{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O6ZEAPRTD5DTBG6OPLZJJGXAEJ","short_pith_number":"pith:O6ZEAPRT","schema_version":"1.0","canonical_sha256":"77b2403e331f47309bce7af2949ae0225ab74190464b45f11fa0fe5ac4c8b8d4","source":{"kind":"arxiv","id":"2212.06121","version":1},"attestation_state":"computed","paper":{"title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guilherme Rosa, Hugo Abonizio, Luiz Bonifacio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2022-12-12T18:50:03Z","abstract_excerpt":"Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines. In this work we study the generalization ability of these two types of architectures on a wide range of parameter count on both in-domain and out-of-domain scenarios. We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furth"},"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":"2212.06121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-12-12T18:50:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b4f79084246f0aa82237c4f586ce7011392d7e3f9477ca6b02b01e6217b2fcab","abstract_canon_sha256":"b4232e9c97561a70358a6ca3069d812960a801050cfdb8073a5104aa9e9cb558"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:22.869450Z","signature_b64":"rAdIU+3G9tNA9kPsjEAVnB10ipyEi9J0UEuUWp/Kq2QeJ/dDkeZ/KWCPulYAik7Dzt+FDPI2K7Yed8gocTenDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77b2403e331f47309bce7af2949ae0225ab74190464b45f11fa0fe5ac4c8b8d4","last_reissued_at":"2026-07-05T05:24:22.869032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:22.869032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guilherme Rosa, Hugo Abonizio, Luiz Bonifacio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2022-12-12T18:50:03Z","abstract_excerpt":"Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines. In this work we study the generalization ability of these two types of architectures on a wide range of parameter count on both in-domain and out-of-domain scenarios. We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06121","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/2212.06121/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":"2212.06121","created_at":"2026-07-05T05:24:22.869087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06121v1","created_at":"2026-07-05T05:24:22.869087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06121","created_at":"2026-07-05T05:24:22.869087+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6ZEAPRTD5DT","created_at":"2026-07-05T05:24:22.869087+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6ZEAPRTD5DTBG6O","created_at":"2026-07-05T05:24:22.869087+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6ZEAPRT","created_at":"2026-07-05T05:24:22.869087+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/O6ZEAPRTD5DTBG6OPLZJJGXAEJ","json":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ.json","graph_json":"https://pith.science/api/pith-number/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/graph.json","events_json":"https://pith.science/api/pith-number/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/events.json","paper":"https://pith.science/paper/O6ZEAPRT"},"agent_actions":{"view_html":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ","download_json":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ.json","view_paper":"https://pith.science/paper/O6ZEAPRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06121&json=true","fetch_graph":"https://pith.science/api/pith-number/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/action/storage_attestation","attest_author":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/action/author_attestation","sign_citation":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/action/citation_signature","submit_replication":"https://pith.science/pith/O6ZEAPRTD5DTBG6OPLZJJGXAEJ/action/replication_record"}},"created_at":"2026-07-05T05:24:22.869087+00:00","updated_at":"2026-07-05T05:24:22.869087+00:00"}