{"as_of":"2026-08-23T04:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:94ce0eb620e4c19bbc8df6fd218fa70ac03daf8e9475f75d2fe5d0ea30c59fa4","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T16:39:14.759719Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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":"2026-07-01T01:19:12.424654Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T13:05:44.274610Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"cited_work":{"arxiv_id":"2501.13023","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.13023","snapshot_observed_at":"2026-07-01T13:05:44.274610Z","title":"Provably-safe neural network train- ing using hybrid zonotope reachability analysis,","venue":null,"work_id":"ba3954b8-78b0-495e-9306-cecf484e8a58","year":2025},"citing_paper":{"arxiv_id":"2606.30935","last_updated":"2026-06-29T21:38:44Z","snapshot_observed_at":"2026-08-18T10:15:37.231396Z","submitted_at":"2026-06-29T21:38:44Z","title":"ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-01T01:19:12.424654Z"},"links":{"cited_paper":"/paper/2501.13023","citing_paper":"/paper/2606.30935"},"observation_digest":"sha256:788834e2229117201db9b8f819f151dc02fb8f67311ddf4cc4fd88e5215a4fdb","observation_id":"54be8bad-4a9d-4032-8b0a-8f37b07fd2aa","resolution":{"observed_at":"2026-07-01T13:05:44.276129Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.13023/citation-record","integrity":"/paper/2501.13023/integrity","json":"/paper/2501.13023/citation-record.json","paper":"/paper/2501.13023"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.243587Z","title":"Challenges of real-world reinforcement learning: definitions, benchmarks and analysis,","venue":null,"work_id":"25973dbc-3a34-4e92-86fe-25e4d06b460b","year":2021},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.620078Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:a6b7a0da6c646e945ac82774c819f8d1774c9cc244fa269d66d2888b6b9a40f6","observation_id":"f65a25b8-2c66-4e7a-b99c-2a1ab0d655da","resolution":{"observed_at":"2026-08-10T16:39:15.249479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.227875Z","title":"Robust physical-world attacks on deep learning visual classification,","venue":null,"work_id":"090b6735-cf96-4ca4-8128-265174db0bc5","year":2018},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.624099Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:fac190776f625c559a9c7ea53c6c9ac95b4e9ea03695ea3d1544126fec7c0072","observation_id":"c01c97eb-06e9-4b8f-bea3-1f260c6acd8d","resolution":{"observed_at":"2026-08-10T16:39:15.233249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.10330","last_updated":"2024-05-24T22:33:04Z","snapshot_observed_at":"2026-08-20T13:48:07.834342Z","submitted_at":"2022-05-20T17:42:38Z","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.10330","snapshot_observed_at":"2026-08-10T16:39:14.627505Z","title":"A review of safe reinforce- ment learning: Methods, theory and applications,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.627505Z"},"links":{"cited_paper":"/paper/2205.10330","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:4f926645fd9869271dbfe50bc979b235e1eac6baaf9155ab31a1bcbc7f8bb3d2","observation_id":"43076690-9623-4ec8-8866-bd19b6056914","resolution":{"observed_at":"2026-08-10T16:39:14.627505Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.213413Z","title":"Constrained decision transformer for offline safe reinforcement learning,","venue":null,"work_id":"4a5d27bb-c375-4ab1-a0f6-c10e7a17cde0","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.631483Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:799e2ea7f6e0e5ab6cebe030650c21820ef2a7c1a501151f29cc5015dd49b8f7","observation_id":"5e2f1b91-b65e-464e-b832-4249fcd4b507","resolution":{"observed_at":"2026-08-10T16:39:15.217841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.199716Z","title":"POLICE: Provably optimal linear constraint enforcement for deep neural networks,","venue":null,"work_id":"5a39c73e-de54-4b1d-b1ca-c5d6322a37bf","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.635177Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:8e797f3cfe6e71875dfc75aaa7e84903941f4de5f5a1b7f8dbff22b6109b1dd4","observation_id":"c2ecbe97-e62f-4ccb-81f5-39bb71bf37ca","resolution":{"observed_at":"2026-08-10T16:39:15.204349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.186995Z","title":"Hybrid zonotopes