{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CC3WETSPPKCI7JBBL66NHCPF4N","short_pith_number":"pith:CC3WETSP","schema_version":"1.0","canonical_sha256":"10b7624e4f7a848fa4215fbcd389e5e356f431e35f9873c6d9af438d84177fa5","source":{"kind":"arxiv","id":"2506.01877","version":1},"attestation_state":"computed","paper":{"title":"When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dayoon Ko, Gunhee Kim, Jaehoon Lee, Jinhyuk Kim, Jinyoung Kim, Minyoung Lee, Seonghak Song, Sohyeon Kim","submitted_at":"2025-06-02T17:06:35Z","abstract_excerpt":"Dense retrievers encode texts into embeddings to efficiently retrieve relevant documents from large databases in response to user queries. However, real-world corpora continually evolve, leading to a shift from the original training distribution of the retriever. Without timely updates or retraining, indexing newly emerging documents can degrade retrieval performance for future queries. Thus, identifying when a dense retriever requires an update is critical for maintaining robust retrieval systems. In this paper, we propose a novel task of predicting whether a corpus is out-of-distribution (OO"},"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":"2506.01877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-02T17:06:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9355d7b1a32f9cfb868c8fe42dd485e72114e2882163d00bfb8df080bf25a742","abstract_canon_sha256":"ac4831c12285a7b23e63be2a4cfe55ccffcdfb43a920b5db33dfb5f1a0712fbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:20.780868Z","signature_b64":"zfrH28vBw7XElBL0zoW+bRelwTB66gfn1AeC8a6890JWqOBb2EEgeeVJZk80N5/rPbTt8G8G7UaJ/eMedY2mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10b7624e4f7a848fa4215fbcd389e5e356f431e35f9873c6d9af438d84177fa5","last_reissued_at":"2026-07-05T11:14:20.780477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:20.780477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Dayoon Ko, Gunhee Kim, Jaehoon Lee, Jinhyuk Kim, Jinyoung Kim, Minyoung Lee, Seonghak Song, Sohyeon Kim","submitted_at":"2025-06-02T17:06:35Z","abstract_excerpt":"Dense retrievers encode texts into embeddings to efficiently retrieve relevant documents from large databases in response to user queries. However, real-world corpora continually evolve, leading to a shift from the original training distribution of the retriever. Without timely updates or retraining, indexing newly emerging documents can degrade retrieval performance for future queries. Thus, identifying when a dense retriever requires an update is critical for maintaining robust retrieval systems. In this paper, we propose a novel task of predicting whether a corpus is out-of-distribution (OO"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01877","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/2506.01877/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":"2506.01877","created_at":"2026-07-05T11:14:20.780528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01877v1","created_at":"2026-07-05T11:14:20.780528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01877","created_at":"2026-07-05T11:14:20.780528+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC3WETSPPKCI","created_at":"2026-07-05T11:14:20.780528+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC3WETSPPKCI7JBB","created_at":"2026-07-05T11:14:20.780528+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC3WETSP","created_at":"2026-07-05T11:14:20.780528+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/CC3WETSPPKCI7JBBL66NHCPF4N","json":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N.json","graph_json":"https://pith.science/api/pith-number/CC3WETSPPKCI7JBBL66NHCPF4N/graph.json","events_json":"https://pith.science/api/pith-number/CC3WETSPPKCI7JBBL66NHCPF4N/events.json","paper":"https://pith.science/paper/CC3WETSP"},"agent_actions":{"view_html":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N","download_json":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N.json","view_paper":"https://pith.science/paper/CC3WETSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01877&json=true","fetch_graph":"https://pith.science/api/pith-number/CC3WETSPPKCI7JBBL66NHCPF4N/graph.json","fetch_events":"https://pith.science/api/pith-number/CC3WETSPPKCI7JBBL66NHCPF4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N/action/storage_attestation","attest_author":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N/action/author_attestation","sign_citation":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N/action/citation_signature","submit_replication":"https://pith.science/pith/CC3WETSPPKCI7JBBL66NHCPF4N/action/replication_record"}},"created_at":"2026-07-05T11:14:20.780528+00:00","updated_at":"2026-07-05T11:14:20.780528+00:00"}