{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3736LWURCIRSPZZPXGHABR4TBG","short_pith_number":"pith:3736LWUR","schema_version":"1.0","canonical_sha256":"dff7e5da91122327e72fb98e00c79309a239a827ab31e6805cd806a8a1b2a306","source":{"kind":"arxiv","id":"2411.03768","version":1},"attestation_state":"computed","paper":{"title":"A Bayesian Approach to Data Point Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brais Martinez, Minyoung Kim, Royson Lee, Timothy Hospedales, Xinnuo Xu","submitted_at":"2024-11-06T09:04:13Z","abstract_excerpt":"Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or processed data. Existing approaches to DPS are predominantly based on a bi-level optimisation (BLO) formulation, which is demanding in terms of memory and computation, and exhibits some theoretical defects regarding minibatches. Thus, we propose a novel Bayesian approach to DPS. We view the DPS problem as posterior inference in a novel Bayesian model where the posterior distributions of the instance-wise weights and the"},"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":"2411.03768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-06T09:04:13Z","cross_cats_sorted":[],"title_canon_sha256":"a491b3d7345a415c3bd1894ca45581204d1d4a2ee6eb139ff3df9b8d1e8d1e1f","abstract_canon_sha256":"dc3e3257ef370ef608f46fd234f3e64bfd8d8850ee38c65544d073d3e76c7915"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:55.696259Z","signature_b64":"uk/dWnO1ceeo5pVxbltCWPGpkWDAoV4XsRjsFN9j7e9DBJwNKeskvL+QsPiBHTyqSs2uDUrd+lhuBHmBtTGiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dff7e5da91122327e72fb98e00c79309a239a827ab31e6805cd806a8a1b2a306","last_reissued_at":"2026-07-05T09:31:55.695824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:55.695824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bayesian Approach to Data Point Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brais Martinez, Minyoung Kim, Royson Lee, Timothy Hospedales, Xinnuo Xu","submitted_at":"2024-11-06T09:04:13Z","abstract_excerpt":"Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or processed data. Existing approaches to DPS are predominantly based on a bi-level optimisation (BLO) formulation, which is demanding in terms of memory and computation, and exhibits some theoretical defects regarding minibatches. Thus, we propose a novel Bayesian approach to DPS. We view the DPS problem as posterior inference in a novel Bayesian model where the posterior distributions of the instance-wise weights and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03768","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/2411.03768/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":"2411.03768","created_at":"2026-07-05T09:31:55.695883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03768v1","created_at":"2026-07-05T09:31:55.695883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03768","created_at":"2026-07-05T09:31:55.695883+00:00"},{"alias_kind":"pith_short_12","alias_value":"3736LWURCIRS","created_at":"2026-07-05T09:31:55.695883+00:00"},{"alias_kind":"pith_short_16","alias_value":"3736LWURCIRSPZZP","created_at":"2026-07-05T09:31:55.695883+00:00"},{"alias_kind":"pith_short_8","alias_value":"3736LWUR","created_at":"2026-07-05T09:31:55.695883+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/3736LWURCIRSPZZPXGHABR4TBG","json":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG.json","graph_json":"https://pith.science/api/pith-number/3736LWURCIRSPZZPXGHABR4TBG/graph.json","events_json":"https://pith.science/api/pith-number/3736LWURCIRSPZZPXGHABR4TBG/events.json","paper":"https://pith.science/paper/3736LWUR"},"agent_actions":{"view_html":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG","download_json":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG.json","view_paper":"https://pith.science/paper/3736LWUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03768&json=true","fetch_graph":"https://pith.science/api/pith-number/3736LWURCIRSPZZPXGHABR4TBG/graph.json","fetch_events":"https://pith.science/api/pith-number/3736LWURCIRSPZZPXGHABR4TBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG/action/storage_attestation","attest_author":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG/action/author_attestation","sign_citation":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG/action/citation_signature","submit_replication":"https://pith.science/pith/3736LWURCIRSPZZPXGHABR4TBG/action/replication_record"}},"created_at":"2026-07-05T09:31:55.695883+00:00","updated_at":"2026-07-05T09:31:55.695883+00:00"}