{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NJTSJ7XWIXAYRDU3E6RTM5SJUU","short_pith_number":"pith:NJTSJ7XW","canonical_record":{"source":{"id":"2309.09571","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T08:30:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f08118d5257e1b4e3475325477add417134bc086664378f82b1ec8348ffbb4e1","abstract_canon_sha256":"cc3bb134bbebbe5b8466b00cab476c82a3b5856d0ab1909c5264334f79e5587f"},"schema_version":"1.0"},"canonical_sha256":"6a6724fef645c1888e9b27a3367649a53970fa08c13b617ac4303e51fbf57a2c","source":{"kind":"arxiv","id":"2309.09571","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09571","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09571v2","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09571","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"pith_short_12","alias_value":"NJTSJ7XWIXAY","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"pith_short_16","alias_value":"NJTSJ7XWIXAYRDU3","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"pith_short_8","alias_value":"NJTSJ7XW","created_at":"2026-07-05T07:32:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NJTSJ7XWIXAYRDU3E6RTM5SJUU","target":"record","payload":{"canonical_record":{"source":{"id":"2309.09571","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T08:30:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f08118d5257e1b4e3475325477add417134bc086664378f82b1ec8348ffbb4e1","abstract_canon_sha256":"cc3bb134bbebbe5b8466b00cab476c82a3b5856d0ab1909c5264334f79e5587f"},"schema_version":"1.0"},"canonical_sha256":"6a6724fef645c1888e9b27a3367649a53970fa08c13b617ac4303e51fbf57a2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:23.483521Z","signature_b64":"ZhSLmdCdQJmMBzP+e3MkkFiPu1XwJ5HA04YJ+wZRPc49tj3YcNleDba3V2vdnDqESzwK832V+tw6wkpO0alnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a6724fef645c1888e9b27a3367649a53970fa08c13b617ac4303e51fbf57a2c","last_reissued_at":"2026-07-05T07:32:23.482970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:23.482970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.09571","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":"2026-07-05T07:32:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/2Q1pLIhfxLCVpWhGezNz8h/YpiuwVmqXg+5ouskU9MFOMaZ0gw6YHX4pSU+miQsHFmTpaieM00/rhVmaKhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:24:55.069768Z"},"content_sha256":"eb438fe438a0388cb32fe9995b5bd2432df64b03dfcccfbf2572fd14d0aa2cb0","schema_version":"1.0","event_id":"sha256:eb438fe438a0388cb32fe9995b5bd2432df64b03dfcccfbf2572fd14d0aa2cb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NJTSJ7XWIXAYRDU3E6RTM5SJUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heterogeneous Generative Knowledge Distillation with Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Jing Hao, Shumin Han, Xianbin Cao, Xiaodi Wang, Ziming Wang","submitted_at":"2023-09-18T08:30:55Z","abstract_excerpt":"Small CNN-based models usually require transferring knowledge from a large model before they are deployed in computationally resource-limited edge devices. Masked image modeling (MIM) methods achieve great success in various visual tasks but remain largely unexplored in knowledge distillation for heterogeneous deep models. The reason is mainly due to the significant discrepancy between the Transformer-based large model and the CNN-based small network. In this paper, we develop the first Heterogeneous Generative Knowledge Distillation (H-GKD) based on MIM, which can efficiently transfer knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09571","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/2309.09571/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":"2026-07-05T07:32:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e86IIjPRmJUIhDZFU0wZe+3pWl1bY6wU3kOnjWLJsj1bIfBXTBHVOzUe+9grFaCvPNVVurN215eAzH2+KsKoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:24:55.070645Z"},"content_sha256":"1fdd95806b3158b40e8847441d15270fea004a2407eb21e232e842d2d927549f","schema_version":"1.0","event_id":"sha256:1fdd95806b3158b40e8847441d15270fea004a2407eb21e232e842d2d927549f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU/bundle.json","state_url":"https://pith.science/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU/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":"2026-07-07T07:24:55Z","links":{"resolver":"https://pith.science/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU","bundle":"https://pith.science/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU/bundle.json","state":"https://pith.science/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJTSJ7XWIXAYRDU3E6RTM5SJUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NJTSJ7XWIXAYRDU3E6RTM5SJUU","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":"cc3bb134bbebbe5b8466b00cab476c82a3b5856d0ab1909c5264334f79e5587f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T08:30:55Z","title_canon_sha256":"f08118d5257e1b4e3475325477add417134bc086664378f82b1ec8348ffbb4e1"},"schema_version":"1.0","source":{"id":"2309.09571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09571","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09571v2","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09571","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"pith_short_12","alias_value":"NJTSJ7XWIXAY","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"pith_short_16","alias_value":"NJTSJ7XWIXAYRDU3","created_at":"2026-07-05T07:32:23Z"},{"alias_kind":"pith_short_8","alias_value":"NJTSJ7XW","created_at":"2026-07-05T07:32:23Z"}],"graph_snapshots":[{"event_id":"sha256:1fdd95806b3158b40e8847441d15270fea004a2407eb21e232e842d2d927549f","target":"graph","created_at":"2026-07-05T07:32:23Z","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/2309.09571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small CNN-based models usually require transferring knowledge from a large model before they are deployed in computationally resource-limited edge devices. Masked image modeling (MIM) methods achieve great success in various visual tasks but remain largely unexplored in knowledge distillation for heterogeneous deep models. The reason is mainly due to the significant discrepancy between the Transformer-based large model and the CNN-based small network. In this paper, we develop the first Heterogeneous Generative Knowledge Distillation (H-GKD) based on MIM, which can efficiently transfer knowled","authors_text":"Baochang Zhang, Jing Hao, Shumin Han, Xianbin Cao, Xiaodi Wang, Ziming Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T08:30:55Z","title":"Heterogeneous Generative Knowledge Distillation with Masked Image Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09571","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:eb438fe438a0388cb32fe9995b5bd2432df64b03dfcccfbf2572fd14d0aa2cb0","target":"record","created_at":"2026-07-05T07:32:23Z","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":"cc3bb134bbebbe5b8466b00cab476c82a3b5856d0ab1909c5264334f79e5587f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T08:30:55Z","title_canon_sha256":"f08118d5257e1b4e3475325477add417134bc086664378f82b1ec8348ffbb4e1"},"schema_version":"1.0","source":{"id":"2309.09571","kind":"arxiv","version":2}},"canonical_sha256":"6a6724fef645c1888e9b27a3367649a53970fa08c13b617ac4303e51fbf57a2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6724fef645c1888e9b27a3367649a53970fa08c13b617ac4303e51fbf57a2c","first_computed_at":"2026-07-05T07:32:23.482970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:23.482970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhSLmdCdQJmMBzP+e3MkkFiPu1XwJ5HA04YJ+wZRPc49tj3YcNleDba3V2vdnDqESzwK832V+tw6wkpO0alnDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:23.483521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb438fe438a0388cb32fe9995b5bd2432df64b03dfcccfbf2572fd14d0aa2cb0","sha256:1fdd95806b3158b40e8847441d15270fea004a2407eb21e232e842d2d927549f"],"state_sha256":"08ba16bbc0d82caa986b262c735788781711ae08b238bb86843265fbc7df0fd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RwgXZWZ9ttnrLD9+9D65mloE2GbcTUDNj0dfqqi4Xdeb+412xeyIO/HvijklolibXG6tj8BwPcMJIx8DoRL9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:24:55.073935Z","bundle_sha256":"1fa3bf3077d584a91f7549d1a32094075e633666f18f64a6be75cdbad17046b2"}}