{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Y3NGOAFSHUBQEO7XOZEI7F5L5Q","short_pith_number":"pith:Y3NGOAFS","canonical_record":{"source":{"id":"2112.00038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T19:01:32Z","cross_cats_sorted":["hep-ex"],"title_canon_sha256":"158894a947c56765ee7cfcb499e0a90466a7f54cc0d8e409b0635b7c3def77b4","abstract_canon_sha256":"cdefb4222e03c4a819b9bfc1de016ff037ac837ff4e7df53f0766299659defd8"},"schema_version":"1.0"},"canonical_sha256":"c6da6700b23d03023bf776488f97abec337d18e1ca3b7988298970c1d68c26ad","source":{"kind":"arxiv","id":"2112.00038","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00038","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00038v2","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00038","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"Y3NGOAFSHUBQ","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"pith_short_16","alias_value":"Y3NGOAFSHUBQEO7X","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"pith_short_8","alias_value":"Y3NGOAFS","created_at":"2026-07-05T06:42:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Y3NGOAFSHUBQEO7XOZEI7F5L5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2112.00038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T19:01:32Z","cross_cats_sorted":["hep-ex"],"title_canon_sha256":"158894a947c56765ee7cfcb499e0a90466a7f54cc0d8e409b0635b7c3def77b4","abstract_canon_sha256":"cdefb4222e03c4a819b9bfc1de016ff037ac837ff4e7df53f0766299659defd8"},"schema_version":"1.0"},"canonical_sha256":"c6da6700b23d03023bf776488f97abec337d18e1ca3b7988298970c1d68c26ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:55.562092Z","signature_b64":"NSGqSQ8uzvec78prbFNKkQ5/E9d3uchqEUg8weXI4iXmb58NejLgTmyUlPW64c+gtomq9i5JYTocf+VcEX0bDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6da6700b23d03023bf776488f97abec337d18e1ca3b7988298970c1d68c26ad","last_reissued_at":"2026-07-05T06:42:55.561551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:55.561551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.00038","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:42:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ovwRIg1q36oc+ta3Vs1xYQuQkYHAoaQr3Lwna6eZpZIsMrQxZKfhPaFcdQdZQOdLPQt9TZyNlIvmAnyWekzECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:18:46.874300Z"},"content_sha256":"6de68e7a927df63926e052b9db5f8d44f5b5275700c4f7a3a207b68689d41e14","schema_version":"1.0","event_id":"sha256:6de68e7a927df63926e052b9db5f8d44f5b5275700c4f7a3a207b68689d41e14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Y3NGOAFSHUBQEO7XOZEI7F5L5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust and Provably Monotonic Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["hep-ex"],"primary_cat":"cs.LG","authors_text":"Mike Williams, Niklas Nolte, Ouail Kitouni","submitted_at":"2021-11-30T19:01:32Z","abstract_excerpt":"The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep learning models that can also be generalized to other architectures. The method relies on a simple weight normalization scheme during training that ensures the Lipschitz constant of every layer is below an upper limit specified by the analyst. A simple monotonic residual connection can then be used to make the model monotonic in any subset of its inputs, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00038","kind":"arxiv","version":2},"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/2112.00038/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:42:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DX3Cxit5wDp5cIKxlJ0DMZmYtifu69YtnTrkeHzSs2f/o6ks7b4ON9zhGldEnUui76Ffvn/4Bt2E8/mCexIGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:18:46.874672Z"},"content_sha256":"13ad569b2da6ba97377d2087612f730fe4a2ff03c985854bbcd93edc9d5e784e","schema_version":"1.0","event_id":"sha256:13ad569b2da6ba97377d2087612f730fe4a2ff03c985854bbcd93edc9d5e784e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q/bundle.json","state_url":"https://pith.science/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q/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":"2026-08-20T04:18:46Z","links":{"resolver":"https://pith.science/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q","bundle":"https://pith.science/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q/bundle.json","state":"https://pith.science/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3NGOAFSHUBQEO7XOZEI7F5L5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Y3NGOAFSHUBQEO7XOZEI7F5L5Q","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":"cdefb4222e03c4a819b9bfc1de016ff037ac837ff4e7df53f0766299659defd8","cross_cats_sorted":["hep-ex"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T19:01:32Z","title_canon_sha256":"158894a947c56765ee7cfcb499e0a90466a7f54cc0d8e409b0635b7c3def77b4"},"schema_version":"1.0","source":{"id":"2112.00038","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00038","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00038v2","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00038","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"Y3NGOAFSHUBQ","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"pith_short_16","alias_value":"Y3NGOAFSHUBQEO7X","created_at":"2026-07-05T06:42:55Z"},{"alias_kind":"pith_short_8","alias_value":"Y3NGOAFS","created_at":"2026-07-05T06:42:55Z"}],"graph_snapshots":[{"event_id":"sha256:13ad569b2da6ba97377d2087612f730fe4a2ff03c985854bbcd93edc9d5e784e","target":"graph","created_at":"2026-07-05T06:42:55Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.00038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep learning models that can also be generalized to other architectures. The method relies on a simple weight normalization scheme during training that ensures the Lipschitz constant of every layer is below an upper limit specified by the analyst. A simple monotonic residual connection can then be used to make the model monotonic in any subset of its inputs, which","authors_text":"Mike Williams, Niklas Nolte, Ouail Kitouni","cross_cats":["hep-ex"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T19:01:32Z","title":"Robust and Provably Monotonic Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00038","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6de68e7a927df63926e052b9db5f8d44f5b5275700c4f7a3a207b68689d41e14","target":"record","created_at":"2026-07-05T06:42:55Z","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":"cdefb4222e03c4a819b9bfc1de016ff037ac837ff4e7df53f0766299659defd8","cross_cats_sorted":["hep-ex"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T19:01:32Z","title_canon_sha256":"158894a947c56765ee7cfcb499e0a90466a7f54cc0d8e409b0635b7c3def77b4"},"schema_version":"1.0","source":{"id":"2112.00038","kind":"arxiv","version":2}},"canonical_sha256":"c6da6700b23d03023bf776488f97abec337d18e1ca3b7988298970c1d68c26ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6da6700b23d03023bf776488f97abec337d18e1ca3b7988298970c1d68c26ad","first_computed_at":"2026-07-05T06:42:55.561551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:55.561551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NSGqSQ8uzvec78prbFNKkQ5/E9d3uchqEUg8weXI4iXmb58NejLgTmyUlPW64c+gtomq9i5JYTocf+VcEX0bDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:55.562092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00038","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6de68e7a927df63926e052b9db5f8d44f5b5275700c4f7a3a207b68689d41e14","sha256:13ad569b2da6ba97377d2087612f730fe4a2ff03c985854bbcd93edc9d5e784e"],"state_sha256":"008b8558c3e367803499737c5015e81fcee283b59c04a2b9c0b7ab306505ce9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rItWNoTaEBDrwpZW80bba/HWln/oKwg44nA/rZ/jJZ0K+m+5REJoghRaAFRHU0+BCtk5bSZjh5cWnR15M6BCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:18:46.877364Z","bundle_sha256":"846034b78bb929656e82a836dc7d4fb244506043a519b6e24233fca72c279ede"}}