{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NMJIAECGNPHXQ56IRE27HMI2LP","short_pith_number":"pith:NMJIAECG","schema_version":"1.0","canonical_sha256":"6b128010466bcf7877c88935f3b11a5bee687954d2aeb42611426f79258e84c4","source":{"kind":"arxiv","id":"2605.29823","version":1},"attestation_state":"computed","paper":{"title":"Quantifying and Optimizing Simplicity via Polynomial Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Chen, Guanyu Chen, Minghao Xiao, Tianren Zhang, Xiangxin Li","submitted_at":"2026-05-28T12:05:41Z","abstract_excerpt":"Deep networks often exhibit a preference for \"simple\" solutions, and such a simplicity bias is widely believed to play a key role in generalization. Yet a broadly applicable, quantitative measure of simplicity remains elusive. We introduce polynomial representations as a distribution-aware, low-dimensional surrogate for neural functions: we approximate a network's predictive behavior along data-dependent interpolation paths using orthogonal polynomial bases, yielding a compact functional representation. We show that the effective degree of this representation serves as a practical simplicity m"},"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":"2605.29823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T12:05:41Z","cross_cats_sorted":[],"title_canon_sha256":"b0c65a7dadccd1c8b81be101bef1760191966c921fae01b255c23cf25ad1434f","abstract_canon_sha256":"b8e7e082efb3b5fdc4f6275d8558799a7be62c5be7c94ee43d02c3f8d2674816"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:54.722222Z","signature_b64":"fSJ97cJpStVmaaqlrhBBI/KjEAPC9pps0DREEwSNbJaOlj9srSAuUyVJGcs2G2LCTA+qfVlNLXJjwRcLez2/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b128010466bcf7877c88935f3b11a5bee687954d2aeb42611426f79258e84c4","last_reissued_at":"2026-05-29T02:05:54.721526Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:54.721526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying and Optimizing Simplicity via Polynomial Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Feng Chen, Guanyu Chen, Minghao Xiao, Tianren Zhang, Xiangxin Li","submitted_at":"2026-05-28T12:05:41Z","abstract_excerpt":"Deep networks often exhibit a preference for \"simple\" solutions, and such a simplicity bias is widely believed to play a key role in generalization. Yet a broadly applicable, quantitative measure of simplicity remains elusive. We introduce polynomial representations as a distribution-aware, low-dimensional surrogate for neural functions: we approximate a network's predictive behavior along data-dependent interpolation paths using orthogonal polynomial bases, yielding a compact functional representation. We show that the effective degree of this representation serves as a practical simplicity m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29823","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/2605.29823/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":"2605.29823","created_at":"2026-05-29T02:05:54.721613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29823v1","created_at":"2026-05-29T02:05:54.721613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29823","created_at":"2026-05-29T02:05:54.721613+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMJIAECGNPHX","created_at":"2026-05-29T02:05:54.721613+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMJIAECGNPHXQ56I","created_at":"2026-05-29T02:05:54.721613+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMJIAECG","created_at":"2026-05-29T02:05:54.721613+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/NMJIAECGNPHXQ56IRE27HMI2LP","json":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP.json","graph_json":"https://pith.science/api/pith-number/NMJIAECGNPHXQ56IRE27HMI2LP/graph.json","events_json":"https://pith.science/api/pith-number/NMJIAECGNPHXQ56IRE27HMI2LP/events.json","paper":"https://pith.science/paper/NMJIAECG"},"agent_actions":{"view_html":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP","download_json":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP.json","view_paper":"https://pith.science/paper/NMJIAECG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29823&json=true","fetch_graph":"https://pith.science/api/pith-number/NMJIAECGNPHXQ56IRE27HMI2LP/graph.json","fetch_events":"https://pith.science/api/pith-number/NMJIAECGNPHXQ56IRE27HMI2LP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP/action/storage_attestation","attest_author":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP/action/author_attestation","sign_citation":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP/action/citation_signature","submit_replication":"https://pith.science/pith/NMJIAECGNPHXQ56IRE27HMI2LP/action/replication_record"}},"created_at":"2026-05-29T02:05:54.721613+00:00","updated_at":"2026-05-29T02:05:54.721613+00:00"}