{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZEXJMCXFE5JSG6TDE7FPHYH4AA","short_pith_number":"pith:ZEXJMCXF","schema_version":"1.0","canonical_sha256":"c92e960ae52753237a6327caf3e0fc001391ac1bb0b0fc50aee49c8ce7de2215","source":{"kind":"arxiv","id":"2409.01890","version":1},"attestation_state":"computed","paper":{"title":"A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew McCallum, Manzil Zaheer, Michael Boratko, Nicholas Monath, Rob Fergus, Will Grathwohl","submitted_at":"2024-09-03T13:29:13Z","abstract_excerpt":"In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e.g., textual passages for information retrieval). Significant challenges arise in training such encoders in the increasingly prevalent scenario of (1) a large number of targets, (2) a computationally expensive target encoder model, (3) cached target embeddings that are out-of-date due to ongoing training of target encoder parameters. This paper presents a simple and highly scalable response to these challeng"},"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":"2409.01890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-03T13:29:13Z","cross_cats_sorted":[],"title_canon_sha256":"0525435a5ea77ee2b37e2c687f821ff51693ff84490dc056a0b60b057c3e978d","abstract_canon_sha256":"eb11c20486bb00e27607e3af2f97c5fde0b27cc1d7511a947f9e889b6b50fd44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:35.476686Z","signature_b64":"bNOzT96UC58GRPiWkY449oM/5GO+BHv33DLhY/4wu9h5/rPfyYfnjZbhwaAbcfp6X+b/eQfz98lv32lvxatvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c92e960ae52753237a6327caf3e0fc001391ac1bb0b0fc50aee49c8ce7de2215","last_reissued_at":"2026-07-05T09:02:35.475945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:35.475945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew McCallum, Manzil Zaheer, Michael Boratko, Nicholas Monath, Rob Fergus, Will Grathwohl","submitted_at":"2024-09-03T13:29:13Z","abstract_excerpt":"In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e.g., textual passages for information retrieval). Significant challenges arise in training such encoders in the increasingly prevalent scenario of (1) a large number of targets, (2) a computationally expensive target encoder model, (3) cached target embeddings that are out-of-date due to ongoing training of target encoder parameters. This paper presents a simple and highly scalable response to these challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01890","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/2409.01890/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":"2409.01890","created_at":"2026-07-05T09:02:35.476145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01890v1","created_at":"2026-07-05T09:02:35.476145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01890","created_at":"2026-07-05T09:02:35.476145+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEXJMCXFE5JS","created_at":"2026-07-05T09:02:35.476145+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEXJMCXFE5JSG6TD","created_at":"2026-07-05T09:02:35.476145+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEXJMCXF","created_at":"2026-07-05T09:02:35.476145+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/ZEXJMCXFE5JSG6TDE7FPHYH4AA","json":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA.json","graph_json":"https://pith.science/api/pith-number/ZEXJMCXFE5JSG6TDE7FPHYH4AA/graph.json","events_json":"https://pith.science/api/pith-number/ZEXJMCXFE5JSG6TDE7FPHYH4AA/events.json","paper":"https://pith.science/paper/ZEXJMCXF"},"agent_actions":{"view_html":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA","download_json":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA.json","view_paper":"https://pith.science/paper/ZEXJMCXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01890&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEXJMCXFE5JSG6TDE7FPHYH4AA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEXJMCXFE5JSG6TDE7FPHYH4AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA/action/storage_attestation","attest_author":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA/action/author_attestation","sign_citation":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA/action/citation_signature","submit_replication":"https://pith.science/pith/ZEXJMCXFE5JSG6TDE7FPHYH4AA/action/replication_record"}},"created_at":"2026-07-05T09:02:35.476145+00:00","updated_at":"2026-07-05T09:02:35.476145+00:00"}