{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CB4MYUJQBYQZKLPYGJNUO63ROU","short_pith_number":"pith:CB4MYUJQ","canonical_record":{"source":{"id":"1811.08390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-20T17:52:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a4d60059cf727d3136b688c3bde12fbe67730636b5ac326c9663d8899d24871","abstract_canon_sha256":"8ce7977e22c217b466cae2bd6ee4aca23c7c2628e618d299944494f6400f8542"},"schema_version":"1.0"},"canonical_sha256":"1078cc51300e21952df8325b477b71751716b5da88bb56ff4b4adf53fdf8811e","source":{"kind":"arxiv","id":"1811.08390","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08390","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08390v2","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08390","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"CB4MYUJQBYQZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CB4MYUJQBYQZKLPY","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CB4MYUJQ","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CB4MYUJQBYQZKLPYGJNUO63ROU","target":"record","payload":{"canonical_record":{"source":{"id":"1811.08390","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-20T17:52:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a4d60059cf727d3136b688c3bde12fbe67730636b5ac326c9663d8899d24871","abstract_canon_sha256":"8ce7977e22c217b466cae2bd6ee4aca23c7c2628e618d299944494f6400f8542"},"schema_version":"1.0"},"canonical_sha256":"1078cc51300e21952df8325b477b71751716b5da88bb56ff4b4adf53fdf8811e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:56.865111Z","signature_b64":"0CLHICP6CICr7xgaLkEP0wtG5j5nZ6phM5W09h22SrQjNxv8IrdLAuqYocGg0jWSmXcVmh8gf3D9zF01STYSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1078cc51300e21952df8325b477b71751716b5da88bb56ff4b4adf53fdf8811e","last_reissued_at":"2026-05-17T23:57:56.864464Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:56.864464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.08390","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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJadPc+waep6LyJA/n8anXgpCDrMN9+H7b3pWFTJltuMQUfiaQWdNWl0bKn37nvn4IwM42+ke4nCsar/szm7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:55:52.915305Z"},"content_sha256":"24143d18725b2c25ca9813dbf8ab8769708ea65a29be8e59e075c5eb3b643108","schema_version":"1.0","event_id":"sha256:24143d18725b2c25ca9813dbf8ab8769708ea65a29be8e59e075c5eb3b643108"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CB4MYUJQBYQZKLPYGJNUO63ROU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Pruning for Efficient ConvNets via Incremental Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haoji Hu, Huan Wang, Qiming Zhang, Yuehai Wang","submitted_at":"2018-11-20T17:52:54Z","abstract_excerpt":"Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fact that the expressiveness of CNNs is fragile and needs a more gentle way of regularization for the networks to adapt during pruning. To solve this problem, we propose a new regularization-based pruning method (named IncReg) to incrementally assign different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08390","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":"2026-05-17T23:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4R3TQK/iAVY273S0I3t7cr/LDXaW/BCsR7UxfR4q587qxLZNzhPV+ugwhfW9DV3jFgMqFjnz1zYyoOtsQJJDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:55:52.916008Z"},"content_sha256":"f6377bff8ed39e1661520dd72cfad405a36d108ec8dab3b85e00ec4e588f5959","schema_version":"1.0","event_id":"sha256:f6377bff8ed39e1661520dd72cfad405a36d108ec8dab3b85e00ec4e588f5959"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CB4MYUJQBYQZKLPYGJNUO63ROU/bundle.json","state_url":"https://pith.science/pith/CB4MYUJQBYQZKLPYGJNUO63ROU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CB4MYUJQBYQZKLPYGJNUO63ROU/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":"2026-05-26T03:55:52Z","links":{"resolver":"https://pith.science/pith/CB4MYUJQBYQZKLPYGJNUO63ROU","bundle":"https://pith.science/pith/CB4MYUJQBYQZKLPYGJNUO63ROU/bundle.json","state":"https://pith.science/pith/CB4MYUJQBYQZKLPYGJNUO63ROU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CB4MYUJQBYQZKLPYGJNUO63ROU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CB4MYUJQBYQZKLPYGJNUO63ROU","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":"8ce7977e22c217b466cae2bd6ee4aca23c7c2628e618d299944494f6400f8542","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-20T17:52:54Z","title_canon_sha256":"9a4d60059cf727d3136b688c3bde12fbe67730636b5ac326c9663d8899d24871"},"schema_version":"1.0","source":{"id":"1811.08390","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.08390","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1811.08390v2","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08390","created_at":"2026-05-17T23:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"CB4MYUJQBYQZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CB4MYUJQBYQZKLPY","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CB4MYUJQ","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:f6377bff8ed39e1661520dd72cfad405a36d108ec8dab3b85e00ec4e588f5959","target":"graph","created_at":"2026-05-17T23:57:56Z","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":"Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fact that the expressiveness of CNNs is fragile and needs a more gentle way of regularization for the networks to adapt during pruning. To solve this problem, we propose a new regularization-based pruning method (named IncReg) to incrementally assign different ","authors_text":"Haoji Hu, Huan Wang, Qiming Zhang, Yuehai Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-20T17:52:54Z","title":"Structured Pruning for Efficient ConvNets via Incremental Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08390","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":"sha256:24143d18725b2c25ca9813dbf8ab8769708ea65a29be8e59e075c5eb3b643108","target":"record","created_at":"2026-05-17T23:57:56Z","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":"8ce7977e22c217b466cae2bd6ee4aca23c7c2628e618d299944494f6400f8542","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-20T17:52:54Z","title_canon_sha256":"9a4d60059cf727d3136b688c3bde12fbe67730636b5ac326c9663d8899d24871"},"schema_version":"1.0","source":{"id":"1811.08390","kind":"arxiv","version":2}},"canonical_sha256":"1078cc51300e21952df8325b477b71751716b5da88bb56ff4b4adf53fdf8811e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1078cc51300e21952df8325b477b71751716b5da88bb56ff4b4adf53fdf8811e","first_computed_at":"2026-05-17T23:57:56.864464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:56.864464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0CLHICP6CICr7xgaLkEP0wtG5j5nZ6phM5W09h22SrQjNxv8IrdLAuqYocGg0jWSmXcVmh8gf3D9zF01STYSCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:56.865111Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.08390","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24143d18725b2c25ca9813dbf8ab8769708ea65a29be8e59e075c5eb3b643108","sha256:f6377bff8ed39e1661520dd72cfad405a36d108ec8dab3b85e00ec4e588f5959"],"state_sha256":"e0c68b6abd196ab2cedc74bb68b75a2c06b865a6b5ab5530ab959aef556e3327"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFkTnCMBYqB6j0G0ZC8xhXqCN7Bx5g6UXi1IOVJqMPB4VcWqqYNFcEoge7I1/cK6KptvnRZJ7PUZHR+CcYliDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:55:52.919695Z","bundle_sha256":"d2ee90b6737242ee8c1686897777c919128d82babadade5c96b9043dc8f28105"}}