{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FAPU6H7I42I664XC4KSXNEGDDT","short_pith_number":"pith:FAPU6H7I","canonical_record":{"source":{"id":"1812.02425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T09:48:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"085f15d80273e74c96cf6dc9cae104e047febd33aba1e9f7423a6655e8bd102c","abstract_canon_sha256":"c86c0204341e499dc3a0d6052c519bc15970e7903425f2a7eb700c36cf0c78bd"},"schema_version":"1.0"},"canonical_sha256":"281f4f1fe8e691ef72e2e2a57690c31cc419a79baba144489bd3df634baf63a6","source":{"kind":"arxiv","id":"1812.02425","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02425","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02425v2","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02425","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"FAPU6H7I42I6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FAPU6H7I42I664XC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FAPU6H7I","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FAPU6H7I42I664XC4KSXNEGDDT","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T09:48:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"085f15d80273e74c96cf6dc9cae104e047febd33aba1e9f7423a6655e8bd102c","abstract_canon_sha256":"c86c0204341e499dc3a0d6052c519bc15970e7903425f2a7eb700c36cf0c78bd"},"schema_version":"1.0"},"canonical_sha256":"281f4f1fe8e691ef72e2e2a57690c31cc419a79baba144489bd3df634baf63a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:37.006560Z","signature_b64":"xan661AJSxQZej14ZY3GqkCQnm7tLKTB39sSBgZKNX+qo7dVSmdj7AkkVsYmCtMF1yvp5Orh4+7XnEz0gmdoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"281f4f1fe8e691ef72e2e2a57690c31cc419a79baba144489bd3df634baf63a6","last_reissued_at":"2026-05-17T23:39:37.006030Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:37.006030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02425","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":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pyIIJau3H5FiTGI4joCfEUCEBk4xMtNcAP238jvG7DdqJwEBvW8l1h7qckiYes6A/P+bcu/yXfCUZJ16jXc2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:29:41.553252Z"},"content_sha256":"b1c14d8c00649ce9e0a4cf311b75a82d7c170dd579829ebfc2fc17fe5a03c86b","schema_version":"1.0","event_id":"sha256:b1c14d8c00649ce9e0a4cf311b75a82d7c170dd579829ebfc2fc17fe5a03c86b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FAPU6H7I42I664XC4KSXNEGDDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MEAL: Multi-Model Ensemble via Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Xiangyang Xue, Zhankui He, Zhiqiang Shen","submitted_at":"2018-12-06T09:48:49Z","abstract_excerpt":"Often the best performing deep neural models are ensembles of multiple base-level networks. Unfortunately, the space required to store these many networks, and the time required to execute them at test-time, prohibits their use in applications where test sets are large (e.g., ImageNet). In this paper, we present a method for compressing large, complex trained ensembles into a single network, where knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN. In order to distill diverse knowledge from different trained (teacher) models, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02425","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":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2VEcGCqoOXqSIK5D9HUNoQCcE4Ys0asSNBzLfHcD/VLmdAKJuxXtFXzKy5PRubpywZcjd7mRZ/96Q9n91iQyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:29:41.553647Z"},"content_sha256":"f3f39e365261c7a415b941b6a42fb5694a63c83b7ba294303414214534391e90","schema_version":"1.0","event_id":"sha256:f3f39e365261c7a415b941b6a42fb5694a63c83b7ba294303414214534391e90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAPU6H7I42I664XC4KSXNEGDDT/bundle.json","state_url":"https://pith.science/pith/FAPU6H7I42I664XC4KSXNEGDDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAPU6H7I42I664XC4KSXNEGDDT/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":"2026-05-31T00:29:41Z","links":{"resolver":"https://pith.science/pith/FAPU6H7I42I664XC4KSXNEGDDT","bundle":"https://pith.science/pith/FAPU6H7I42I664XC4KSXNEGDDT/bundle.json","state":"https://pith.science/pith/FAPU6H7I42I664XC4KSXNEGDDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAPU6H7I42I664XC4KSXNEGDDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FAPU6H7I42I664XC4KSXNEGDDT","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":"c86c0204341e499dc3a0d6052c519bc15970e7903425f2a7eb700c36cf0c78bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T09:48:49Z","title_canon_sha256":"085f15d80273e74c96cf6dc9cae104e047febd33aba1e9f7423a6655e8bd102c"},"schema_version":"1.0","source":{"id":"1812.02425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02425","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02425v2","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02425","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"FAPU6H7I42I6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FAPU6H7I42I664XC","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FAPU6H7I","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:f3f39e365261c7a415b941b6a42fb5694a63c83b7ba294303414214534391e90","target":"graph","created_at":"2026-05-17T23:39:37Z","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":"Often the best performing deep neural models are ensembles of multiple base-level networks. Unfortunately, the space required to store these many networks, and the time required to execute them at test-time, prohibits their use in applications where test sets are large (e.g., ImageNet). In this paper, we present a method for compressing large, complex trained ensembles into a single network, where knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN. In order to distill diverse knowledge from different trained (teacher) models, we propose","authors_text":"Xiangyang Xue, Zhankui He, Zhiqiang Shen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T09:48:49Z","title":"MEAL: Multi-Model Ensemble via Adversarial Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02425","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:b1c14d8c00649ce9e0a4cf311b75a82d7c170dd579829ebfc2fc17fe5a03c86b","target":"record","created_at":"2026-05-17T23:39:37Z","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":"c86c0204341e499dc3a0d6052c519bc15970e7903425f2a7eb700c36cf0c78bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T09:48:49Z","title_canon_sha256":"085f15d80273e74c96cf6dc9cae104e047febd33aba1e9f7423a6655e8bd102c"},"schema_version":"1.0","source":{"id":"1812.02425","kind":"arxiv","version":2}},"canonical_sha256":"281f4f1fe8e691ef72e2e2a57690c31cc419a79baba144489bd3df634baf63a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"281f4f1fe8e691ef72e2e2a57690c31cc419a79baba144489bd3df634baf63a6","first_computed_at":"2026-05-17T23:39:37.006030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:37.006030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xan661AJSxQZej14ZY3GqkCQnm7tLKTB39sSBgZKNX+qo7dVSmdj7AkkVsYmCtMF1yvp5Orh4+7XnEz0gmdoCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:37.006560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1c14d8c00649ce9e0a4cf311b75a82d7c170dd579829ebfc2fc17fe5a03c86b","sha256:f3f39e365261c7a415b941b6a42fb5694a63c83b7ba294303414214534391e90"],"state_sha256":"af5c958dcade0c0bfbd655208bea059d06c753dccd1eb1f505d9254a5ace5502"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QVgaQ/nUpIOAL/ViQQdEheENTn0oMQiJHXegplHxdC4l6BgFtWXwd50YHKKJL16bcMBtShuJ/dbXv5zvFMcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T00:29:41.555915Z","bundle_sha256":"af53c91e7d6666c51f8be8d5e9a990a5680d437110004baa2191f288252cad60"}}