{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7GU62A5OJVHBZWLXQJW337PUSF","short_pith_number":"pith:7GU62A5O","schema_version":"1.0","canonical_sha256":"f9a9ed03ae4d4e1cd977826dbdfdf4916f459ac890ee6161458500c9a71a239d","source":{"kind":"arxiv","id":"1810.03025","version":1},"attestation_state":"computed","paper":{"title":"Discretizing Logged Interaction Data Biases Learning for Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"stat.ML","authors_text":"Peter Schulam, Suchi Saria","submitted_at":"2018-10-06T17:08:47Z","abstract_excerpt":"Time series data that are not measured at regular intervals are commonly discretized as a preprocessing step. For example, data about customer arrival times might be simplified by summing the number of arrivals within hourly intervals, which produces a discrete-time time series that is easier to model. In this abstract, we show that discretization introduces a bias that affects models trained for decision-making. We refer to this phenomenon as discretization bias, and show that we can avoid it by using continuous-time models instead."},"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":"1810.03025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-06T17:08:47Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"title_canon_sha256":"e532e8501be041703efc3240f57760db17d991c8baf7320c0d0e7f98a163e6f4","abstract_canon_sha256":"e413e1922a03c185a2fbcb716bf2c3c86d63a37afa2a0d4a510ac7fd03311000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:54.780397Z","signature_b64":"u0RkWNSntekYJHhD4YPl3nMe6VDdjz4FubWgDnx3GhbhBql/jidJd+ZMwB+w51XMED5M9UFztB54pczHMelWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9a9ed03ae4d4e1cd977826dbdfdf4916f459ac890ee6161458500c9a71a239d","last_reissued_at":"2026-05-18T00:03:54.779738Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:54.779738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discretizing Logged Interaction Data Biases Learning for Decision-Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"stat.ML","authors_text":"Peter Schulam, Suchi Saria","submitted_at":"2018-10-06T17:08:47Z","abstract_excerpt":"Time series data that are not measured at regular intervals are commonly discretized as a preprocessing step. For example, data about customer arrival times might be simplified by summing the number of arrivals within hourly intervals, which produces a discrete-time time series that is easier to model. In this abstract, we show that discretization introduces a bias that affects models trained for decision-making. We refer to this phenomenon as discretization bias, and show that we can avoid it by using continuous-time models instead."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03025","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":""},"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":"1810.03025","created_at":"2026-05-18T00:03:54.779832+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03025v1","created_at":"2026-05-18T00:03:54.779832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03025","created_at":"2026-05-18T00:03:54.779832+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GU62A5OJVHB","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GU62A5OJVHBZWLX","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GU62A5O","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.06603","citing_title":"The hidden risks of temporal resampling in clinical reinforcement learning","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF","json":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF.json","graph_json":"https://pith.science/api/pith-number/7GU62A5OJVHBZWLXQJW337PUSF/graph.json","events_json":"https://pith.science/api/pith-number/7GU62A5OJVHBZWLXQJW337PUSF/events.json","paper":"https://pith.science/paper/7GU62A5O"},"agent_actions":{"view_html":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF","download_json":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF.json","view_paper":"https://pith.science/paper/7GU62A5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03025&json=true","fetch_graph":"https://pith.science/api/pith-number/7GU62A5OJVHBZWLXQJW337PUSF/graph.json","fetch_events":"https://pith.science/api/pith-number/7GU62A5OJVHBZWLXQJW337PUSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF/action/storage_attestation","attest_author":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF/action/author_attestation","sign_citation":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF/action/citation_signature","submit_replication":"https://pith.science/pith/7GU62A5OJVHBZWLXQJW337PUSF/action/replication_record"}},"created_at":"2026-05-18T00:03:54.779832+00:00","updated_at":"2026-05-18T00:03:54.779832+00:00"}