{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DE4AFFB52HB6I2ITVJ7IJY2YJG","short_pith_number":"pith:DE4AFFB5","schema_version":"1.0","canonical_sha256":"193802943dd1c3e46913aa7e84e358498a18541c0a97605305c5528adb827b12","source":{"kind":"arxiv","id":"2004.14584","version":1},"attestation_state":"computed","paper":{"title":"Out-of-the-box channel pruned networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Luo, Gurumurthy Swaminathan, Ragav Venkatesan, Xiong Zhou","submitted_at":"2020-04-30T04:40:47Z","abstract_excerpt":"In the last decade convolutional neural networks have become gargantuan. Pre-trained models, when used as initializers are able to fine-tune ever larger networks on small datasets. Consequently, not all the convolutional features that these fine-tuned models detect are requisite for the end-task. Several works of channel pruning have been proposed to prune away compute and memory from models that were trained already. Typically, these involve policies that decide which and how many channels to remove from each layer leading to channel-wise and/or layer-wise pruning profiles, respectively. In t"},"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":"2004.14584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T04:40:47Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"4575c6585b209ba9229e1daf1f75b222aeba6726c05a9870a6752047b3a00572","abstract_canon_sha256":"10627c9971667ee95c669f9c12e4df245633a7c123fe2e4119f3ef6e9a4061d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:27.667748Z","signature_b64":"xPOpfyvpptnZvpCedoWfYIA1ocjxotB/Sv1uIXsI9d6P+DAhSAuy49ytIcqRpLgESIMBlLkQMJu8sXHHNRJ+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"193802943dd1c3e46913aa7e84e358498a18541c0a97605305c5528adb827b12","last_reissued_at":"2026-07-05T00:59:27.667259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:27.667259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-the-box channel pruned networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Luo, Gurumurthy Swaminathan, Ragav Venkatesan, Xiong Zhou","submitted_at":"2020-04-30T04:40:47Z","abstract_excerpt":"In the last decade convolutional neural networks have become gargantuan. Pre-trained models, when used as initializers are able to fine-tune ever larger networks on small datasets. Consequently, not all the convolutional features that these fine-tuned models detect are requisite for the end-task. Several works of channel pruning have been proposed to prune away compute and memory from models that were trained already. Typically, these involve policies that decide which and how many channels to remove from each layer leading to channel-wise and/or layer-wise pruning profiles, respectively. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14584","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.14584/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.14584","created_at":"2026-07-05T00:59:27.667322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14584v1","created_at":"2026-07-05T00:59:27.667322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14584","created_at":"2026-07-05T00:59:27.667322+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE4AFFB52HB6","created_at":"2026-07-05T00:59:27.667322+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE4AFFB52HB6I2IT","created_at":"2026-07-05T00:59:27.667322+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE4AFFB5","created_at":"2026-07-05T00:59:27.667322+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/DE4AFFB52HB6I2ITVJ7IJY2YJG","json":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG.json","graph_json":"https://pith.science/api/pith-number/DE4AFFB52HB6I2ITVJ7IJY2YJG/graph.json","events_json":"https://pith.science/api/pith-number/DE4AFFB52HB6I2ITVJ7IJY2YJG/events.json","paper":"https://pith.science/paper/DE4AFFB5"},"agent_actions":{"view_html":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG","download_json":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG.json","view_paper":"https://pith.science/paper/DE4AFFB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14584&json=true","fetch_graph":"https://pith.science/api/pith-number/DE4AFFB52HB6I2ITVJ7IJY2YJG/graph.json","fetch_events":"https://pith.science/api/pith-number/DE4AFFB52HB6I2ITVJ7IJY2YJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG/action/storage_attestation","attest_author":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG/action/author_attestation","sign_citation":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG/action/citation_signature","submit_replication":"https://pith.science/pith/DE4AFFB52HB6I2ITVJ7IJY2YJG/action/replication_record"}},"created_at":"2026-07-05T00:59:27.667322+00:00","updated_at":"2026-07-05T00:59:27.667322+00:00"}