{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PI6UGOLKPJNT3JBFJ3QEB46VNU","short_pith_number":"pith:PI6UGOLK","schema_version":"1.0","canonical_sha256":"7a3d43396a7a5b3da4254ee040f3d56d1adae6f1568c8527ac3a9bf46cc4dfbc","source":{"kind":"arxiv","id":"2605.29885","version":1},"attestation_state":"computed","paper":{"title":"Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","math.OC","math.RT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongsung Huh","submitted_at":"2026-05-28T13:10:04Z","abstract_excerpt":"Modern statistical learning theory and deep learning characterize generalization primarily in terms of continuous capacity control (e.g., norm-based regularization, margin maximization, low-rank bias). While highly successful in continuous domains, deep learning consistently fails to extrapolate exact algorithmic or discrete algebraic rules, reflecting a missing inductive bias toward algorithmic complexity minimization. We propose the Cayley-table completion as the canonical testbed for this missing bias, serving as the discrete algebraic counterpart to matrix completion. Just as matrix factor"},"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":"2605.29885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T13:10:04Z","cross_cats_sorted":["cond-mat.dis-nn","math.OC","math.RT","stat.ML"],"title_canon_sha256":"a2f292ab8f796f8cba83e9762ba5309641ef6b9a0fc5c46739b8c150643bae27","abstract_canon_sha256":"2037bd0ae9b1c92127e545e6b1d2247f7d4b6b7bd8e3ae51f2559e00e91f20cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:57.712334Z","signature_b64":"LZ3B8QyI+22eBu2SIrtJjfPyvZu5l+76fDLo0YVqXNx+2b7DglwBN9VQF7tiYgkfVeaO8yNOTCu4yArhN6zQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a3d43396a7a5b3da4254ee040f3d56d1adae6f1568c8527ac3a9bf46cc4dfbc","last_reissued_at":"2026-05-29T02:05:57.711843Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:57.711843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","math.OC","math.RT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongsung Huh","submitted_at":"2026-05-28T13:10:04Z","abstract_excerpt":"Modern statistical learning theory and deep learning characterize generalization primarily in terms of continuous capacity control (e.g., norm-based regularization, margin maximization, low-rank bias). While highly successful in continuous domains, deep learning consistently fails to extrapolate exact algorithmic or discrete algebraic rules, reflecting a missing inductive bias toward algorithmic complexity minimization. We propose the Cayley-table completion as the canonical testbed for this missing bias, serving as the discrete algebraic counterpart to matrix completion. Just as matrix factor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29885","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/2605.29885/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":"2605.29885","created_at":"2026-05-29T02:05:57.711912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29885v1","created_at":"2026-05-29T02:05:57.711912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29885","created_at":"2026-05-29T02:05:57.711912+00:00"},{"alias_kind":"pith_short_12","alias_value":"PI6UGOLKPJNT","created_at":"2026-05-29T02:05:57.711912+00:00"},{"alias_kind":"pith_short_16","alias_value":"PI6UGOLKPJNT3JBF","created_at":"2026-05-29T02:05:57.711912+00:00"},{"alias_kind":"pith_short_8","alias_value":"PI6UGOLK","created_at":"2026-05-29T02:05:57.711912+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/PI6UGOLKPJNT3JBFJ3QEB46VNU","json":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU.json","graph_json":"https://pith.science/api/pith-number/PI6UGOLKPJNT3JBFJ3QEB46VNU/graph.json","events_json":"https://pith.science/api/pith-number/PI6UGOLKPJNT3JBFJ3QEB46VNU/events.json","paper":"https://pith.science/paper/PI6UGOLK"},"agent_actions":{"view_html":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU","download_json":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU.json","view_paper":"https://pith.science/paper/PI6UGOLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29885&json=true","fetch_graph":"https://pith.science/api/pith-number/PI6UGOLKPJNT3JBFJ3QEB46VNU/graph.json","fetch_events":"https://pith.science/api/pith-number/PI6UGOLKPJNT3JBFJ3QEB46VNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU/action/storage_attestation","attest_author":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU/action/author_attestation","sign_citation":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU/action/citation_signature","submit_replication":"https://pith.science/pith/PI6UGOLKPJNT3JBFJ3QEB46VNU/action/replication_record"}},"created_at":"2026-05-29T02:05:57.711912+00:00","updated_at":"2026-05-29T02:05:57.711912+00:00"}