{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:46YFJF7KJ73YX5UAURMVBQ7F65","short_pith_number":"pith:46YFJF7K","schema_version":"1.0","canonical_sha256":"e7b05497ea4ff78bf680a45950c3e5f754cea050e23ef2f271121f58eed50bd3","source":{"kind":"arxiv","id":"1809.08415","version":1},"attestation_state":"computed","paper":{"title":"Differentiable Unbiased Online Learning to Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Harrie Oosterhuis, Maarten de Rijke","submitted_at":"2018-09-22T09:19:21Z","abstract_excerpt":"Online Learning to Rank (OLTR) methods optimize rankers based on user interactions. State-of-the-art OLTR methods are built specifically for linear models. Their approaches do not extend well to non-linear models such as neural networks. We introduce an entirely novel approach to OLTR that constructs a weighted differentiable pairwise loss after each interaction: Pairwise Differentiable Gradient Descent (PDGD). PDGD breaks away from the traditional approach that relies on interleaving or multileaving and extensive sampling of models to estimate gradients. Instead, its gradient is based on infe"},"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":"1809.08415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-09-22T09:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"be115ab99f9000a6f3ad8c6bf4143a9c2e9a54c7c3f8b5208174fd62bbbd5b86","abstract_canon_sha256":"aad742be676d86d885a78f10630e10fb3dc5889d5e0d9e8da9da8ff6c459dc67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:08.575429Z","signature_b64":"nBwdxoC2uj2zADToIVJH+kLdmc8u6uNBn/q5b6+GOgt/FvuMqAR1cghlf2BDaMxdrB+SDLwdY0DR8zQxtu/nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7b05497ea4ff78bf680a45950c3e5f754cea050e23ef2f271121f58eed50bd3","last_reissued_at":"2026-05-18T00:05:08.574952Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:08.574952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Unbiased Online Learning to Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Harrie Oosterhuis, Maarten de Rijke","submitted_at":"2018-09-22T09:19:21Z","abstract_excerpt":"Online Learning to Rank (OLTR) methods optimize rankers based on user interactions. State-of-the-art OLTR methods are built specifically for linear models. Their approaches do not extend well to non-linear models such as neural networks. We introduce an entirely novel approach to OLTR that constructs a weighted differentiable pairwise loss after each interaction: Pairwise Differentiable Gradient Descent (PDGD). PDGD breaks away from the traditional approach that relies on interleaving or multileaving and extensive sampling of models to estimate gradients. Instead, its gradient is based on infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08415","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":"1809.08415","created_at":"2026-05-18T00:05:08.575019+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.08415v1","created_at":"2026-05-18T00:05:08.575019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08415","created_at":"2026-05-18T00:05:08.575019+00:00"},{"alias_kind":"pith_short_12","alias_value":"46YFJF7KJ73Y","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"46YFJF7KJ73YX5UA","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"46YFJF7K","created_at":"2026-05-18T12:32:05.422762+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/46YFJF7KJ73YX5UAURMVBQ7F65","json":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65.json","graph_json":"https://pith.science/api/pith-number/46YFJF7KJ73YX5UAURMVBQ7F65/graph.json","events_json":"https://pith.science/api/pith-number/46YFJF7KJ73YX5UAURMVBQ7F65/events.json","paper":"https://pith.science/paper/46YFJF7K"},"agent_actions":{"view_html":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65","download_json":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65.json","view_paper":"https://pith.science/paper/46YFJF7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.08415&json=true","fetch_graph":"https://pith.science/api/pith-number/46YFJF7KJ73YX5UAURMVBQ7F65/graph.json","fetch_events":"https://pith.science/api/pith-number/46YFJF7KJ73YX5UAURMVBQ7F65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65/action/storage_attestation","attest_author":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65/action/author_attestation","sign_citation":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65/action/citation_signature","submit_replication":"https://pith.science/pith/46YFJF7KJ73YX5UAURMVBQ7F65/action/replication_record"}},"created_at":"2026-05-18T00:05:08.575019+00:00","updated_at":"2026-05-18T00:05:08.575019+00:00"}