{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7AXTEYZETGNO7MROT7DQ6DJMI","short_pith_number":"pith:Y7AXTEYZ","schema_version":"1.0","canonical_sha256":"c7c179931924ccd77d9174fe387869623726f5b69d45f1666e3bab8e7a250024","source":{"kind":"arxiv","id":"2606.02814","version":1},"attestation_state":"computed","paper":{"title":"Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Edgar Altszyler, Francisco Valentini, Martin Fajcik","submitted_at":"2026-06-01T19:31:28Z","abstract_excerpt":"Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and this selection can favor certain document types over others. We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior: a query-independent signal encoded in their representation space as a side effect of training on annotated data. We estimate this prior by training simple classifiers on frozen document embeddings and evaluate th"},"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":"2606.02814","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-01T19:31:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4e4537e3fede01ab0041ac31da51580ac764d27ce445bdec04865809d1096d78","abstract_canon_sha256":"b502011b685c2bb8135d28821c95936cc69f611d39c782549ea5fe448156dc19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:23.685594Z","signature_b64":"dcWnXSJ59hMrE8HtTeSqW374SGzrSHO7c3RgF5+E/RIo07TdUDZk/Zx893fpEryycVTyVqEBv0MVQONlhAXfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c179931924ccd77d9174fe387869623726f5b69d45f1666e3bab8e7a250024","last_reissued_at":"2026-06-03T01:05:23.685222Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:23.685222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Edgar Altszyler, Francisco Valentini, Martin Fajcik","submitted_at":"2026-06-01T19:31:28Z","abstract_excerpt":"Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and this selection can favor certain document types over others. We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior: a query-independent signal encoded in their representation space as a side effect of training on annotated data. We estimate this prior by training simple classifiers on frozen document embeddings and evaluate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02814","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/2606.02814/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":"2606.02814","created_at":"2026-06-03T01:05:23.685284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02814v1","created_at":"2026-06-03T01:05:23.685284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02814","created_at":"2026-06-03T01:05:23.685284+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7AXTEYZETGN","created_at":"2026-06-03T01:05:23.685284+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7AXTEYZETGNO7MR","created_at":"2026-06-03T01:05:23.685284+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7AXTEYZ","created_at":"2026-06-03T01:05:23.685284+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/Y7AXTEYZETGNO7MROT7DQ6DJMI","json":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI.json","graph_json":"https://pith.science/api/pith-number/Y7AXTEYZETGNO7MROT7DQ6DJMI/graph.json","events_json":"https://pith.science/api/pith-number/Y7AXTEYZETGNO7MROT7DQ6DJMI/events.json","paper":"https://pith.science/paper/Y7AXTEYZ"},"agent_actions":{"view_html":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI","download_json":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI.json","view_paper":"https://pith.science/paper/Y7AXTEYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02814&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7AXTEYZETGNO7MROT7DQ6DJMI/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7AXTEYZETGNO7MROT7DQ6DJMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI/action/storage_attestation","attest_author":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI/action/author_attestation","sign_citation":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI/action/citation_signature","submit_replication":"https://pith.science/pith/Y7AXTEYZETGNO7MROT7DQ6DJMI/action/replication_record"}},"created_at":"2026-06-03T01:05:23.685284+00:00","updated_at":"2026-06-03T01:05:23.685284+00:00"}