{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3RAFHSEXNBVBMAWDQL6LVA6E5C","short_pith_number":"pith:3RAFHSEX","canonical_record":{"source":{"id":"2505.06169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T16:19:34Z","cross_cats_sorted":["cs.DM","cs.NE","math.CO"],"title_canon_sha256":"c81e6b1f4ec8f3122ca699b54c2288801b800ceec57a41ffa39a9174f96f10a1","abstract_canon_sha256":"ab78d4d11fe6e096e949cff0798ee6e85a5847351626e1a997b2e8bfb00c1a7e"},"schema_version":"1.0"},"canonical_sha256":"dc4053c897686a1602c382fcba83c4e894df55a33e4c6375ae7ae059eda45394","source":{"kind":"arxiv","id":"2505.06169","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06169","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06169v1","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06169","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"pith_short_12","alias_value":"3RAFHSEXNBVB","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"pith_short_16","alias_value":"3RAFHSEXNBVBMAWD","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"pith_short_8","alias_value":"3RAFHSEX","created_at":"2026-07-05T11:00:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3RAFHSEXNBVBMAWDQL6LVA6E5C","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T16:19:34Z","cross_cats_sorted":["cs.DM","cs.NE","math.CO"],"title_canon_sha256":"c81e6b1f4ec8f3122ca699b54c2288801b800ceec57a41ffa39a9174f96f10a1","abstract_canon_sha256":"ab78d4d11fe6e096e949cff0798ee6e85a5847351626e1a997b2e8bfb00c1a7e"},"schema_version":"1.0"},"canonical_sha256":"dc4053c897686a1602c382fcba83c4e894df55a33e4c6375ae7ae059eda45394","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:55.279296Z","signature_b64":"j0eoaNhI3/84yy92wahOaodETj9zpsPNdKmCq/1m41puzaUDU6zoFQN2F58FxomIDm79PQaQxNdl1Wtrty05Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4053c897686a1602c382fcba83c4e894df55a33e4c6375ae7ae059eda45394","last_reissued_at":"2026-07-05T11:00:55.278797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:55.278797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06169","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/Ii54JRxLG46t7TN1Z1/B5d/ZEfk0k8GqVI9iLfy8cKMaYBz/bmuJbB2iTw13Zme91u719GySygd1XE+TnEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:00:55.588509Z"},"content_sha256":"e1528df5fe8f5dd736555fa0d01bbc49770bcae372032c8913b71a0e9995e3fd","schema_version":"1.0","event_id":"sha256:e1528df5fe8f5dd736555fa0d01bbc49770bcae372032c8913b71a0e9995e3fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3RAFHSEXNBVBMAWDQL6LVA6E5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Depth of Monotone ReLU Neural Networks and ICNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DM","cs.NE","math.CO"],"primary_cat":"cs.LG","authors_text":"Amir Yehudayoff, Christoph Hertrich, Daniel Reichman, Egor Bakaev, Florestan Brunck","submitted_at":"2025-05-09T16:19:34Z","abstract_excerpt":"We study two models of ReLU neural networks: monotone networks (ReLU$^+$) and input convex neural networks (ICNN). Our focus is on expressivity, mostly in terms of depth, and we prove the following lower bounds. For the maximum function MAX$_n$ computing the maximum of $n$ real numbers, we show that ReLU$^+$ networks cannot compute MAX$_n$, or even approximate it. We prove a sharp $n$ lower bound on the ICNN depth complexity of MAX$_n$. We also prove depth separations between ReLU networks and ICNNs; for every $k$, there is a depth-2 ReLU network of size $O(k^2)$ that cannot be simulated by a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06169","kind":"arxiv","version":1},"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/2505.06169/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":"2026-07-05T11:00:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZA/YG3nzUyn6eiaRzsDCuSYvqnkJqrajDEtJbKOzrvK51ARfbA+Mq4z6xS8CCej9SJwAm4GHXlHeSpL+5BjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:00:55.589039Z"},"content_sha256":"aeb5cc3ddaf8541fb40fb8d85e8041940977225cabe77f3aecb208d8f5e833bf","schema_version":"1.0","event_id":"sha256:aeb5cc3ddaf8541fb40fb8d85e8041940977225cabe77f3aecb208d8f5e833bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C/bundle.json","state_url":"https://pith.science/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C/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":"2026-08-11T19:00:55Z","links":{"resolver":"https://pith.science/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C","bundle":"https://pith.science/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C/bundle.json","state":"https://pith.science/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RAFHSEXNBVBMAWDQL6LVA6E5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3RAFHSEXNBVBMAWDQL6LVA6E5C","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":"ab78d4d11fe6e096e949cff0798ee6e85a5847351626e1a997b2e8bfb00c1a7e","cross_cats_sorted":["cs.DM","cs.NE","math.