exactly represent ReLU neural networks,","venue":null,"work_id":"232abe95-1bff-4e50-bbf9-14177b00e6c9","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.639077Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:dca097e34acac9996cfd9750c19f85b12cc567062c36908a7024d60f671f9340","observation_id":"076105ab-ee21-4b8a-ac17-64d0002859b6","resolution":{"observed_at":"2026-08-10T16:39:15.191283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.169314Z","title":"Open- and closed-loop neural network verification using polynomial zono- topes,","venue":null,"work_id":"4caca505-c1ed-444e-8dc8-56b222fde602","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.643148Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:509762403974c4b57362ea7d1e9744674e815357cf608c08707451f316406d41","observation_id":"cd256108-f0ee-444c-87b6-7985fb3f4fc5","resolution":{"observed_at":"2026-08-10T16:39:15.177951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.646616Z","title":"Verification of deep convolutional neural networks using imagestars,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.646616Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:666aa32864108f126aeea322cab160b702c98d22dae7549c70d638f37c67d79a","observation_id":"240e2d9d-708c-4184-9bff-e0662879d8c2","resolution":{"observed_at":"2026-08-10T16:39:14.646616Z","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":"2026-08-10T16:39:14.650520Z","title":"Verification of recurrent neural networks with star reachability,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.650520Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:b6d5fbd9544693cacb2f3cfb33e61b38d3654e041ee666566dc3a6d7ec818fa8","observation_id":"a2427baf-7f4a-4915-b906-472f5859c58c","resolution":{"observed_at":"2026-08-10T16:39:14.650520Z","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":"2026-08-10T16:39:14.654287Z","title":"Lyapunov- stable neural-network control,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.654287Z"},"links":{"cited_paper":"/paper/2109.14152","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:02f2cd308000addc25abfbf9ad423a08e9ea0b556f476827bea0364af5ef3d8e","observation_id":"12ab7f56-631a-492f-903e-a944bbb17b52","resolution":{"observed_at":"2026-08-10T16:39:14.654287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.01273","last_updated":"2026-06-24T14:13:43Z","snapshot_observed_at":"2026-08-17T22:01:55.707542Z","submitted_at":"2024-08-02T13:55:26Z","title":"Certified Robust Invariant Polytope Training in Neural Controlled ODEs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.01273","snapshot_observed_at":"2026-08-10T16:39:14.658258Z","title":"Certified Robust Invariant Polytope Training in Neural Controlled ODEs,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.658258Z"},"links":{"cited_paper":"/paper/2408.01273","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:75e025944af49c51784f607e1edefdacda25ab06b527ec6339e59ceb2cbad966","observation_id":"d03e8bb9-dd6d-4a1c-8906-138393fe9516","resolution":{"observed_at":"2026-08-10T16:39:14.658258Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.134033Z","title":"Differentiable abstract interpretation for provably robust neural networks,","venue":null,"work_id":"7b6c54b0-dc48-4758-a6e5-b5e4e6967047","year":2018},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.662740Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:2a0294ebc92ad6ce3775e3d1adedd94c61012a431f67975f2895fff970a4369a","observation_id":"3f66a7d3-c1b4-48c1-8960-89aa861f2b09","resolution":{"observed_at":"2026-08-10T16:39:15.138433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.122046Z","title":null,"venue":null,"work_id":"9f5a94a1-1b4d-445a-b4a5-bfd68083bfce","year":2020},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.666615Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:50b684fff7e5b84b992f3e0a3724a33e175016f9d4b42d964f1cefd6b01e3e95","observation_id":"c92e052e-f4d3-4338-ae9a-042b457b299d","resolution":{"observed_at":"2026-08-10T16:39:15.125859Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.109032Z","title":"Provable defenses against adversarial ex- amples via the convex outer adversarial