{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FLFWNA6CBECFLLT5JTRIQUNIWO","short_pith_number":"pith:FLFWNA6C","canonical_record":{"source":{"id":"2204.00783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T07:09:17Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"71a2b3dbad7b46a0ddc2356f2a8a16b673cb03fff54bd4cd080cf376f7544c3a","abstract_canon_sha256":"896342c3cdcba809cd3c304ad13e44ad589b14dfdb5c1882a5b331b1b32e9d2e"},"schema_version":"1.0"},"canonical_sha256":"2acb6683c2090455ae7d4ce28851a8b398c286fdfdef5951d2647d83929edfbc","source":{"kind":"arxiv","id":"2204.00783","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00783","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00783v3","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00783","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"FLFWNA6CBECF","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"FLFWNA6CBECFLLT5","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"FLFWNA6C","created_at":"2026-07-05T11:23:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FLFWNA6CBECFLLT5JTRIQUNIWO","target":"record","payload":{"canonical_record":{"source":{"id":"2204.00783","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T07:09:17Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"71a2b3dbad7b46a0ddc2356f2a8a16b673cb03fff54bd4cd080cf376f7544c3a","abstract_canon_sha256":"896342c3cdcba809cd3c304ad13e44ad589b14dfdb5c1882a5b331b1b32e9d2e"},"schema_version":"1.0"},"canonical_sha256":"2acb6683c2090455ae7d4ce28851a8b398c286fdfdef5951d2647d83929edfbc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:12.994108Z","signature_b64":"JbIAzLVev5Oncaobuw/ogoNoGEibps4R9GOE/iyjfqVHzDa2gli8hS/h2ypYG5acYJXV7gWYRh4wW1vDp5GQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2acb6683c2090455ae7d4ce28851a8b398c286fdfdef5951d2647d83929edfbc","last_reissued_at":"2026-07-05T11:23:12.993520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:12.993520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.00783","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5HnAgO4gSbZ5DzhCOF/3xsMwbyypfMsFgbj1XftF7tssQEqM61E0OdEmp5c299MHLgpMZlq8JqrRFH/uZ0LYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:19:58.294637Z"},"content_sha256":"af60e7474cc178bf5bd58d262e1c8cb684b00615285f54a07c5ced8194d7b990","schema_version":"1.0","event_id":"sha256:af60e7474cc178bf5bd58d262e1c8cb684b00615285f54a07c5ced8194d7b990"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FLFWNA6CBECFLLT5JTRIQUNIWO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervised Robustness-preserving Data-free Neural Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Guangdong Bai, Jin Song Dong, Mark Huasong Meng, Sin Gee Teo","submitted_at":"2022-04-02T07:09:17Z","abstract_excerpt":"When deploying pre-trained neural network models in real-world applications, model consumers often encounter resource-constraint platforms such as mobile and smart devices. They typically use the pruning technique to reduce the size and complexity of the model, generating a lighter one with less resource consumption. Nonetheless, most existing pruning methods are proposed with the premise that the model after being pruned has a chance to be fine-tuned or even retrained based on the original training data. This may be unrealistic in practice, as the data controllers are often reluctant to provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00783","kind":"arxiv","version":3},"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/2204.00783/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":"2026-07-05T11:23:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q9FTckl03ZdeBHUrF6ZfzyHZV2mgDs3c5QFultnjctkseiUQx6sAFG3ucAHl76jD82kGJ/nee6S+rPfqRahXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T00:19:58.295014Z"},"content_sha256":"89da48187a97b16bbbecbb1379e8eaf0ce8bbb1e50b8a5e49d58ea8658fbe955","schema_version":"1.0","event_id":"sha256:89da48187a97b16bbbecbb1379e8eaf0ce8bbb1e50b8a5e49d58ea8658fbe955"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FLFWNA6CBECFLLT5JTRIQUNIWO/bundle.json","state_url":"https://pith.science/pith/FLFWNA6CBECFLLT5JTRIQUNIWO