{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OUKUSR52TMGDUH3MOZJEYJ46S5","short_pith_number":"pith:OUKUSR52","schema_version":"1.0","canonical_sha256":"75154947ba9b0c3a1f6c76524c279e9770219b8ef18adbe2d3c244229320f377","source":{"kind":"arxiv","id":"2307.09994","version":1},"attestation_state":"computed","paper":{"title":"Impact of Disentanglement on Pruning Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Abd El Rahman Shabayek, Anis Kacem, Carl Shneider, Djamila Aouada, Nilotpal Sinha, Peyman Rostami","submitted_at":"2023-07-19T13:58:01Z","abstract_excerpt":"Deploying deep learning neural networks on edge devices, to accomplish task specific objectives in the real-world, requires a reduction in their memory footprint, power consumption, and latency. This can be realized via efficient model compression. Disentangled latent representations produced by variational autoencoder (VAE) networks are a promising approach for achieving model compression because they mainly retain task-specific information, discarding useless information for the task at hand. We make use of the Beta-VAE framework combined with a standard criterion for pruning to investigate "},"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":"2307.09994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-19T13:58:01Z","cross_cats_sorted":["cs.CV","eess.SP"],"title_canon_sha256":"c6edf3f90307cb4522aad71167993ffb41d65a3352a6984a67121e125cba67e8","abstract_canon_sha256":"2c9873d1964af5d69ffbdb87a8f80a7e9bb0efaa5ab49258eb53e3716d0fc124"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:49.035620Z","signature_b64":"JoYurlCYpyTrR/wgkK5hmX9T454wl3c3gcv7O3MIf5YFG1VUIoOcVpQPHB09G30OoIukndmTMeGcM0UtL7apAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75154947ba9b0c3a1f6c76524c279e9770219b8ef18adbe2d3c244229320f377","last_reissued_at":"2026-07-05T06:32:49.035117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:49.035117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of Disentanglement on Pruning Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Abd El Rahman Shabayek, Anis Kacem, Carl Shneider, Djamila Aouada, Nilotpal Sinha, Peyman Rostami","submitted_at":"2023-07-19T13:58:01Z","abstract_excerpt":"Deploying deep learning neural networks on edge devices, to accomplish task specific objectives in the real-world, requires a reduction in their memory footprint, power consumption, and latency. This can be realized via efficient model compression. Disentangled latent representations produced by variational autoencoder (VAE) networks are a promising approach for achieving model compression because they mainly retain task-specific information, discarding useless information for the task at hand. We make use of the Beta-VAE framework combined with a standard criterion for pruning to investigate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09994","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/2307.09994/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":"2307.09994","created_at":"2026-07-05T06:32:49.035174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.09994v1","created_at":"2026-07-05T06:32:49.035174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09994","created_at":"2026-07-05T06:32:49.035174+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUKUSR52TMGD","created_at":"2026-07-05T06:32:49.035174+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUKUSR52TMGDUH3M","created_at":"2026-07-05T06:32:49.035174+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUKUSR52","created_at":"2026-07-05T06:32:49.035174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18578","citing_title":"Pruning Deep Convolutional Neural Network Using Conditional Mutual Information","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5","json":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5.json","graph_json":"https://pith.science/api/pith-number/OUKUSR52TMGDUH3MOZJEYJ46S5/graph.json","events_json":"https://pith.science/api/pith-number/OUKUSR52TMGDUH3MOZJEYJ46S5/events.json","paper":"https://pith.science/paper/OUKUSR52"},"agent_actions":{"view_html":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5","download_json":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5.json","view_paper":"https://pith.science/paper/OUKUSR52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.09994&json=true","fetch_graph":"https://pith.science/api/pith-number/OUKUSR52TMGDUH3MOZJEYJ46S5/graph.json","fetch_events":"https://pith.science/api/pith-number/OUKUSR52TMGDUH3MOZJEYJ46S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5/action/storage_attestation","attest_author":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5/action/author_attestation","sign_citation":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5/action/citation_signature","submit_replication":"https://pith.science/pith/OUKUSR52TMGDUH3MOZJEYJ46S5/action/replication_record"}},"created_at":"2026-07-05T06:32:49.035174+00:00","updated_at":"2026-07-05T06:32:49.035174+00:00"}