{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PYOQWCCD5DJJDGXHDTEKNIEPCE","short_pith_number":"pith:PYOQWCCD","canonical_record":{"source":{"id":"1709.06994","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T03:13:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"687e5be478742bb5ed0c632bbd04e331edc23ac4c1a9bff1f2944859287c5ae6","abstract_canon_sha256":"4a2bdf0d15ac8ddd957886d6cb6a67609874f2f6484d7af4cf2a32bc1a505025"},"schema_version":"1.0"},"canonical_sha256":"7e1d0b0843e8d2919ae71cc8a6a08f1101d66cd5ebf57c47b41c2446d93e42c6","source":{"kind":"arxiv","id":"1709.06994","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06994","created_at":"2026-05-18T00:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06994v3","created_at":"2026-05-18T00:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06994","created_at":"2026-05-18T00:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"PYOQWCCD5DJJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PYOQWCCD5DJJDGXH","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PYOQWCCD","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PYOQWCCD5DJJDGXHDTEKNIEPCE","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06994","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T03:13:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"687e5be478742bb5ed0c632bbd04e331edc23ac4c1a9bff1f2944859287c5ae6","abstract_canon_sha256":"4a2bdf0d15ac8ddd957886d6cb6a67609874f2f6484d7af4cf2a32bc1a505025"},"schema_version":"1.0"},"canonical_sha256":"7e1d0b0843e8d2919ae71cc8a6a08f1101d66cd5ebf57c47b41c2446d93e42c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:56.607574Z","signature_b64":"HFGH8WKpJs1zTTJheainGGLoBGrGhhcrgKTw07u1KTj66TAxrsKtlOvhQYiVWkV7ehAgpPYC4eWQ0I17MzelBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e1d0b0843e8d2919ae71cc8a6a08f1101d66cd5ebf57c47b41c2446d93e42c6","last_reissued_at":"2026-05-18T00:05:56.606996Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:56.606996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06994","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":"2026-05-18T00:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TYgn7E0IEveVe/CFdnr1z/6myYWQxswFVexLX5c+kNVXzqVBaILwQKEOr22GRuqiG9tCi5FBYFOk4XysRZo/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T05:41:12.373166Z"},"content_sha256":"7ce0e6bdcf83fcc2e4ccb2a66abec79d5171167c736e149571e848b350aa36fa","schema_version":"1.0","event_id":"sha256:7ce0e6bdcf83fcc2e4ccb2a66abec79d5171167c736e149571e848b350aa36fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PYOQWCCD5DJJDGXHDTEKNIEPCE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Probabilistic Pruning for Convolutional Neural Network Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoji Hu, Huan Wang, Qiming Zhang, Yuehai Wang","submitted_at":"2017-09-20T03:13:40Z","abstract_excerpt":"In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06994","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":""},"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":"2026-05-18T00:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+CM76wWn+F2EHux9/5j5y4DphoFnCYI0gqtgMOwZzSpj8tPOwvXsrTVl9rHKgOhymP8Owqvm+NHwsh6feEoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T05:41:12.373649Z"},"content_sha256":"ffce985eb0cfdaa439820e75b392ff171005c2d66a43078870cfa6be80afca9f","schema_version":"1.0","event_id":"sha256:ffce985eb0cfdaa439820e75b392ff171005c2d66a43078870cfa6be80afca9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE/bundle.json","state_url":"https://pith.science/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE/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":"2026-05-26T05:41:12Z","links":{"resolver":"https://pith.science/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE","bundle":"https://pith.science/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE/bundle.json","state":"https://pith.science/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYOQWCCD5DJJDGXHDTEKNIEPCE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PYOQWCCD5DJJDGXHDTEKNIEPCE","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":"4a2bdf0d15ac8ddd957886d6cb6a67609874f2f6484d7af4cf2a32bc1a505025","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T03:13:40Z","title_canon_sha256":"687e5be478742bb5ed0c632bbd04e331edc23ac4c1a9bff1f2944859287c5ae6"},"schema_version":"1.0","source":{"id":"1709.06994","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06994","created_at":"2026-05-18T00:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06994v3","created_at":"2026-05-18T00:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06994","created_at":"2026-05-18T00:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"PYOQWCCD5DJJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PYOQWCCD5DJJDGXH","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PYOQWCCD","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:ffce985eb0cfdaa439820e75b392ff171005c2d66a43078870cfa6be80afca9f","target":"graph","created_at":"2026-05-18T00:05:56Z","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":"In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Exp","authors_text":"Haoji Hu, Huan Wang, Qiming Zhang, Yuehai Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T03:13:40Z","title":"Structured Probabilistic Pruning for Convolutional Neural Network Acceleration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06994","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":"sha256:7ce0e6bdcf83fcc2e4ccb2a66abec79d5171167c736e149571e848b350aa36fa","target":"record","created_at":"2026-05-18T00:05:56Z","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":"4a2bdf0d15ac8ddd957886d6cb6a67609874f2f6484d7af4cf2a32bc1a505025","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-20T03:13:40Z","title_canon_sha256":"687e5be478742bb5ed0c632bbd04e331edc23ac4c1a9bff1f2944859287c5ae6"},"schema_version":"1.0","source":{"id":"1709.06994","kind":"arxiv","version":3}},"canonical_sha256":"7e1d0b0843e8d2919ae71cc8a6a08f1101d66cd5ebf57c47b41c2446d93e42c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e1d0b0843e8d2919ae71cc8a6a08f1101d66cd5ebf57c47b41c2446d93e42c6","first_computed_at":"2026-05-18T00:05:56.606996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:56.606996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HFGH8WKpJs1zTTJheainGGLoBGrGhhcrgKTw07u1KTj66TAxrsKtlOvhQYiVWkV7ehAgpPYC4eWQ0I17MzelBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:56.607574Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06994","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ce0e6bdcf83fcc2e4ccb2a66abec79d5171167c736e149571e848b350aa36fa","sha256:ffce985eb0cfdaa439820e75b392ff171005c2d66a43078870cfa6be80afca9f"],"state_sha256":"2791ef3eada7bec51b39cbf4b18fa787ff7bd9a5153ee38d80541f300fefcd6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P85HssRR0y7c701qTgmOl9tD85S8Lr4ewtXHCzqilcJ4l71YKQGSEPtPSuCJ+5izAOSJhovDiInK0oV30T0WCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T05:41:12.376728Z","bundle_sha256":"b9c4c9e34eabbe7accbafdc70c75ab00945315e0395e412bb5fa65159390f13e"}}