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T16:19:34Z","title_canon_sha256":"c81e6b1f4ec8f3122ca699b54c2288801b800ceec57a41ffa39a9174f96f10a1"},"schema_version":"1.0","source":{"id":"2505.06169","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06169","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06169v1","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06169","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"pith_short_12","alias_value":"3RAFHSEXNBVB","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"pith_short_16","alias_value":"3RAFHSEXNBVBMAWD","created_at":"2026-07-05T11:00:55Z"},{"alias_kind":"pith_short_8","alias_value":"3RAFHSEX","created_at":"2026-07-05T11:00:55Z"}],"graph_snapshots":[{"event_id":"sha256:aeb5cc3ddaf8541fb40fb8d85e8041940977225cabe77f3aecb208d8f5e833bf","target":"graph","created_at":"2026-07-05T11:00:55Z","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/2505.06169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study two models of ReLU neural networks: monotone networks (ReLU$^+$) and input convex neural networks (ICNN). Our focus is on expressivity, mostly in terms of depth, and we prove the following lower bounds. For the maximum function MAX$_n$ computing the maximum of $n$ real numbers, we show that ReLU$^+$ networks cannot compute MAX$_n$, or even approximate it. We prove a sharp $n$ lower bound on the ICNN depth complexity of MAX$_n$. We also prove depth separations between ReLU networks and ICNNs; for every $k$, there is a depth-2 ReLU network of size $O(k^2)$ that cannot be simulated by a ","authors_text":"Amir Yehudayoff, Christoph Hertrich, Daniel Reichman, Egor Bakaev, Florestan Brunck","cross_cats":["cs.DM","cs.NE","math.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T16:19:34Z","title":"On the Depth of Monotone ReLU Neural Networks and ICNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06169","kind":"arxiv","version":1},"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:e1528df5fe8f5dd736555fa0d01bbc49770bcae372032c8913b71a0e9995e3fd","target":"record","created_at":"2026-07-05T11:00:55Z","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":"ab78d4d11fe6e096e949cff0798ee6e85a5847351626e1a997b2e8bfb00c1a7e","cross_cats_sorted":["cs.DM","cs.NE","math.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-09T16:19:34Z","title_canon_sha256":"c81e6b1f4ec8f3122ca699b54c2288801b800ceec57a41ffa39a9174f96f10a1"},"schema_version":"1.0","source":{"id":"2505.06169","kind":"arxiv","version":1}},"canonical_sha256":"dc4053c897686a1602c382fcba83c4e894df55a33e4c6375ae7ae059eda45394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc4053c897686a1602c382fcba83c4e894df55a33e4c6375ae7ae059eda45394","first_computed_at":"2026-07-05T11:00:55.278797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:55.278797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j0eoaNhI3/84yy92wahOaodETj9zpsPNdKmCq/1m41puzaUDU6zoFQN2F58FxomIDm79PQaQxNdl1Wtrty05Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:55.279296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06169","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1528df5fe8f5dd736555fa0d01bbc49770bcae372032c8913b71a0e9995e3fd","sha256:aeb5cc3ddaf8541fb40fb8d85e8041940977225cabe77f3aecb208d8f5e833bf"],"state_sha256":"bd6494678cfdefa368b8e679f3ce8e96df7af526495319d1b84e4a7edc858e0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fnJVYxoO93pE81hMX0T+wqKqjBxjdHVTb2Lea2UOJmxF7XMJlUt+AKX/C8BpV9fzxlKX0Dkq+GfAziTtaQ7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:00:55.596073Z","bundle_sha256":"482af0647b35a0b1cd7402543eb19ee781fdd65a21317aae3606878de79598f5"}}