polytope,","venue":null,"work_id":"0b7019a2-2d65-4a4a-8020-a80a62c697ff","year":2018},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.670652Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:12fc9b4fa18e3e893e24c6ea958bd3074ac236398d0dbb7c44f46102ce01b82b","observation_id":"c6fc243c-1202-4837-83aa-6accc600d2d8","resolution":{"observed_at":"2026-08-10T16:39:15.113245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07696","last_updated":"2021-07-16T04:03:01Z","snapshot_observed_at":"2026-08-19T07:15:49.265722Z","submitted_at":"2021-07-16T04:03:01Z","title":"Constrained Feedforward Neural Network Training via Reachability Analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07696","snapshot_observed_at":"2026-08-10T16:39:14.675069Z","title":"Constrained feedforward neural network training via reachability analysis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.675069Z"},"links":{"cited_paper":"/paper/2107.07696","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:ce3e20176eaaa885a54f5fade0fa3d0b36e0663b8437fb7942be42d514c444f3","observation_id":"0803a134-9758-4c46-896e-eb2d70b72ef2","resolution":{"observed_at":"2026-08-10T16:39:14.675069Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.096792Z","title":"Neural network repair with reachability analysis,","venue":null,"work_id":"ebfdec8f-665c-4df3-aefa-b2198aee2085","year":2022},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.679432Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:138dccec73b7983f0f2fe9d65bd083b82004d40edf5c384d01e1ec878c6ba283","observation_id":"efe1cf70-cbda-425f-a37d-81abbfbf3405","resolution":{"observed_at":"2026-08-10T16:39:15.100666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.084949Z","title":"Hybrid zonotopes: A new set representation for reachability analysis of mixed logical dynamical systems,","venue":null,"work_id":"14341065-8ed0-42bf-9899-695ee82e9963","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.683295Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:c1f130c0af4c2da8422961abd2dbe94f4dc43bd7bed0c561989b77ee5659249c","observation_id":"3147175a-bcf4-4ce5-919f-ac88e48cdf3f","resolution":{"observed_at":"2026-08-10T16:39:15.088972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.073539Z","title":"Unions and complements of hybrid zonotopes,","venue":null,"work_id":"fb9c4f7c-7992-4da1-947b-0600ee88e746","year":2021},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.686824Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:2fd2377e454f0ad509ba7b7ff2278cf82ce1a479dae8a88341ec1ab21866dc5a","observation_id":"205007c3-ec71-40cf-8b1e-f4d40c3b06c2","resolution":{"observed_at":"2026-08-10T16:39:15.077465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.062301Z","title":"zonoLAB: A MATLAB toolbox for set-based control systems anal- ysis using hybrid zonotopes,","venue":null,"work_id":"46a63531-c789-4d58-b78f-cd9a3f8ec5e4","year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.690360Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:d07ca3cdee6a031555850c8701cbf9a4911e630849636816e5212d6b377d1a22","observation_id":"8470a841-3f85-4e70-b0b9-c32b5ce71888","resolution":{"observed_at":"2026-08-10T16:39:15.066271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.049324Z","title":"Backward reachability analysis of neural feedback systems using hybrid zonotopes,","venue":null,"work_id":"4c38a529-808b-4464-b554-07327e5cb492","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.694023Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:41b983b50cffe12e509893cee0da01d809c5a865eff24911fa0676f9f308b786","observation_id":"9608a2fd-20af-4051-8343-827ba78f556c","resolution":{"observed_at":"2026-08-10T16:39:15.053489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.035750Z","title":"A set-based approach for robust control co-design,","venue":null,"work_id":"45e406c4-da9b-4a3f-8bcf-1aed781180da","year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.697813Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:d01bb5c7b1d7e299474da0721614297d10a2c648d2a1ca4a66c40af3cef1f9cb","observation_id":"aa729b0b-1213-4d5e-92bf-079f5a43a291","resolution":{"observed_at":"2026-08-10T16:39:15.040128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.021639Z","title":"Hybrid Zonotope-Based Backward Reachability Analysis for Neural Feedback Systems With Nonlinear Plant Models,","venue":null,"work_id":"2660038f-fc77-412f-88bf-00581c9ac923","year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.701642Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:39fe9deea6d34953727795773a24fa57ed0286fac38cf04834bc8f7d790ed5bc","observation_id":"463947a3-e4c9-4b4a-9486-b76f26fa044d","resolution":{"observed_at":"2026-08-10T16:39:15.026490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:15.006960Z","title":"Reachability