{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UJS7CDBIUR23UA6XHW22WZE4RA","short_pith_number":"pith:UJS7CDBI","schema_version":"1.0","canonical_sha256":"a265f10c28a475ba03d73db5ab649c8833465e0637ccdea0306b6ded8b8b0c59","source":{"kind":"arxiv","id":"2311.13583","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anshumali Shrivastava, Benito Geordie, Benjamin Coleman, Shabnam Daghaghi","submitted_at":"2023-11-22T18:40:18Z","abstract_excerpt":"Data sampling is an effective method to improve the training speed of neural networks, with recent results demonstrating that it can even break the neural scaling laws. These results critically rely on high-quality scores to estimate the importance of an input to the network. We observe that there are two dominant strategies: static sampling, where the scores are determined before training, and dynamic sampling, where the scores can depend on the model weights. Static algorithms are computationally inexpensive but less effective than their dynamic counterparts, which can cause end-to-end slowd"},"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":"2311.13583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:40:18Z","cross_cats_sorted":[],"title_canon_sha256":"09e3ab285fe569a029c0839685c82170f0c2e5575571c979b29a09425a848ce0","abstract_canon_sha256":"8ae19e35b61e5068f1eee411fe373896bf0db92c1ac04f889c33ae88a4eeadf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:40.445894Z","signature_b64":"LnasugcK1ebcfZcv92rlo/t506rUVc5MdxiB3S0s+BO9UwG1HVCumBdqT+Cyy0gF7iTh2APoZ6AHKkWpjWCJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a265f10c28a475ba03d73db5ab649c8833465e0637ccdea0306b6ded8b8b0c59","last_reissued_at":"2026-07-05T07:15:40.445445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:40.445445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anshumali Shrivastava, Benito Geordie, Benjamin Coleman, Shabnam Daghaghi","submitted_at":"2023-11-22T18:40:18Z","abstract_excerpt":"Data sampling is an effective method to improve the training speed of neural networks, with recent results demonstrating that it can even break the neural scaling laws. These results critically rely on high-quality scores to estimate the importance of an input to the network. We observe that there are two dominant strategies: static sampling, where the scores are determined before training, and dynamic sampling, where the scores can depend on the model weights. Static algorithms are computationally inexpensive but less effective than their dynamic counterparts, which can cause end-to-end slowd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13583","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/2311.13583/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":"2311.13583","created_at":"2026-07-05T07:15:40.445499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13583v1","created_at":"2026-07-05T07:15:40.445499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13583","created_at":"2026-07-05T07:15:40.445499+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJS7CDBIUR23","created_at":"2026-07-05T07:15:40.445499+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJS7CDBIUR23UA6X","created_at":"2026-07-05T07:15:40.445499+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJS7CDBI","created_at":"2026-07-05T07:15:40.445499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07207","citing_title":"Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA","json":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA.json","graph_json":"https://pith.science/api/pith-number/UJS7CDBIUR23UA6XHW22WZE4RA/graph.json","events_json":"https://pith.science/api/pith-number/UJS7CDBIUR23UA6XHW22WZE4RA/events.json","paper":"https://pith.science/paper/UJS7CDBI"},"agent_actions":{"view_html":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA","download_json":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA.json","view_paper":"https://pith.science/paper/UJS7CDBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13583&json=true","fetch_graph":"https://pith.science/api/pith-number/UJS7CDBIUR23UA6XHW22WZE4RA/graph.json","fetch_events":"https://pith.science/api/pith-number/UJS7CDBIUR23UA6XHW22WZE4RA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA/action/storage_attestation","attest_author":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA/action/author_attestation","sign_citation":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA/action/citation_signature","submit_replication":"https://pith.science/pith/UJS7CDBIUR23UA6XHW22WZE4RA/action/replication_record"}},"created_at":"2026-07-05T07:15:40.445499+00:00","updated_at":"2026-07-05T07:15:40.445499+00:00"}