{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6TBTJB4Q5RDF5OPQH7AQAYK2DS","short_pith_number":"pith:6TBTJB4Q","canonical_record":{"source":{"id":"1510.02437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-08T18:40:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f7cebfb2f9c66bae1bf0008b48896b705880577d9e127c952c4fafed4e4ef40","abstract_canon_sha256":"c4e4be3be000b91a6108173bf55d6132185dd4c5123b197b4c544d3834d6b40e"},"schema_version":"1.0"},"canonical_sha256":"f4c3348790ec465eb9f03fc100615a1cbc5f9835d3db6ac67505964ea73506c4","source":{"kind":"arxiv","id":"1510.02437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.02437","created_at":"2026-05-18T01:30:43Z"},{"alias_kind":"arxiv_version","alias_value":"1510.02437v1","created_at":"2026-05-18T01:30:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.02437","created_at":"2026-05-18T01:30:43Z"},{"alias_kind":"pith_short_12","alias_value":"6TBTJB4Q5RDF","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6TBTJB4Q5RDF5OPQ","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6TBTJB4Q","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6TBTJB4Q5RDF5OPQH7AQAYK2DS","target":"record","payload":{"canonical_record":{"source":{"id":"1510.02437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-08T18:40:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f7cebfb2f9c66bae1bf0008b48896b705880577d9e127c952c4fafed4e4ef40","abstract_canon_sha256":"c4e4be3be000b91a6108173bf55d6132185dd4c5123b197b4c544d3834d6b40e"},"schema_version":"1.0"},"canonical_sha256":"f4c3348790ec465eb9f03fc100615a1cbc5f9835d3db6ac67505964ea73506c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:30:43.744145Z","signature_b64":"cdw/5OAI1tUqgaxCoE1suXPAhl5Wh1OZISAgmnk+s6MfoLG4+iGno0QzYaTf97tCDK+LKtA4QBz1RIYgnjbMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4c3348790ec465eb9f03fc100615a1cbc5f9835d3db6ac67505964ea73506c4","last_reissued_at":"2026-05-18T01:30:43.742230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:30:43.742230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1510.02437","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":"2026-05-18T01:30:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nm01iAUCaGssZVZ0YziwIkMHz0MhLErlW4Dmb6vWHpmDN8VTWaTXCQzW7q6TXBnFoZ6pz2LRDXKXIcwbHh32BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:24:50.433668Z"},"content_sha256":"1c38e82f45124b914fbef698cc99b3e0474368cab791a78790eab03dfc284bc9","schema_version":"1.0","event_id":"sha256:1c38e82f45124b914fbef698cc99b3e0474368cab791a78790eab03dfc284bc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6TBTJB4Q5RDF5OPQH7AQAYK2DS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Model Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"George Papamakarios","submitted_at":"2015-10-08T18:40:50Z","abstract_excerpt":"Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like to replace such cumbersome models with simpler models that perform equally well.\n  In this thesis, we study knowledge distillation, the idea of extracting the knowledge contained in a complex model and injecting it into a more convenient model. We present a general framework for knowledge distillation, whereby a convenient model of our choosing learns how t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.02437","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":""},"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":"2026-05-18T01:30:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRJGFyGo/2r8hL32L04U/iNgPHcnavMaaJpS+Lg1RpovfYdD57Npv53ACU9IPTPkFPHPVE6KAUjZFANh37sXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:24:50.434405Z"},"content_sha256":"02e51b86cf99b4e1dd2e1ad6c7c44314a430c920be6cb921e416a69d4ed7fa52","schema_version":"1.0","event_id":"sha256:02e51b86cf99b4e1dd2e1ad6c7c44314a430c920be6cb921e416a69d4ed7fa52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS/bundle.json","state_url":"https://pith.science/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS/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":"2026-05-27T09:24:50Z","links":{"resolver":"https://pith.science/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS","bundle":"https://pith.science/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS/bundle.json","state":"https://pith.science/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TBTJB4Q5RDF5OPQH7AQAYK2DS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6TBTJB4Q5RDF5OPQH7AQAYK2DS","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":"c4e4be3be000b91a6108173bf55d6132185dd4c5123b197b4c544d3834d6b40e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-08T18:40:50Z","title_canon_sha256":"0f7cebfb2f9c66bae1bf0008b48896b705880577d9e127c952c4fafed4e4ef40"},"schema_version":"1.0","source":{"id":"1510.02437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.02437","created_at":"2026-05-18T01:30:43Z"},{"alias_kind":"arxiv_version","alias_value":"1510.02437v1","created_at":"2026-05-18T01:30:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.02437","created_at":"2026-05-18T01:30:43Z"},{"alias_kind":"pith_short_12","alias_value":"6TBTJB4Q5RDF","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6TBTJB4Q5RDF5OPQ","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6TBTJB4Q","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:02e51b86cf99b4e1dd2e1ad6c7c44314a430c920be6cb921e416a69d4ed7fa52","target":"graph","created_at":"2026-05-18T01:30:43Z","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":"Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like to replace such cumbersome models with simpler models that perform equally well.\n  In this thesis, we study knowledge distillation, the idea of extracting the knowledge contained in a complex model and injecting it into a more convenient model. We present a general framework for knowledge distillation, whereby a convenient model of our choosing learns how t","authors_text":"George Papamakarios","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-08T18:40:50Z","title":"Distilling Model Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.02437","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":"sha256:1c38e82f45124b914fbef698cc99b3e0474368cab791a78790eab03dfc284bc9","target":"record","created_at":"2026-05-18T01:30:43Z","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":"c4e4be3be000b91a6108173bf55d6132185dd4c5123b197b4c544d3834d6b40e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-10-08T18:40:50Z","title_canon_sha256":"0f7cebfb2f9c66bae1bf0008b48896b705880577d9e127c952c4fafed4e4ef40"},"schema_version":"1.0","source":{"id":"1510.02437","kind":"arxiv","version":1}},"canonical_sha256":"f4c3348790ec465eb9f03fc100615a1cbc5f9835d3db6ac67505964ea73506c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4c3348790ec465eb9f03fc100615a1cbc5f9835d3db6ac67505964ea73506c4","first_computed_at":"2026-05-18T01:30:43.742230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:30:43.742230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cdw/5OAI1tUqgaxCoE1suXPAhl5Wh1OZISAgmnk+s6MfoLG4+iGno0QzYaTf97tCDK+LKtA4QBz1RIYgnjbMDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:30:43.744145Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.02437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c38e82f45124b914fbef698cc99b3e0474368cab791a78790eab03dfc284bc9","sha256:02e51b86cf99b4e1dd2e1ad6c7c44314a430c920be6cb921e416a69d4ed7fa52"],"state_sha256":"6dead56e12e256fabac70dc91eaf64bf8ce3aee5d30c64192827613d2fade155"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXo0dSMbrEVPquu0f61rCrn9mmijd6gjJ+1ygHhkebHd/yGNQwTI676JnuIG2/1Zp4hRWNjhncfohcBHAAhICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T09:24:50.438645Z","bundle_sha256":"90c94321e5610335ef41d8ea2e8e09b410c2468ac900de09d01c14c8221b847a"}}