{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IOODR5OTRFDDOXPNFGKW4JKRU3","short_pith_number":"pith:IOODR5OT","canonical_record":{"source":{"id":"2205.11716","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T01:38:43Z","cross_cats_sorted":["math.PR","stat.ML"],"title_canon_sha256":"5b04649662440adb253e0b5038743b8fca38b1c7ceb4c9199111da1c4808878e","abstract_canon_sha256":"2f9a6a0876520f228863143d8a5a201ba30d7f6f5a5228bbaa92a7d97c6e2820"},"schema_version":"1.0"},"canonical_sha256":"439c38f5d38946375ded29956e2551a6cc6749eb20b4c7c0671337c0f52addf0","source":{"kind":"arxiv","id":"2205.11716","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11716","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11716v2","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11716","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"pith_short_12","alias_value":"IOODR5OTRFDD","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"pith_short_16","alias_value":"IOODR5OTRFDDOXPN","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"pith_short_8","alias_value":"IOODR5OT","created_at":"2026-07-05T06:58:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IOODR5OTRFDDOXPNFGKW4JKRU3","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11716","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T01:38:43Z","cross_cats_sorted":["math.PR","stat.ML"],"title_canon_sha256":"5b04649662440adb253e0b5038743b8fca38b1c7ceb4c9199111da1c4808878e","abstract_canon_sha256":"2f9a6a0876520f228863143d8a5a201ba30d7f6f5a5228bbaa92a7d97c6e2820"},"schema_version":"1.0"},"canonical_sha256":"439c38f5d38946375ded29956e2551a6cc6749eb20b4c7c0671337c0f52addf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:04.997347Z","signature_b64":"MiBESEm9zwookXFCBDrNvbzsOPpo6qxdEC2VStRfJk8cCdyONGn0K/5ah+4wLN8HXPpJtDEws+Hboqi4hNvyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"439c38f5d38946375ded29956e2551a6cc6749eb20b4c7c0671337c0f52addf0","last_reissued_at":"2026-07-05T06:58:04.996870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:04.996870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11716","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":"2026-07-05T06:58:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1R0p5HNH7HUbFb6/hOnTHA2neJJYpAZDwCfat77GNhSRxYoFy+k6JWxHnHMFrYm0sSa5DILDy53OoWSTC04RDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:27:31.811698Z"},"content_sha256":"ba11df032a3354498714a70a3d42d0e3a62183550a0850b3603c1b005d580e28","schema_version":"1.0","event_id":"sha256:ba11df032a3354498714a70a3d42d0e3a62183550a0850b3603c1b005d580e28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IOODR5OTRFDDOXPNFGKW4JKRU3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Promit Ghosal, Srinath Mahankali, Yihang Sun","submitted_at":"2022-05-24T01:38:43Z","abstract_excerpt":"Recently, neural networks have demonstrated remarkable capabilities in mapping two arbitrary sets to two linearly separable sets. The prospect of achieving this with randomly initialized neural networks is particularly appealing due to the computational efficiency compared to fully trained networks. This paper contributes by establishing that, given sufficient width, a randomly initialized one-layer neural network can, with high probability, transform two sets into two linearly separable sets without any training. Moreover, we furnish precise bounds on the necessary width of the neural network"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11716","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/2205.11716/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":"2026-07-05T06:58:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lRdOxuJ2xgLgWCTzHGqMSkYKwCI2LKLJNRK0ZNOFj4gshoJmLNhjYZTqn/iNkUpCUz7pZcyhowAxHsnJ/8F+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:27:31.812431Z"},"content_sha256":"bf8208d54113a6fc9e6a8061f54f5660dd7fe4516d08d3cc1680dd238bcbf666","schema_version":"1.0","event_id":"sha256:bf8208d54113a6fc9e6a8061f54f5660dd7fe4516d08d3cc1680dd238bcbf666"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOODR5OTRFDDOXPNFGKW4JKRU3/bundle.json","state_url":"https://pith.science/pith/IOODR5OTRFDDOXPNFGKW4JKRU3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOODR5OTRFDDOXPNFGKW4JKRU3/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":"2026-08-10T18:27:31Z","links":{"resolver":"https://pith.science/pith/IOODR5OTRFDDOXPNFGKW4JKRU3","bundle":"https://pith.science/pith/IOODR5OTRFDDOXPNFGKW4JKRU3/bundle.json","state":"https://pith.science/pith/IOODR5OTRFDDOXPNFGKW4JKRU3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOODR5OTRFDDOXPNFGKW4JKRU3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IOODR5OTRFDDOXPNFGKW4JKRU3","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":"2f9a6a0876520f228863143d8a5a201ba30d7f6f5a5228bbaa92a7d97c6e2820","cross_cats_sorted":["math.PR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T01:38:43Z","title_canon_sha256":"5b04649662440adb253e0b5038743b8fca38b1c7ceb4c9199111da1c4808878e"},"schema_version":"1.0","source":{"id":"2205.11716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11716","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11716v2","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11716","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"pith_short_12","alias_value":"IOODR5OTRFDD","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"pith_short_16","alias_value":"IOODR5OTRFDDOXPN","created_at":"2026-07-05T06:58:04Z"},{"alias_kind":"pith_short_8","alias_value":"IOODR5OT","created_at":"2026-07-05T06:58:04Z"}],"graph_snapshots":[{"event_id":"sha256:bf8208d54113a6fc9e6a8061f54f5660dd7fe4516d08d3cc1680dd238bcbf666","target":"graph","created_at":"2026-07-05T06:58:04Z","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/2205.11716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, neural networks have demonstrated remarkable capabilities in mapping two arbitrary sets to two linearly separable sets. The prospect of achieving this with randomly initialized neural networks is particularly appealing due to the computational efficiency compared to fully trained networks. This paper contributes by establishing that, given sufficient width, a randomly initialized one-layer neural network can, with high probability, transform two sets into two linearly separable sets without any training. Moreover, we furnish precise bounds on the necessary width of the neural network","authors_text":"Promit Ghosal, Srinath Mahankali, Yihang Sun","cross_cats":["math.PR","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T01:38:43Z","title":"Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11716","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:ba11df032a3354498714a70a3d42d0e3a62183550a0850b3603c1b005d580e28","target":"record","created_at":"2026-07-05T06:58:04Z","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":"2f9a6a0876520f228863143d8a5a201ba30d7f6f5a5228bbaa92a7d97c6e2820","cross_cats_sorted":["math.PR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T01:38:43Z","title_canon_sha256":"5b04649662440adb253e0b5038743b8fca38b1c7ceb4c9199111da1c4808878e"},"schema_version":"1.0","source":{"id":"2205.11716","kind":"arxiv","version":2}},"canonical_sha256":"439c38f5d38946375ded29956e2551a6cc6749eb20b4c7c0671337c0f52addf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"439c38f5d38946375ded29956e2551a6cc6749eb20b4c7c0671337c0f52addf0","first_computed_at":"2026-07-05T06:58:04.996870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:04.996870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MiBESEm9zwookXFCBDrNvbzsOPpo6qxdEC2VStRfJk8cCdyONGn0K/5ah+4wLN8HXPpJtDEws+Hboqi4hNvyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:04.997347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba11df032a3354498714a70a3d42d0e3a62183550a0850b3603c1b005d580e28","sha256:bf8208d54113a6fc9e6a8061f54f5660dd7fe4516d08d3cc1680dd238bcbf666"],"state_sha256":"56486d3352258062d03927f54319029c96923a008a911bb95bdbfa844633b8fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n55wkFAMGO5bwNdgMif4x8SYoWvgAkInNAFgEYBiHiDdzzhQR3hAdXtCvStf8B/T6zJeSVefPVNW5cCbhnrZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:27:31.818138Z","bundle_sha256":"8c5be1f32f48436bd8a66247679a0063359ea6d6045cfa1d51b915d1adf89bcd"}}