{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4PNVYDUNEU4UDY6Z7BA746BKBN","short_pith_number":"pith:4PNVYDUN","schema_version":"1.0","canonical_sha256":"e3db5c0e8d253941e3d9f841fe782a0b6ced1f28f27a600846a5c17373759f7d","source":{"kind":"arxiv","id":"1904.03292","version":2},"attestation_state":"computed","paper":{"title":"The Information Complexity of Learning Tasks, their Structure and their Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Achille, Giovanni Paolini, Glen Mbeng, Stefano Soatto","submitted_at":"2019-04-05T21:46:27Z","abstract_excerpt":"We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learning, whereby a parametric model is pre-trained for a task, and then fine-tuned for another. The framework we develop is non-asymptotic, captures the finite nature of the training dataset, and allows distinguishing learning from memorization. It encompasses, as special cases, classical notions from Kolmogorov complexity, Shannon, and Fisher Information. However, unlike some of those frameworks, it can be applied to lar"},"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":"1904.03292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T21:46:27Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"cfc7b11bbfe46474ffeaccefe86899fcc5ae722862f9dd67ff614d82c877d4e2","abstract_canon_sha256":"fb255b3fbc57476c4cc4323ab1a19a97ffa069bde6d9580588e83bda66197abe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:15.201103Z","signature_b64":"LDQpkXaz6gE5xRvmD4BHycz7NxjgA9UxOD/xuCbAaTl95wkL2zyVzyD1rMe04YrZTkbHssyAskuzLry/rk0dCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3db5c0e8d253941e3d9f841fe782a0b6ced1f28f27a600846a5c17373759f7d","last_reissued_at":"2026-07-05T01:18:15.200659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:15.200659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Information Complexity of Learning Tasks, their Structure and their Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Achille, Giovanni Paolini, Glen Mbeng, Stefano Soatto","submitted_at":"2019-04-05T21:46:27Z","abstract_excerpt":"We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learning, whereby a parametric model is pre-trained for a task, and then fine-tuned for another. The framework we develop is non-asymptotic, captures the finite nature of the training dataset, and allows distinguishing learning from memorization. It encompasses, as special cases, classical notions from Kolmogorov complexity, Shannon, and Fisher Information. However, unlike some of those frameworks, it can be applied to lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03292","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/1904.03292/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":"1904.03292","created_at":"2026-07-05T01:18:15.200716+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03292v2","created_at":"2026-07-05T01:18:15.200716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03292","created_at":"2026-07-05T01:18:15.200716+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PNVYDUNEU4U","created_at":"2026-07-05T01:18:15.200716+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PNVYDUNEU4UDY6Z","created_at":"2026-07-05T01:18:15.200716+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PNVYDUN","created_at":"2026-07-05T01:18:15.200716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.08142","citing_title":"Transferability and Hardness of Supervised Classification Tasks","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN","json":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN.json","graph_json":"https://pith.science/api/pith-number/4PNVYDUNEU4UDY6Z7BA746BKBN/graph.json","events_json":"https://pith.science/api/pith-number/4PNVYDUNEU4UDY6Z7BA746BKBN/events.json","paper":"https://pith.science/paper/4PNVYDUN"},"agent_actions":{"view_html":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN","download_json":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN.json","view_paper":"https://pith.science/paper/4PNVYDUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03292&json=true","fetch_graph":"https://pith.science/api/pith-number/4PNVYDUNEU4UDY6Z7BA746BKBN/graph.json","fetch_events":"https://pith.science/api/pith-number/4PNVYDUNEU4UDY6Z7BA746BKBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN/action/storage_attestation","attest_author":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN/action/author_attestation","sign_citation":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN/action/citation_signature","submit_replication":"https://pith.science/pith/4PNVYDUNEU4UDY6Z7BA746BKBN/action/replication_record"}},"created_at":"2026-07-05T01:18:15.200716+00:00","updated_at":"2026-07-05T01:18:15.200716+00:00"}