015f-442f-9897-928276ce6a58","resolution":{"observed_at":"2026-07-30T23:38:38.609093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2607.04531/citation-record","integrity":"/paper/2607.04531/integrity","json":"/paper/2607.04531/citation-record.json","paper":"/paper/2607.04531"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:7e107bc293ffe5048cdb3d5bf6a05c3cfbb3a203e6009fe5e4dfa169040bd4e2","observation_id":"23392695-c48f-4bf6-80ee-ceb6571d2147","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.08203","last_updated":"2018-03-22T02:14:08Z","snapshot_observed_at":"2026-08-19T12:43:22.243156Z","submitted_at":"2018-03-22T02:14:08Z","title":"Residual Networks: Lyapunov Stability and Convex Decomposition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.08203","snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Residual Networks: Lyapunov Stability and Convex Decomposition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"cited_paper":"/paper/1803.08203","citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:67115aabb7b1e8957be9c0f2cc5885c3db96f066c85806ad068d98949ed2c63f","observation_id":"689554fb-4e80-4c7a-ac4d-6f5f7fd8ea0c","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"The Lyapunov Neural Network: Adaptive Sta- bility Certification for Safe Learning of Dynamical Systems","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:8cdfb31aad94c34fccbe881db4c220f8a4efea7ddacf707d4ea757cf0d0f759b","observation_id":"1b7c1fb8-402e-4dd8-a68f-62009d7cc90e","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"An SMT Theory of Fixed- Point Arithmetic","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:2e4fd0751e1839716abc00847e774a4d71a3df28ec1cb249695f65a7dd45f41c","observation_id":"dac25ac7-aa85-4f13-9157-fbd524c8bf50","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"An SMT Theory of Fixed- Point Arithmetic","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:c61ae377a9b0abae0ebbddbd8774c8deb897a1b2a85d1ade66441efb2001776d","observation_id":"528793dd-cf9d-4bd6-9dd1-ff2bfe903445","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Quantization of Deep Neural Networks for Accumulator-Constrained Processors","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:f601a57a6979f15b444c8e5345a39e381f261e1f1540c2ef2d201d669f769886","observation_id":"fb008f9d-2edb-428f-a045-b9615cd911e3","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14152","last_updated":"2021-09-29T02:40:32Z","snapshot_observed_at":"2026-08-16T17:53:15.842577Z","submitted_at":"2021-09-29T02:40:32Z","title":"Lyapunov-stable neural-network control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14152","snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Lyapunov-Stable Neural-Network Control","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"cited_paper":"/paper/2109.14152","citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:053bfcf30e036e194b98a13d7d9808be9ef0d5ede306a8eb4c44143d23a6dbda","observation_id":"cb77a88b-76b6-4d0e-bf68-3b97183cdc63","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13630","last_updated":"2021-06-21T21:01:12Z","snapshot_observed_at":"2026-08-19T12:45:19.661887Z","submitted_at":"2021-03-25T06:57:11Z","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.13630","snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"A Survey of Quantization Meth- ods for Efficient Neural Network Inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"cited_paper":"/paper/2103.13630","citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:9847142a331fa43accf5bb16c468c93ae726ee2b6fb47c6019e815dc29446960","observation_id":"4159fcf2-36dd-47b0-80b2-a690665a03d8","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Stable Neural ODE with Lyapunov- Stable Equilibrium Points for Defending Against Ad- versarial Attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:a0d7be0c6a2b1c51926947fee95962eb952e20ebdc10f41c452d50aa2cdb77c7","observation_id":"d2879482-5ceb-4adc-8f2c-465d9654bd4f","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08295","last_updated":"2021-06-15T17:12:42Z","snapshot_observed_at":"2026-08-19T05:42:08.537901Z","submitted_at":"2021-06-15T17:12:42Z","title":"A White Paper on Neural Network Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08295","snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"A White Paper on Neural Network Quantization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"cited_paper":"/paper/2106.08295","citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:ca6d3cba9a27fa25c59389e9eb61a7bd065420015a6f41d0a538957b273cbdab","observation_id":"a2753168-a1cd-4891-b575-0e815f2ca6b7","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.06126","last_updated":"2023-01-18T00:43:34Z","snapshot_observed_at":"2026-08-19T12:42:07.192576Z","submitted_at":"2021-12-08T22:49:39Z","title":"Neural Network Quantization for Efficient Inference: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.06126","snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Neural Network Quantization for Ef- ficient Inference: A Survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"cited_paper":"/paper/2112.06126","citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:9b19053e7c31d61374f0523bb9e82dab3637021f5283ae314ede0d3416ef0ea9","observation_id":"c60f0486-b71f-4218-9cf2-cf0a4cc3135f","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"LyaNet: A Lyapunov Framework for Training Neural ODEs","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:1a339b6ae2944d5e1cff799a55762c110932746976bd00dfe3e0a66d80696552","observation_id":"bdceb3a7-7799-449f-b112-d1374f5d09d9","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.07877","last_updated":"2023-10-23T17:22:51Z","snapshot_observed_at":"2026-08-16T17:00:19.961408Z","submitted_at":"2022-05-14T15:08:32Z","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.07877","snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"A Comprehensive Survey on Model Quanti- zation for Deep Neural Networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"cited_paper":"/paper/2205.07877","citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:6e24fd969312a9d399e9cbe522f86e2461abb1bc3d9312efd98f6085a187163c","observation_id":"20570c8b-b71e-47c2-a31f-c93fd3bdf5e6","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"A2Q: Accumulator-Aware Quanti- zation with Guaranteed Overflow Avoidance","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:283de85f65218366cb5b183c9b4e3b9fa7ace30e0076c80e4a300832f2df0dac","observation_id":"8c6a5573-52de-4955-832e-6d1d39af7874","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T17:52:29.131365Z","title":"Advances in the Neural Network Quan- tization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-11T17:52:29.131365Z"},"links":{"citing_paper":"/paper/2607.04531"},"observation_digest":"sha256:a56dd4ab8276f928c109387a32d3ac35ef5f5677ce3248f48f6724d808c3b1a3","observation_id":"e9f97fe7-f371-4ca9-8f78-c01a739a5cd8","resolution":{"observed_at":"2026-07-11T17:52:29.131365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.04531","last_updated":"2026-07-05T22:25:52Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T03:26:44.618521Z","submitted_at":"2026-07-05T22:25:52Z","title":"Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":15},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2607.04531."}