{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6HMTIY33M6A3TFATB3PR75Y4SU","short_pith_number":"pith:6HMTIY33","canonical_record":{"source":{"id":"2210.16222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T15:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"6d2f7a5b1820f604ece9054727ab9d7363a70d43e1056e9c258ddcab6bd6c8ad","abstract_canon_sha256":"f8cb50095f90455c8bf6ae792c51e55c9319442be3f4b8bfd357fcc4cbc19b49"},"schema_version":"1.0"},"canonical_sha256":"f1d934637b6781b994130edf1ff71c9516edb4c1eca14de125f82334ab8b9a55","source":{"kind":"arxiv","id":"2210.16222","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16222","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16222v2","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16222","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"6HMTIY33M6A3","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"6HMTIY33M6A3TFAT","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"6HMTIY33","created_at":"2026-07-05T07:25:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6HMTIY33M6A3TFATB3PR75Y4SU","target":"record","payload":{"canonical_record":{"source":{"id":"2210.16222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T15:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"6d2f7a5b1820f604ece9054727ab9d7363a70d43e1056e9c258ddcab6bd6c8ad","abstract_canon_sha256":"f8cb50095f90455c8bf6ae792c51e55c9319442be3f4b8bfd357fcc4cbc19b49"},"schema_version":"1.0"},"canonical_sha256":"f1d934637b6781b994130edf1ff71c9516edb4c1eca14de125f82334ab8b9a55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:38.049497Z","signature_b64":"259oqQ0hH3UfdfSVnp+1Iw6L0JxjukGzBKqTU5/A9YLISKn0aUXv71GUqNo8lywYJjhqRHsRgUIkjab5vhfIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d934637b6781b994130edf1ff71c9516edb4c1eca14de125f82334ab8b9a55","last_reissued_at":"2026-07-05T07:25:38.049044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:38.049044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.16222","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":"2026-07-05T07:25:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEApOpBozF9kum/RMRMuuWs7Ul7qg/lYh6BJLy7rASxmuwzsWdIKKR7NR7ePhRdD4wtFa3hwQ0WRasICYtwbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:40:52.751729Z"},"content_sha256":"891f2a6882a0c1372259f17f8060865440aa869d2748a0729f08dbf07e2048df","schema_version":"1.0","event_id":"sha256:891f2a6882a0c1372259f17f8060865440aa869d2748a0729f08dbf07e2048df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6HMTIY33M6A3TFATB3PR75Y4SU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexis Goujon, Dimitris Perdios, Michael Unser, Pakshal Bohra, Sebastian Neumayer, Stanislas Ducotterd","submitted_at":"2022-10-28T15:56:55Z","abstract_excerpt":"Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both theoretically and empirically that they perform poorly when equipped with ReLU activation functions. By contrast, neural networks with learnable 1-Lipschitz linear splines are known to be more expressive. In this paper, we show that such networks correspond to global optima of a constrained functional optimization problem that consists of the training of a neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16222","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/2210.16222/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":"2026-07-05T07:25:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tf86wxpdDzyizhj1PKSUEaUXRvu8znBey0/4XqCSETrXbNUKomGUDVERB/1eRtplNRJ92SxTSUIiAtJvsZAACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:40:52.752085Z"},"content_sha256":"f6d7624240d2fabe146c90f1d215d8fee4fd12388b39232d0ef71ad24e30b722","schema_version":"1.0","event_id":"sha256:f6d7624240d2fabe146c90f1d215d8fee4fd12388b39232d0ef71ad24e30b722"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HMTIY33M6A3TFATB3PR75Y4SU/bundle.json","state_url":"https://pith.science/pith/6HMTIY33M6A3TFATB3PR75Y4SU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HMTIY33M6A3TFATB3PR75Y4SU/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":"2026-08-18T16:40:52Z","links":{"resolver":"https://pith.science/pith/6HMTIY33M6A3TFATB3PR75Y4SU","bundle":"https://pith.science/pith/6HMTIY33M6A3TFATB3PR75Y4SU/bundle.json","state":"https://pith.science/pith/6HMTIY33M6A3TFATB3PR75Y4SU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HMTIY33M6A3TFATB3PR75Y4SU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6HMTIY33M6A3TFATB3PR75Y4SU","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":"f8cb50095f90455c8bf6ae792c51e55c9319442be3f4b8bfd357fcc4cbc19b49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T15:56:55Z","title_canon_sha256":"6d2f7a5b1820f604ece9054727ab9d7363a70d43e1056e9c258ddcab6bd6c8ad"},"schema_version":"1.0","source":{"id":"2210.16222","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16222","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16222v2","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16222","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"6HMTIY33M6A3","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"6HMTIY33M6A3TFAT","created_at":"2026-07-05T07:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"6HMTIY33","created_at":"2026-07-05T07:25:38Z"}],"graph_snapshots":[{"event_id":"sha256:f6d7624240d2fabe146c90f1d215d8fee4fd12388b39232d0ef71ad24e30b722","target":"graph","created_at":"2026-07-05T07:25:38Z","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/2210.16222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both theoretically and empirically that they perform poorly when equipped with ReLU activation functions. By contrast, neural networks with learnable 1-Lipschitz linear splines are known to be more expressive. In this paper, we show that such networks correspond to global optima of a constrained functional optimization problem that consists of the training of a neural ","authors_text":"Alexis Goujon, Dimitris Perdios, Michael Unser, Pakshal Bohra, Sebastian Neumayer, Stanislas Ducotterd","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T15:56:55Z","title":"Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16222","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":"sha256:891f2a6882a0c1372259f17f8060865440aa869d2748a0729f08dbf07e2048df","target":"record","created_at":"2026-07-05T07:25:38Z","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":"f8cb50095f90455c8bf6ae792c51e55c9319442be3f4b8bfd357fcc4cbc19b49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T15:56:55Z","title_canon_sha256":"6d2f7a5b1820f604ece9054727ab9d7363a70d43e1056e9c258ddcab6bd6c8ad"},"schema_version":"1.0","source":{"id":"2210.16222","kind":"arxiv","version":2}},"canonical_sha256":"f1d934637b6781b994130edf1ff71c9516edb4c1eca14de125f82334ab8b9a55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d934637b6781b994130edf1ff71c9516edb4c1eca14de125f82334ab8b9a55","first_computed_at":"2026-07-05T07:25:38.049044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:38.049044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"259oqQ0hH3UfdfSVnp+1Iw6L0JxjukGzBKqTU5/A9YLISKn0aUXv71GUqNo8lywYJjhqRHsRgUIkjab5vhfIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:38.049497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.16222","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891f2a6882a0c1372259f17f8060865440aa869d2748a0729f08dbf07e2048df","sha256:f6d7624240d2fabe146c90f1d215d8fee4fd12388b39232d0ef71ad24e30b722"],"state_sha256":"97fcdb052e1a2fd25807f21fea958e211a0825c367b622327f994f98c17c804f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q+PLIvIiNkOijEjTovXV1jShMVB4J0h9AQudfD11CMf1hQ6DeaI+frf+4O3oc5r8kE6BtnWt3mXf8m1j5OohCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:40:52.755895Z","bundle_sha256":"ba2e92444725c554b1c8fadfee94e381d6c79ac7e1dfd2935a83da1fe7ab7518"}}