{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZDR4OR4BXTXOCTL2VZUYRLMDGE","short_pith_number":"pith:ZDR4OR4B","canonical_record":{"source":{"id":"1710.07535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-19T16:04:05Z","cross_cats_sorted":[],"title_canon_sha256":"4807c2f75e92d247f9e2d56b4930118fd531604f6395e045a55a7faae457e79e","abstract_canon_sha256":"9d140b335a84b701a3e52c37aaae73f31f367334d415244a223a1f2ee48b4c71"},"schema_version":"1.0"},"canonical_sha256":"c8e3c74781bceee14d7aae6988ad833115741c3914e75b892d8b8476d9475cf6","source":{"kind":"arxiv","id":"1710.07535","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.07535","created_at":"2026-05-18T00:29:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.07535v2","created_at":"2026-05-18T00:29:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07535","created_at":"2026-05-18T00:29:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZDR4OR4BXTXO","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZDR4OR4BXTXOCTL2","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZDR4OR4B","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZDR4OR4BXTXOCTL2VZUYRLMDGE","target":"record","payload":{"canonical_record":{"source":{"id":"1710.07535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-19T16:04:05Z","cross_cats_sorted":[],"title_canon_sha256":"4807c2f75e92d247f9e2d56b4930118fd531604f6395e045a55a7faae457e79e","abstract_canon_sha256":"9d140b335a84b701a3e52c37aaae73f31f367334d415244a223a1f2ee48b4c71"},"schema_version":"1.0"},"canonical_sha256":"c8e3c74781bceee14d7aae6988ad833115741c3914e75b892d8b8476d9475cf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:45.405632Z","signature_b64":"lfhh7tJZqARgDD5umLLGmcjRH17xXv1efni3CB7ro7s1bMRoUnlvPcyOEBCUKIn0ASh0zZN8zmMwFP+4mSMPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e3c74781bceee14d7aae6988ad833115741c3914e75b892d8b8476d9475cf6","last_reissued_at":"2026-05-18T00:29:45.404915Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:45.404915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.07535","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":"2026-05-18T00:29:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WyZksCXxWSiFjx9FoGyn92KfHfUUsb/ygzm6LDGX/tfMCAUJUjb1ZqqI9/KosCc3adq2JoUQ7+4J+ju0R/HICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:37:37.788477Z"},"content_sha256":"b666b4ad68c0f6854cb34c06e0c4e3b34369ecbc662af158229b9854f9be7d53","schema_version":"1.0","event_id":"sha256:b666b4ad68c0f6854cb34c06e0c4e3b34369ecbc662af158229b9854f9be7d53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZDR4OR4BXTXOCTL2VZUYRLMDGE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Free Knowledge Distillation for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Raphael Gontijo Lopes, Stefano Fenu, Thad Starner","submitted_at":"2017-10-19T16:04:05Z","abstract_excerpt":"Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to the original training set, which might not always be possible if the network to be compressed was trained on a very large dataset, or on a dataset whose release poses privacy or safety concerns as may be the case for biometrics tasks. We present a method for data-free knowledge distillation, which is able to compress deep neural networks trained on large-scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07535","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":""},"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":"2026-05-18T00:29:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9cF8mw0TYQgd5iIMsvCocrtvZWi/h3VphWR6qnNIkas6OWpm5l5nHddwF94VRCNT/6+9Bg03wsFiUDBX2+mbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:37:37.789202Z"},"content_sha256":"2c99f4cbcc6d70d0d88f9a4c860661e89f0c17c484debff6850e33bb0fb34458","schema_version":"1.0","event_id":"sha256:2c99f4cbcc6d70d0d88f9a4c860661e89f0c17c484debff6850e33bb0fb34458"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE/bundle.json","state_url":"https://pith.science/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE/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":"2026-05-30T10:37:37Z","links":{"resolver":"https://pith.science/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE","bundle":"https://pith.science/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE/bundle.json","state":"https://pith.science/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDR4OR4BXTXOCTL2VZUYRLMDGE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZDR4OR4BXTXOCTL2VZUYRLMDGE","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":"9d140b335a84b701a3e52c37aaae73f31f367334d415244a223a1f2ee48b4c71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-19T16:04:05Z","title_canon_sha256":"4807c2f75e92d247f9e2d56b4930118fd531604f6395e045a55a7faae457e79e"},"schema_version":"1.0","source":{"id":"1710.07535","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.07535","created_at":"2026-05-18T00:29:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.07535v2","created_at":"2026-05-18T00:29:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07535","created_at":"2026-05-18T00:29:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZDR4OR4BXTXO","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZDR4OR4BXTXOCTL2","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZDR4OR4B","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:2c99f4cbcc6d70d0d88f9a4c860661e89f0c17c484debff6850e33bb0fb34458","target":"graph","created_at":"2026-05-18T00:29:45Z","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":"Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to the original training set, which might not always be possible if the network to be compressed was trained on a very large dataset, or on a dataset whose release poses privacy or safety concerns as may be the case for biometrics tasks. We present a method for data-free knowledge distillation, which is able to compress deep neural networks trained on large-scal","authors_text":"Raphael Gontijo Lopes, Stefano Fenu, Thad Starner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-19T16:04:05Z","title":"Data-Free Knowledge Distillation for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07535","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:b666b4ad68c0f6854cb34c06e0c4e3b34369ecbc662af158229b9854f9be7d53","target":"record","created_at":"2026-05-18T00:29:45Z","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":"9d140b335a84b701a3e52c37aaae73f31f367334d415244a223a1f2ee48b4c71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-19T16:04:05Z","title_canon_sha256":"4807c2f75e92d247f9e2d56b4930118fd531604f6395e045a55a7faae457e79e"},"schema_version":"1.0","source":{"id":"1710.07535","kind":"arxiv","version":2}},"canonical_sha256":"c8e3c74781bceee14d7aae6988ad833115741c3914e75b892d8b8476d9475cf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8e3c74781bceee14d7aae6988ad833115741c3914e75b892d8b8476d9475cf6","first_computed_at":"2026-05-18T00:29:45.404915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:45.404915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lfhh7tJZqARgDD5umLLGmcjRH17xXv1efni3CB7ro7s1bMRoUnlvPcyOEBCUKIn0ASh0zZN8zmMwFP+4mSMPCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:45.405632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.07535","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b666b4ad68c0f6854cb34c06e0c4e3b34369ecbc662af158229b9854f9be7d53","sha256:2c99f4cbcc6d70d0d88f9a4c860661e89f0c17c484debff6850e33bb0fb34458"],"state_sha256":"c8013552edcbcb49de2cccc7b3f5aab2f78d95ffd483384e17b76e7b76d8e797"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z5Eq3u3yGNJF1OvyYpCDqcrQSCqm/yDTkkHd+YuAUExMl8CIvMII1r2Yzu5VVhYs7UO75OgzPG/ym5KnM5cADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T10:37:37.792728Z","bundle_sha256":"9b94f3c5990a6a7accbe40269a4adfa79d6374e38621db5ed79dc6a6bd4695f1"}}