{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3EA4NGPRV55YNCIZMOWRVHZRBM","short_pith_number":"pith:3EA4NGPR","canonical_record":{"source":{"id":"2501.03017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T13:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"661dbeca0274db55f67778cf4d40c620638710bc88eed707a3496512faf9494f","abstract_canon_sha256":"4a544282001a9f2b42024047d3bc40cb625c35318e18b1eb8abc3bb5d35f46ba"},"schema_version":"1.0"},"canonical_sha256":"d901c699f1af7b86891963ad1a9f310b007810cddf65f1362c48c6dde0cbc704","source":{"kind":"arxiv","id":"2501.03017","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03017","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03017v2","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03017","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"3EA4NGPRV55Y","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"3EA4NGPRV55YNCIZ","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"3EA4NGPR","created_at":"2026-07-05T10:45:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3EA4NGPRV55YNCIZMOWRVHZRBM","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T13:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"661dbeca0274db55f67778cf4d40c620638710bc88eed707a3496512faf9494f","abstract_canon_sha256":"4a544282001a9f2b42024047d3bc40cb625c35318e18b1eb8abc3bb5d35f46ba"},"schema_version":"1.0"},"canonical_sha256":"d901c699f1af7b86891963ad1a9f310b007810cddf65f1362c48c6dde0cbc704","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:58.947119Z","signature_b64":"RRrfBMhYnxLGgB6U/B8rglTeR3SrHrP5wz9e1/HldcRrw7/U/pGAzUFc1curdCA8MNA1VhDfNsoN7OQ5q8vsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d901c699f1af7b86891963ad1a9f310b007810cddf65f1362c48c6dde0cbc704","last_reissued_at":"2026-07-05T10:45:58.946690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:58.946690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03017","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":"2026-07-05T10:45:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mp7Spfi4KKqdGYSTE3ttO0HUYoGi276aAakjp/4PsV5m7ETipvECQWd6HQWIICGSRtMNizpO+PU0HwbZbpIPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:19:08.028122Z"},"content_sha256":"02f784da6f1fde6352e4db7aaae5d4019e6b19c9a913877584df72e10d1ee245","schema_version":"1.0","event_id":"sha256:02f784da6f1fde6352e4db7aaae5d4019e6b19c9a913877584df72e10d1ee245"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3EA4NGPRV55YNCIZMOWRVHZRBM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convexity in ReLU Neural Networks: beyond ICNNs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anne Gagneux, Emmanuel Soubies, Mathurin Massias, R\\'emi Gribonval","submitted_at":"2025-01-06T13:53:59Z","abstract_excerpt":"Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to use learning-based methods, where fixed functions or operators are replaced by learned neural networks. Regardless of their empirical superiority, establishing rigorous guarantees for these methods often requires to impose structural constraints on neural architectures, in particular convexity. The most popular way to do so is to use so-called Input Convex Neural Networks (ICNNs). In order to explore the expressivity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03017","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/2501.03017/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":"2026-07-05T10:45:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RDLuO/4qpFSkw0TN2zgNPFheKjfqU6hTnrcUXbgEH2ba7gfqNIs7qjmMdc7XKcYRoLaA6PJmxFdwfWJrrnFZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:19:08.028438Z"},"content_sha256":"7aec086b8fd7094daef6a30b27f29b2e8695b60cef957e2de170fe53047f75ea","schema_version":"1.0","event_id":"sha256:7aec086b8fd7094daef6a30b27f29b2e8695b60cef957e2de170fe53047f75ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EA4NGPRV55YNCIZMOWRVHZRBM/bundle.json","state_url":"https://pith.science/pith/3EA4NGPRV55YNCIZMOWRVHZRBM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EA4NGPRV55YNCIZMOWRVHZRBM/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":"2026-08-15T02:19:08Z","links":{"resolver":"https://pith.science/pith/3EA4NGPRV55YNCIZMOWRVHZRBM","bundle":"https://pith.science/pith/3EA4NGPRV55YNCIZMOWRVHZRBM/bundle.json","state":"https://pith.science/pith/3EA4NGPRV55YNCIZMOWRVHZRBM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EA4NGPRV55YNCIZMOWRVHZRBM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3EA4NGPRV55YNCIZMOWRVHZRBM","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":"4a544282001a9f2b42024047d3bc40cb625c35318e18b1eb8abc3bb5d35f46ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T13:53:59Z","title_canon_sha256":"661dbeca0274db55f67778cf4d40c620638710bc88eed707a3496512faf9494f"},"schema_version":"1.0","source":{"id":"2501.03017","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03017","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03017v2","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03017","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"3EA4NGPRV55Y","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"3EA4NGPRV55YNCIZ","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"3EA4NGPR","created_at":"2026-07-05T10:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:7aec086b8fd7094daef6a30b27f29b2e8695b60cef957e2de170fe53047f75ea","target":"graph","created_at":"2026-07-05T10:45:58Z","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/2501.03017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to use learning-based methods, where fixed functions or operators are replaced by learned neural networks. Regardless of their empirical superiority, establishing rigorous guarantees for these methods often requires to impose structural constraints on neural architectures, in particular convexity. The most popular way to do so is to use so-called Input Convex Neural Networks (ICNNs). In order to explore the expressivity ","authors_text":"Anne Gagneux, Emmanuel Soubies, Mathurin Massias, R\\'emi Gribonval","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T13:53:59Z","title":"Convexity in ReLU Neural Networks: beyond ICNNs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03017","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":"sha256:02f784da6f1fde6352e4db7aaae5d4019e6b19c9a913877584df72e10d1ee245","target":"record","created_at":"2026-07-05T10:45:58Z","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":"4a544282001a9f2b42024047d3bc40cb625c35318e18b1eb8abc3bb5d35f46ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T13:53:59Z","title_canon_sha256":"661dbeca0274db55f67778cf4d40c620638710bc88eed707a3496512faf9494f"},"schema_version":"1.0","source":{"id":"2501.03017","kind":"arxiv","version":2}},"canonical_sha256":"d901c699f1af7b86891963ad1a9f310b007810cddf65f1362c48c6dde0cbc704","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d901c699f1af7b86891963ad1a9f310b007810cddf65f1362c48c6dde0cbc704","first_computed_at":"2026-07-05T10:45:58.946690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:58.946690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RRrfBMhYnxLGgB6U/B8rglTeR3SrHrP5wz9e1/HldcRrw7/U/pGAzUFc1curdCA8MNA1VhDfNsoN7OQ5q8vsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:58.947119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03017","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02f784da6f1fde6352e4db7aaae5d4019e6b19c9a913877584df72e10d1ee245","sha256:7aec086b8fd7094daef6a30b27f29b2e8695b60cef957e2de170fe53047f75ea"],"state_sha256":"5478d7d6322cfcc0caa1e5db229783210234676b289bb11a7f703ac7ce563c50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wmItvmJltj/LFdklDfwKwIANt/Lc319FtJCj2aRFGZKVP7aCzSMIX3BXDwfkPs/6o41ko9vz+kT1Eo+z/fi8Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T02:19:08.032192Z","bundle_sha256":"f6c031799c24443e1d1fcd590fc197fb595c0cc1a0d84839bb5b5051adcd7a64"}}