{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:24VQ6L2NPH2MZG7MCTT7722ZXX","short_pith_number":"pith:24VQ6L2N","schema_version":"1.0","canonical_sha256":"d72b0f2f4d79f4cc9bec14e7ffeb59bdc95bbbced6d2cb6156dadc9570665bdd","source":{"kind":"arxiv","id":"2002.02949","version":2},"attestation_state":"computed","paper":{"title":"Activation Density driven Energy-Efficient Pruning in Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Priyadarshini Panda, Timothy Foldy-Porto, Yeshwanth Venkatesha","submitted_at":"2020-02-07T18:34:31Z","abstract_excerpt":"Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point from which they perform a time-intensive iterative pruning and retraining procedure to regain the original accuracy. We propose a novel pruning method that prunes a network real-time during training, reducing the overall training time to achieve an efficient compressed network. We introduce an activation density based analysis to identify the optimal relative"},"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":"2002.02949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T18:34:31Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"375cdefc9d01f313b2cddd4d25533b421cac9fea95c73d3a7e769edffd802ec3","abstract_canon_sha256":"f054bac44a9552435cbdf21f73822ae1e22216be0d873a822e6c2ae796798f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:50.870758Z","signature_b64":"L6XzHamkJZ+Q8EISNPWNu4qRBNMDofzi8UhpZeI9259uKU/CZZJiCU0nIXXqqvjWv2VgUB4U0JUbhysy3L0/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72b0f2f4d79f4cc9bec14e7ffeb59bdc95bbbced6d2cb6156dadc9570665bdd","last_reissued_at":"2026-07-05T01:41:50.870308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:50.870308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activation Density driven Energy-Efficient Pruning in Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Priyadarshini Panda, Timothy Foldy-Porto, Yeshwanth Venkatesha","submitted_at":"2020-02-07T18:34:31Z","abstract_excerpt":"Neural network pruning with suitable retraining can yield networks with considerably fewer parameters than the original with comparable degrees of accuracy. Typical pruning methods require large, fully trained networks as a starting point from which they perform a time-intensive iterative pruning and retraining procedure to regain the original accuracy. We propose a novel pruning method that prunes a network real-time during training, reducing the overall training time to achieve an efficient compressed network. We introduce an activation density based analysis to identify the optimal relative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02949","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.02949/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":"2002.02949","created_at":"2026-07-05T01:41:50.870375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02949v2","created_at":"2026-07-05T01:41:50.870375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02949","created_at":"2026-07-05T01:41:50.870375+00:00"},{"alias_kind":"pith_short_12","alias_value":"24VQ6L2NPH2M","created_at":"2026-07-05T01:41:50.870375+00:00"},{"alias_kind":"pith_short_16","alias_value":"24VQ6L2NPH2MZG7M","created_at":"2026-07-05T01:41:50.870375+00:00"},{"alias_kind":"pith_short_8","alias_value":"24VQ6L2N","created_at":"2026-07-05T01:41:50.870375+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/24VQ6L2NPH2MZG7MCTT7722ZXX","json":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX.json","graph_json":"https://pith.science/api/pith-number/24VQ6L2NPH2MZG7MCTT7722ZXX/graph.json","events_json":"https://pith.science/api/pith-number/24VQ6L2NPH2MZG7MCTT7722ZXX/events.json","paper":"https://pith.science/paper/24VQ6L2N"},"agent_actions":{"view_html":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX","download_json":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX.json","view_paper":"https://pith.science/paper/24VQ6L2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02949&json=true","fetch_graph":"https://pith.science/api/pith-number/24VQ6L2NPH2MZG7MCTT7722ZXX/graph.json","fetch_events":"https://pith.science/api/pith-number/24VQ6L2NPH2MZG7MCTT7722ZXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX/action/storage_attestation","attest_author":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX/action/author_attestation","sign_citation":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX/action/citation_signature","submit_replication":"https://pith.science/pith/24VQ6L2NPH2MZG7MCTT7722ZXX/action/replication_record"}},"created_at":"2026-07-05T01:41:50.870375+00:00","updated_at":"2026-07-05T01:41:50.870375+00:00"}