{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5V2MNCMPMWP6ZNQIYRTKRYM6X7","short_pith_number":"pith:5V2MNCMP","schema_version":"1.0","canonical_sha256":"ed74c6898f659fecb608c466a8e19ebffa823cc5b383301c496def00fc73e0af","source":{"kind":"arxiv","id":"2004.10915","version":1},"attestation_state":"computed","paper":{"title":"Doubly-stochastic mining for heterogeneous retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Krishna Menon, Andreas Veit, Ankit Singh Rawat, Felix Yu, Sanjiv Kumar, Sashank J. Reddi","submitted_at":"2020-04-23T00:43:13Z","abstract_excerpt":"Modern retrieval problems are characterised by training sets with potentially billions of labels, and heterogeneous data distributions across subpopulations (e.g., users of a retrieval system may be from different countries), each of which poses a challenge. The first challenge concerns scalability: with a large number of labels, standard losses are difficult to optimise even on a single example. The second challenge concerns uniformity: one ideally wants good performance on each subpopulation. While several solutions have been proposed to address the first challenge, the second challenge has "},"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":"2004.10915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-23T00:43:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c5513b362854d64cdbd21dfc1a8b71a42b0d8770dded9848e0a9a1000186fe57","abstract_canon_sha256":"ebca69fe7a905e28f8a6fc9285216aa0b30039a37cbe09d9f3e4f7c09ebb6208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:57:37.274698Z","signature_b64":"kxWAlsvXh2nHFd9SFwo7NtnF34J0X7bORJRoHzEG9hS49oduHCuqYKrn3l7yGoS9kK59JOCY4C/FYDLkSPUqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed74c6898f659fecb608c466a8e19ebffa823cc5b383301c496def00fc73e0af","last_reissued_at":"2026-07-05T00:57:37.274251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:57:37.274251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly-stochastic mining for heterogeneous retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Krishna Menon, Andreas Veit, Ankit Singh Rawat, Felix Yu, Sanjiv Kumar, Sashank J. Reddi","submitted_at":"2020-04-23T00:43:13Z","abstract_excerpt":"Modern retrieval problems are characterised by training sets with potentially billions of labels, and heterogeneous data distributions across subpopulations (e.g., users of a retrieval system may be from different countries), each of which poses a challenge. The first challenge concerns scalability: with a large number of labels, standard losses are difficult to optimise even on a single example. The second challenge concerns uniformity: one ideally wants good performance on each subpopulation. While several solutions have been proposed to address the first challenge, the second challenge has "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.10915","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/2004.10915/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":"2004.10915","created_at":"2026-07-05T00:57:37.274307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.10915v1","created_at":"2026-07-05T00:57:37.274307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.10915","created_at":"2026-07-05T00:57:37.274307+00:00"},{"alias_kind":"pith_short_12","alias_value":"5V2MNCMPMWP6","created_at":"2026-07-05T00:57:37.274307+00:00"},{"alias_kind":"pith_short_16","alias_value":"5V2MNCMPMWP6ZNQI","created_at":"2026-07-05T00:57:37.274307+00:00"},{"alias_kind":"pith_short_8","alias_value":"5V2MNCMP","created_at":"2026-07-05T00:57:37.274307+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/5V2MNCMPMWP6ZNQIYRTKRYM6X7","json":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7.json","graph_json":"https://pith.science/api/pith-number/5V2MNCMPMWP6ZNQIYRTKRYM6X7/graph.json","events_json":"https://pith.science/api/pith-number/5V2MNCMPMWP6ZNQIYRTKRYM6X7/events.json","paper":"https://pith.science/paper/5V2MNCMP"},"agent_actions":{"view_html":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7","download_json":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7.json","view_paper":"https://pith.science/paper/5V2MNCMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.10915&json=true","fetch_graph":"https://pith.science/api/pith-number/5V2MNCMPMWP6ZNQIYRTKRYM6X7/graph.json","fetch_events":"https://pith.science/api/pith-number/5V2MNCMPMWP6ZNQIYRTKRYM6X7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7/action/storage_attestation","attest_author":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7/action/author_attestation","sign_citation":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7/action/citation_signature","submit_replication":"https://pith.science/pith/5V2MNCMPMWP6ZNQIYRTKRYM6X7/action/replication_record"}},"created_at":"2026-07-05T00:57:37.274307+00:00","updated_at":"2026-07-05T00:57:37.274307+00:00"}