analysis and safety verification of neural feedback systems via hybrid zonotopes,","venue":null,"work_id":"cb8a31d7-8fcd-4b45-b66f-793a7f9681c0","year":2023},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.705407Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:d948933049dd733b3488e360825fe49bfa25a9761a9a5397d3224cb3ef107e06","observation_id":"857b3db1-c045-4c36-8a1f-b9d2f23f1950","resolution":{"observed_at":"2026-08-10T16:39:15.012001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.993747Z","title":"Scalable zonotopic under-approximation of backward reachable sets for uncertain linear systems,","venue":null,"work_id":"97f529fd-ebdc-4a76-b40e-81d34fd1c9a8","year":2021},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.709799Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:c56d541e4120a9e6d126f68d789d491da045d110aad482f645a607d9bc87a8ad","observation_id":"c3dd1064-1c03-4e96-a416-b8f6ab99817d","resolution":{"observed_at":"2026-08-10T16:39:14.998164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.979641Z","title":"Presolve reductions in mixed integer programming,","venue":null,"work_id":"9eeb17a4-10d6-4db2-a6b9-bc967f2b5471","year":2020},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.713883Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:c1fb51faf19b384f6a5bb71c9101d77472fe7e6f815d655be76aae393921c272","observation_id":"af690699-ca9b-4554-9155-0d74c3fbfe83","resolution":{"observed_at":"2026-08-10T16:39:14.984167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.717561Z","title":"Constrained zonotopes: A new tool for set-based estimation and fault detection,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.717561Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:fbaddee37b484389fc4be277ba75fe8c8a32d35f7b84b75390aabedc4e34e65b","observation_id":"89578086-4193-438b-a239-769c724e6c57","resolution":{"observed_at":"2026-08-10T16:39:14.717561Z","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":"2026-08-10T16:39:14.721414Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.721414Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:6e5b35a97fa434b831c1a4ba5e39ee6b307261d05e40a0cfa9984693520dd3c5","observation_id":"6e697969-f539-4462-97d0-017142f6b45b","resolution":{"observed_at":"2026-08-10T16:39:14.721414Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.950401Z","title":"Two-Stage Predict+ Optimize for MILPs with Unknown Parameters in Constraints,","venue":null,"work_id":"0a60ec5c-e66b-4f1c-85fd-ed2bed4723a6","year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.725413Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:0da41b078bd23b7287e9e4e1b85e08f1703468ff9f247f0d8d0c104603937889","observation_id":"ae6b7ec5-61ae-4c26-b756-9d78fb7f346f","resolution":{"observed_at":"2026-08-10T16:39:14.954416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.938147Z","title":"Interior point solving for lp-based pre- diction+ optimisation,","venue":null,"work_id":"c183525c-025a-4048-ab53-5762ca8e8b86","year":2020},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.729053Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:b11cd0e4b96c935b656680e1b31276cba17ed7e124d6127533f8bd430cb01ab9","observation_id":"0380415d-7e2c-44ac-bb87-2f4d357d652d","resolution":{"observed_at":"2026-08-10T16:39:14.942167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-10T16:39:14.732970Z","title":"Adam: A method for stochastic optimiza- tion,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.732970Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:c55daa0a57d1feb76d913cb6167c699de2acec102bc4185e6b05176970142263","observation_id":"598e9823-e56b-41ac-a742-fe21e1150c65","resolution":{"observed_at":"2026-08-10T16:39:14.732970Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.925936Z","title":"Gurobi Optimization, Gurobi optimizer reference manual , 