{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:ZLE4FHBKFF4HCIXBVPAAKE2Y2O","short_pith_number":"pith:ZLE4FHBK","canonical_record":{"source":{"id":"1412.7149","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-22T20:53:30Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"0cf6471a77eb322f5b1aef0fc5430173238ca1e2412d1d9242d810486653be04","abstract_canon_sha256":"9ac2247daeee8a3434e39295732c997f09964d9a6573c5ce781d118d19a01f3b"},"schema_version":"1.0"},"canonical_sha256":"cac9c29c2a29787122e1abc0051358d38807e34e5676429fab21fe8e02ab14a6","source":{"kind":"arxiv","id":"1412.7149","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.7149","created_at":"2026-05-18T01:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"1412.7149v4","created_at":"2026-05-18T01:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.7149","created_at":"2026-05-18T01:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZLE4FHBKFF4H","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZLE4FHBKFF4HCIXB","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZLE4FHBK","created_at":"2026-05-18T12:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:ZLE4FHBKFF4HCIXBVPAAKE2Y2O","target":"record","payload":{"canonical_record":{"source":{"id":"1412.7149","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-22T20:53:30Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"0cf6471a77eb322f5b1aef0fc5430173238ca1e2412d1d9242d810486653be04","abstract_canon_sha256":"9ac2247daeee8a3434e39295732c997f09964d9a6573c5ce781d118d19a01f3b"},"schema_version":"1.0"},"canonical_sha256":"cac9c29c2a29787122e1abc0051358d38807e34e5676429fab21fe8e02ab14a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:41.655679Z","signature_b64":"hlCP2/sYb9I9E/M3N02YJ6xrHmuD0EWRk92NZlLbDr+wVKmrXlP86/qvWg7CyiDSG8+zzxBE5Ht4Ne4R8Qe6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cac9c29c2a29787122e1abc0051358d38807e34e5676429fab21fe8e02ab14a6","last_reissued_at":"2026-05-18T01:36:41.655055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:41.655055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.7149","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:36:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U23SQaUKB5VBpzk2CawIejkCyhIMveukmNk9d8o1ytKWd/eTl7bJ9JOqyedgrAyWWG1aGMjYRAubZdk+/qfhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T22:37:47.946139Z"},"content_sha256":"92ccf8cb7e7ea3461f3eb8b6450b2ddb51321672738b954725959f195c719147","schema_version":"1.0","event_id":"sha256:92ccf8cb7e7ea3461f3eb8b6450b2ddb51321672738b954725959f195c719147"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:ZLE4FHBKFF4HCIXBVPAAKE2Y2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Fried Convnets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Smola, Le Song, Marcin Moczulski, Misha Denil, Nando de Freitas, Zichao Yang, Ziyu Wang","submitted_at":"2014-12-22T20:53:30Z","abstract_excerpt":"The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important for operating deep neural networks in memory constrained environments such as GPUs or embedded devices.\n  In this paper we show how kernel methods, in particular a single Fastfood layer, can be used to replace all fully connected layers in a deep convolutional neural network. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.7149","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T01:36:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nDm08WMlOxGQSob/JU5L1IomTmRNKx/y4La3a8GpNW0eqQp4I5um9h1OAD13+sfnsArSaJUDNvvqIIGnY+OJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T22:37:47.946835Z"},"content_sha256":"fa09d7d165893fb9063e1281ac412d93e7df6b0eb1f99a9555a878bf1ae1e280","schema_version":"1.0","event_id":"sha256:fa09d7d165893fb9063e1281ac412d93e7df6b0eb1f99a9555a878bf1ae1e280"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O/bundle.json","state_url":"https://pith.science/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O/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":"2026-05-18T22:37:47Z","links":{"resolver":"https://pith.science/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O","bundle":"https://pith.science/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O/bundle.json","state":"https://pith.science/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLE4FHBKFF4HCIXBVPAAKE2Y2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:ZLE4FHBKFF4HCIXBVPAAKE2Y2O","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":"9ac2247daeee8a3434e39295732c997f09964d9a6573c5ce781d118d19a01f3b","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-22T20:53:30Z","title_canon_sha256":"0cf6471a77eb322f5b1aef0fc5430173238ca1e2412d1d9242d810486653be04"},"schema_version":"1.0","source":{"id":"1412.7149","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.7149","created_at":"2026-05-18T01:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"1412.7149v4","created_at":"2026-05-18T01:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.7149","created_at":"2026-05-18T01:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZLE4FHBKFF4H","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZLE4FHBKFF4HCIXB","created_at":"2026-05-18T12:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZLE4FHBK","created_at":"2026-05-18T12:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:fa09d7d165893fb9063e1281ac412d93e7df6b0eb1f99a9555a878bf1ae1e280","target":"graph","created_at":"2026-05-18T01:36:41Z","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"},"paper":{"abstract_excerpt":"The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important for operating deep neural networks in memory constrained environments such as GPUs or embedded devices.\n  In this paper we show how kernel methods, in particular a single Fastfood layer, can be used to replace all fully connected layers in a deep convolutional neural network. Thi","authors_text":"Alex Smola, Le Song, Marcin Moczulski, Misha Denil, Nando de Freitas, Zichao Yang, Ziyu Wang","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-22T20:53:30Z","title":"Deep Fried Convnets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.7149","kind":"arxiv","version":4},"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":"sha256:92ccf8cb7e7ea3461f3eb8b6450b2ddb51321672738b954725959f195c719147","target":"record","created_at":"2026-05-18T01:36:41Z","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":"9ac2247daeee8a3434e39295732c997f09964d9a6573c5ce781d118d19a01f3b","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-22T20:53:30Z","title_canon_sha256":"0cf6471a77eb322f5b1aef0fc5430173238ca1e2412d1d9242d810486653be04"},"schema_version":"1.0","source":{"id":"1412.7149","kind":"arxiv","version":4}},"canonical_sha256":"cac9c29c2a29787122e1abc0051358d38807e34e5676429fab21fe8e02ab14a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cac9c29c2a29787122e1abc0051358d38807e34e5676429fab21fe8e02ab14a6","first_computed_at":"2026-05-18T01:36:41.655055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:41.655055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hlCP2/sYb9I9E/M3N02YJ6xrHmuD0EWRk92NZlLbDr+wVKmrXlP86/qvWg7CyiDSG8+zzxBE5Ht4Ne4R8Qe6BA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:41.655679Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.7149","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92ccf8cb7e7ea3461f3eb8b6450b2ddb51321672738b954725959f195c719147","sha256:fa09d7d165893fb9063e1281ac412d93e7df6b0eb1f99a9555a878bf1ae1e280"],"state_sha256":"bb19a5c54d081732a36b1e3e75600d93a6643bd291e39b7ce7bac1360912a8b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGavpvexbQ48MkyO8o0T9cv/xuOSOKsg8XQfC2mqjsaHygI6HZKikd7uBxEFHsBGl8GYiQFc5Qkhfr/MCV8XCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T22:37:47.949020Z","bundle_sha256":"e868bdcddce25de439be20323f32fec988b42b40e7e5cc0cd87d7379803fa34e"}}