{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IQU7IWWND2YUX773D7FODAJRWN","short_pith_number":"pith:IQU7IWWN","canonical_record":{"source":{"id":"1810.05270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T22:15:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"90362052d493c3f27fdd63a86fa76e466af08e8bbbec9b0e5535d4a52df21fff","abstract_canon_sha256":"10996b5c8f4a54566fd28f9df321382d2bbf1dc54563d6943b5a73bdcca66dda"},"schema_version":"1.0"},"canonical_sha256":"4429f45acd1eb14bfffb1fcae18131b36aa452d0283e70a29c8f709a4c4c2a4d","source":{"kind":"arxiv","id":"1810.05270","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05270","created_at":"2026-05-17T23:52:04Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05270v2","created_at":"2026-05-17T23:52:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05270","created_at":"2026-05-17T23:52:04Z"},{"alias_kind":"pith_short_12","alias_value":"IQU7IWWND2YU","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IQU7IWWND2YUX773","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IQU7IWWN","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IQU7IWWND2YUX773D7FODAJRWN","target":"record","payload":{"canonical_record":{"source":{"id":"1810.05270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T22:15:28Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"90362052d493c3f27fdd63a86fa76e466af08e8bbbec9b0e5535d4a52df21fff","abstract_canon_sha256":"10996b5c8f4a54566fd28f9df321382d2bbf1dc54563d6943b5a73bdcca66dda"},"schema_version":"1.0"},"canonical_sha256":"4429f45acd1eb14bfffb1fcae18131b36aa452d0283e70a29c8f709a4c4c2a4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:04.866681Z","signature_b64":"yETwOL9lYXccpEalxOonMGwjjnliSzfJu3c5uQ3oy4ywtih8DEES0tIL+48lTXqeCkS/1GY2/nln/X8ScGWLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4429f45acd1eb14bfffb1fcae18131b36aa452d0283e70a29c8f709a4c4c2a4d","last_reissued_at":"2026-05-17T23:52:04.866055Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:04.866055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.05270","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":"2026-05-17T23:52:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wXSzT08N0sw0dR9f67aHqTgOLd8nRAPT4D9/RJ3eHQtO/ZmoFJ+Mb7yAcciK0GMjYI/WDSds9BtgyzKvTm9lAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T07:33:41.837012Z"},"content_sha256":"cd427509572d2ef55ba488993385bf81cf6534d34a2523f9263c095365265070","schema_version":"1.0","event_id":"sha256:cd427509572d2ef55ba488993385bf81cf6534d34a2523f9263c095365265070"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IQU7IWWND2YUX773D7FODAJRWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Value of Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gao Huang, Mingjie Sun, Tinghui Zhou, Trevor Darrell, Zhuang Liu","submitted_at":"2018-10-11T22:15:28Z","abstract_excerpt":"Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning, according to a certain criterion, redundant weights are pruned and important weights are kept to best preserve the accuracy. In this work, we make several surprising observations which contradict common beliefs. For all state-of-the-art structured pruning algorithms we examined, fine-tuning a pruned model only gives comparable or worse performance than trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05270","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":"2026-05-17T23:52:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bu82O5eybbtzHcA3N6oCiyFtY9TWQ/uQyH3/Asi7sfaXguPPE/0G0ZMH7ZQMdA94ldKp1qTzvkyjtucl6j48CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T07:33:41.837373Z"},"content_sha256":"b3633c125e86268ffed98a51dada916dd407f15e1029d7df6c37b776e0e764e3","schema_version":"1.0","event_id":"sha256:b3633c125e86268ffed98a51dada916dd407f15e1029d7df6c37b776e0e764e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQU7IWWND2YUX773D7FODAJRWN/bundle.json","state_url":"https://pith.science/pith/IQU7IWWND2YUX773D7FODAJRWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQU7IWWND2YUX773D7FODAJRWN/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":"2026-05-19T07:33:41Z","links":{"resolver":"https://pith.science/pith/IQU7IWWND2YUX773D7FODAJRWN","bundle":"https://pith.science/pith/IQU7IWWND2YUX773D7FODAJRWN/bundle.json","state":"https://pith.science/pith/IQU7IWWND2YUX773D7FODAJRWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQU7IWWND2YUX773D7FODAJRWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IQU7IWWND2YUX773D7FODAJRWN","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":"10996b5c8f4a54566fd28f9df321382d2bbf1dc54563d6943b5a73bdcca66dda","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T22:15:28Z","title_canon_sha256":"90362052d493c3f27fdd63a86fa76e466af08e8bbbec9b0e5535d4a52df21fff"},"schema_version":"1.0","source":{"id":"1810.05270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.05270","created_at":"2026-05-17T23:52:04Z"},{"alias_kind":"arxiv_version","alias_value":"1810.05270v2","created_at":"2026-05-17T23:52:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05270","created_at":"2026-05-17T23:52:04Z"},{"alias_kind":"pith_short_12","alias_value":"IQU7IWWND2YU","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IQU7IWWND2YUX773","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IQU7IWWN","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:b3633c125e86268ffed98a51dada916dd407f15e1029d7df6c37b776e0e764e3","target":"graph","created_at":"2026-05-17T23:52:04Z","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":"Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning, according to a certain criterion, redundant weights are pruned and important weights are kept to best preserve the accuracy. In this work, we make several surprising observations which contradict common beliefs. For all state-of-the-art structured pruning algorithms we examined, fine-tuning a pruned model only gives comparable or worse performance than trainin","authors_text":"Gao Huang, Mingjie Sun, Tinghui Zhou, Trevor Darrell, Zhuang Liu","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T22:15:28Z","title":"Rethinking the Value of Network Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05270","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:cd427509572d2ef55ba488993385bf81cf6534d34a2523f9263c095365265070","target":"record","created_at":"2026-05-17T23:52:04Z","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":"10996b5c8f4a54566fd28f9df321382d2bbf1dc54563d6943b5a73bdcca66dda","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-11T22:15:28Z","title_canon_sha256":"90362052d493c3f27fdd63a86fa76e466af08e8bbbec9b0e5535d4a52df21fff"},"schema_version":"1.0","source":{"id":"1810.05270","kind":"arxiv","version":2}},"canonical_sha256":"4429f45acd1eb14bfffb1fcae18131b36aa452d0283e70a29c8f709a4c4c2a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4429f45acd1eb14bfffb1fcae18131b36aa452d0283e70a29c8f709a4c4c2a4d","first_computed_at":"2026-05-17T23:52:04.866055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:04.866055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yETwOL9lYXccpEalxOonMGwjjnliSzfJu3c5uQ3oy4ywtih8DEES0tIL+48lTXqeCkS/1GY2/nln/X8ScGWLDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:04.866681Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.05270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd427509572d2ef55ba488993385bf81cf6534d34a2523f9263c095365265070","sha256:b3633c125e86268ffed98a51dada916dd407f15e1029d7df6c37b776e0e764e3"],"state_sha256":"13d0f1b0a1c8e147d6f9f07b82b6e0351b2df3eac23025bc373b91e6f9f9016d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LgZE2v7Jeux48IlpJyKzbBby4TKoEOfDDD69K13Z8HLahF7zyw6E9NNX1BJoOUR9OctdWLOceX3fsutJw1EuAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T07:33:41.839113Z","bundle_sha256":"b2ae2b6eb2aa78f66e475826d28553b078418aef0c37225eaeec77f2de5e2dfa"}}