{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GUM6D7JU2Q263QNNPCZHT2T47J","short_pith_number":"pith:GUM6D7JU","schema_version":"1.0","canonical_sha256":"3519e1fd34d435edc1ad78b279ea7cfa558db7b8fc38e22c1f3a64076adb1de5","source":{"kind":"arxiv","id":"1707.09102","version":1},"attestation_state":"computed","paper":{"title":"Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frederick Tung, Greg Mori, Srikanth Muralidharan","submitted_at":"2017-07-28T04:40:32Z","abstract_excerpt":"When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual space than the source domain used for pre-training (e.g. ImageNet), the fine-tuned network is likely to be over-parameterized. However, applying network pruning as a post-processing step to reduce the memory requirements has drawbacks: fine-tuning and pruning are performed independently; pruning parameters are set once and cannot adapt over time; and the hi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1707.09102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-28T04:40:32Z","cross_cats_sorted":[],"title_canon_sha256":"ceaf7d500ac072b8f82620ae16568a075481184498aa6ab5be2f17da5553e974","abstract_canon_sha256":"a6d7ec56c23630309e16a6775328693d25949c24166a56c986afa9c1b2c4f81a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:17.085065Z","signature_b64":"3LuYeaO4tAx4CUbf1PZUo1FWIYqxHqeyWPMXA9OgJZ3ehu+0u4VkCZiKp1K7BT7LKjGM2Kwrp6/fFnIFuAAPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3519e1fd34d435edc1ad78b279ea7cfa558db7b8fc38e22c1f3a64076adb1de5","last_reissued_at":"2026-05-18T00:39:17.084394Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:17.084394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Frederick Tung, Greg Mori, Srikanth Muralidharan","submitted_at":"2017-07-28T04:40:32Z","abstract_excerpt":"When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual space than the source domain used for pre-training (e.g. ImageNet), the fine-tuned network is likely to be over-parameterized. However, applying network pruning as a post-processing step to reduce the memory requirements has drawbacks: fine-tuning and pruning are performed independently; pruning parameters are set once and cannot adapt over time; and the hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09102","kind":"arxiv","version":1},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1707.09102","created_at":"2026-05-18T00:39:17.084499+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09102v1","created_at":"2026-05-18T00:39:17.084499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09102","created_at":"2026-05-18T00:39:17.084499+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUM6D7JU2Q26","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUM6D7JU2Q263QNN","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUM6D7JU","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J","json":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J.json","graph_json":"https://pith.science/api/pith-number/GUM6D7JU2Q263QNNPCZHT2T47J/graph.json","events_json":"https://pith.science/api/pith-number/GUM6D7JU2Q263QNNPCZHT2T47J/events.json","paper":"https://pith.science/paper/GUM6D7JU"},"agent_actions":{"view_html":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J","download_json":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J.json","view_paper":"https://pith.science/paper/GUM6D7JU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09102&json=true","fetch_graph":"https://pith.science/api/pith-number/GUM6D7JU2Q263QNNPCZHT2T47J/graph.json","fetch_events":"https://pith.science/api/pith-number/GUM6D7JU2Q263QNNPCZHT2T47J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J/action/storage_attestation","attest_author":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J/action/author_attestation","sign_citation":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J/action/citation_signature","submit_replication":"https://pith.science/pith/GUM6D7JU2Q263QNNPCZHT2T47J/action/replication_record"}},"created_at":"2026-05-18T00:39:17.084499+00:00","updated_at":"2026-05-18T00:39:17.084499+00:00"}