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FLFWNA6CBECFLLT5JTRIQUNIWO/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":"2026-08-24T00:19:58Z","links":{"resolver":"https://pith.science/pith/FLFWNA6CBECFLLT5JTRIQUNIWO","bundle":"https://pith.science/pith/FLFWNA6CBECFLLT5JTRIQUNIWO/bundle.json","state":"https://pith.science/pith/FLFWNA6CBECFLLT5JTRIQUNIWO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FLFWNA6CBECFLLT5JTRIQUNIWO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FLFWNA6CBECFLLT5JTRIQUNIWO","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":"896342c3cdcba809cd3c304ad13e44ad589b14dfdb5c1882a5b331b1b32e9d2e","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T07:09:17Z","title_canon_sha256":"71a2b3dbad7b46a0ddc2356f2a8a16b673cb03fff54bd4cd080cf376f7544c3a"},"schema_version":"1.0","source":{"id":"2204.00783","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00783","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00783v3","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00783","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"FLFWNA6CBECF","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"FLFWNA6CBECFLLT5","created_at":"2026-07-05T11:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"FLFWNA6C","created_at":"2026-07-05T11:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:89da48187a97b16bbbecbb1379e8eaf0ce8bbb1e50b8a5e49d58ea8658fbe955","target":"graph","created_at":"2026-07-05T11:23:12Z","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/2204.00783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When deploying pre-trained neural network models in real-world applications, model consumers often encounter resource-constraint platforms such as mobile and smart devices. They typically use the pruning technique to reduce the size and complexity of the model, generating a lighter one with less resource consumption. Nonetheless, most existing pruning methods are proposed with the premise that the model after being pruned has a chance to be fine-tuned or even retrained based on the original training data. This may be unrealistic in practice, as the data controllers are often reluctant to provi","authors_text":"Guangdong Bai, Jin Song Dong, Mark Huasong Meng, Sin Gee Teo","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T07:09:17Z","title":"Supervised Robustness-preserving Data-free Neural Network Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00783","kind":"arxiv","version":3},"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:af60e7474cc178bf5bd58d262e1c8cb684b00615285f54a07c5ced8194d7b990","target":"record","created_at":"2026-07-05T11:23:12Z","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":"896342c3cdcba809cd3c304ad13e44ad589b14dfdb5c1882a5b331b1b32e9d2e","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T07:09:17Z","title_canon_sha256":"71a2b3dbad7b46a0ddc2356f2a8a16b673cb03fff54bd4cd080cf376f7544c3a"},"schema_version":"1.0","source":{"id":"2204.00783","kind":"arxiv","version":3}},"canonical_sha256":"2acb6683c2090455ae7d4ce28851a8b398c286fdfdef5951d2647d83929edfbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2acb6683c2090455ae7d4ce28851a8b398c286fdfdef5951d2647d83929edfbc","first_computed_at":"2026-07-05T11:23:12.993520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:12.993520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JbIAzLVev5Oncaobuw/ogoNoGEibps4R9GOE/iyjfqVHzDa2gli8hS/h2ypYG5acYJXV7gWYRh4wW1vDp5GQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:12.994108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00783","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af60e7474cc178bf5bd58d262e1c8cb684b00615285f54a07c5ced8194d7b990","sha256:89da48187a97b16bbbecbb1379e8eaf0ce8bbb1e50b8a5e49d58ea8658fbe955"],"state_sha256":"05f0e8e8ed5434f19497027e55f92172e42c7804652284886317446e4e2730ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T98j4RwFbrQs1QgiImAF0Xh45CCFfIG69JTpn0R56nJGPbxk/PRqafu7SZqtnlBt1NAoHegwD35r5OwhjL+KDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T00:19:58.297629Z","bundle_sha256":"6c4bae1e44a1909fc4f01682e15a5018485e3e51fc0f1d77b7efef86724f77d0"}}