2021","venue":null,"work_id":"fd5a6af5-89e4-4e37-a1be-8d329f280023","year":2021},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.737080Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:80e9195221362fac2647fbe76882017a746c8ee051eeb978979631156323aba5","observation_id":"e040af23-70cb-4a48-bdc1-430b3dba3c34","resolution":{"observed_at":"2026-08-10T16:39:14.930400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.741284Z","title":null,"venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.741284Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:da0f46a6487bc57e7c4002959ee2414d2a5001615bfaead6da97faa9bb9646e0","observation_id":"e73346d6-75d8-49fe-bea7-a33012454b2f","resolution":{"observed_at":"2026-08-10T16:39:14.741284Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.905613Z","title":"Reachability analysis of nonlinear systems with uncertain parameters using conservative linearization,","venue":null,"work_id":"f14913f3-8cbd-48e7-8bc2-094ddd0620a6","year":2008},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.744991Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:2b9f237ddca2a2e7d5bc06b8ac44c67c50f8f15610c3c1c30a00d7b12c0b504b","observation_id":"a95fb6f6-a5ee-427f-a2ca-905c87fa6d9b","resolution":{"observed_at":"2026-08-10T16:39:14.909790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.13195","last_updated":"2025-03-03T16:38:51Z","snapshot_observed_at":"2026-08-16T13:17:00.231532Z","submitted_at":"2024-09-20T03:55:47Z","title":"Guaranteed Reach-Avoid for Black-Box Systems through Narrow Gaps via Neural Network Reachability","version":2},"cited_work":{"arxiv_id":"2409.13195","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.13195","snapshot_observed_at":"2026-08-10T16:39:14.818722Z","title":"Guaranteed Reach-Avoid for Black-Box Systems through Narrow Gaps via Neural Network Reachability","venue":"cs.RO","work_id":"30ab573c-de6c-4c7d-a122-2c44a4f9bb25","year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.748650Z"},"links":{"cited_paper":"/paper/2409.13195","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:d3a797b4828774216c5ff06d6e621585f546fdf391686cac7fa32fd26cd4104f","observation_id":"0b73d7f4-24d1-47f9-8509-069ff034f25e","resolution":{"observed_at":"2026-08-10T16:39:14.824890Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15604","last_updated":"2024-05-28T18:51:04Z","snapshot_observed_at":"2026-08-16T14:15:47.463588Z","submitted_at":"2024-02-23T20:54:47Z","title":"Goal-Reaching Trajectory Design Near Danger with Piecewise Affine Reach-avoid Computation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15604","snapshot_observed_at":"2026-08-10T16:39:14.752222Z","title":"Goal-reaching trajectory design near danger with piecewise affine reach-avoid computation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.752222Z"},"links":{"cited_paper":"/paper/2402.15604","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:f840658b4070fdcbdd4eec554dafc93ddbd4e22db447e02e78076ac571070435","observation_id":"97f353f2-8859-4a27-974e-71b95edec22d","resolution":{"observed_at":"2026-08-10T16:39:14.752222Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T16:39:14.892657Z","title":"Feurer and F","venue":null,"work_id":"77a32403-bda0-49a1-84cf-8faa09efb634","year":2019},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.756388Z"},"links":{"citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:c214c1a18ab0669f01016558ad97d6f1d2f5f01561e6cfd98b3901ece3c09f78","observation_id":"fcbad085-483d-4bef-bb2b-9952034b2b64","resolution":{"observed_at":"2026-08-10T16:39:14.896741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07956","last_updated":"2024-06-05T00:30:57Z","snapshot_observed_at":"2026-08-21T14:29:01.417267Z","submitted_at":"2024-04-11T17:49:15Z","title":"Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07956","snapshot_observed_at":"2026-08-10T16:39:14.759719Z","title":"Lyapunov-stable neural control for state and output feedback: A novel formulation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T16:39:14.759719Z"},"links":{"cited_paper":"/paper/2404.07956","citing_paper":"/paper/2501.13023"},"observation_digest":"sha256:112b52a292833cf2ee457326012c210ded633cc7924c369ea5fe443dc62c024b","observation_id":"fec8ce34-dd53-400d-b7e3-f5d261adbcca","resolution":{"observed_at":"2026-08-10T16:39:14.759719Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.13023","last_updated":"2025-08-25T18:02:10Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T22:02:55.924131Z","submitted_at":"2025-01-22T17:13:48Z","title":"Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":23},"total_outbound_references":37},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2501.13023."}