{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OTHB6R25JDJ26TYNH6RALEHZYW","short_pith_number":"pith:OTHB6R25","schema_version":"1.0","canonical_sha256":"74ce1f475d48d3af4f0d3fa20590f9c59eef5936af4edf1a11e67312445ffe51","source":{"kind":"arxiv","id":"2505.17469","version":2},"attestation_state":"computed","paper":{"title":"Efficient compression of neural networks and datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Lukas Silvester Barth, Paulo von Petersenn","submitted_at":"2025-05-23T04:50:33Z","abstract_excerpt":"Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), which predict that simpler models generalize better when data arises from low-complexity distributions. In this article, we combine insights from algorithmic information theory and techniques from neural network pruning to improve model generalization by identifying the most effective data compression method. Since exact MDL optimization is intractable, we cast it as $\\ell_0$ regularized learning and explain why parameter sparsity provides an effective compu"},"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":"2505.17469","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T04:50:33Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","math.ST","stat.TH"],"title_canon_sha256":"4a099f81d3640216c28b8b2c1188ca08b29d5cdf36b3f30208ed65dd410dab45","abstract_canon_sha256":"231083c30d03ded8305aea3e84afd27bc2b5b510325acdd7aa0d6048050f1a23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:13.852748Z","signature_b64":"okW+c2DSJu0WuQcY4x1pHaXyHtxzgZEV9vVIV31x2YNTeUqGACdsk8YNAKBCiGD0LdVFNCCZwJ43a2MoZ/9/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74ce1f475d48d3af4f0d3fa20590f9c59eef5936af4edf1a11e67312445ffe51","last_reissued_at":"2026-05-18T02:45:13.852247Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:13.852247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient compression of neural networks and datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Lukas Silvester Barth, Paulo von Petersenn","submitted_at":"2025-05-23T04:50:33Z","abstract_excerpt":"Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), which predict that simpler models generalize better when data arises from low-complexity distributions. In this article, we combine insights from algorithmic information theory and techniques from neural network pruning to improve model generalization by identifying the most effective data compression method. Since exact MDL optimization is intractable, we cast it as $\\ell_0$ regularized learning and explain why parameter sparsity provides an effective compu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17469","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.17469","created_at":"2026-05-18T02:45:13.852327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17469v2","created_at":"2026-05-18T02:45:13.852327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17469","created_at":"2026-05-18T02:45:13.852327+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTHB6R25JDJ2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTHB6R25JDJ26TYN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTHB6R25","created_at":"2026-05-18T12:33:37.589309+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/OTHB6R25JDJ26TYNH6RALEHZYW","json":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW.json","graph_json":"https://pith.science/api/pith-number/OTHB6R25JDJ26TYNH6RALEHZYW/graph.json","events_json":"https://pith.science/api/pith-number/OTHB6R25JDJ26TYNH6RALEHZYW/events.json","paper":"https://pith.science/paper/OTHB6R25"},"agent_actions":{"view_html":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW","download_json":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW.json","view_paper":"https://pith.science/paper/OTHB6R25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17469&json=true","fetch_graph":"https://pith.science/api/pith-number/OTHB6R25JDJ26TYNH6RALEHZYW/graph.json","fetch_events":"https://pith.science/api/pith-number/OTHB6R25JDJ26TYNH6RALEHZYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW/action/storage_attestation","attest_author":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW/action/author_attestation","sign_citation":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW/action/citation_signature","submit_replication":"https://pith.science/pith/OTHB6R25JDJ26TYNH6RALEHZYW/action/replication_record"}},"created_at":"2026-05-18T02:45:13.852327+00:00","updated_at":"2026-05-18T02:45:13.852327+00:00"}