{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H2HRLEBQE7GH6PFTVHGU6GXTHG","short_pith_number":"pith:H2HRLEBQ","canonical_record":{"source":{"id":"2301.12052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:07:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"943efe77296ec5f06f0b6f83ba3641a87c22bfc79834840a6c74f1c990b0c5a5","abstract_canon_sha256":"5ef885a3b9f8c7e9d9853f1de215a3a3d7255b28b77976988a531169a58ec204"},"schema_version":"1.0"},"canonical_sha256":"3e8f15903027cc7f3cb3a9cd4f1af339a74f65c5f437a5323eea704d763fa5df","source":{"kind":"arxiv","id":"2301.12052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12052","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12052v1","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12052","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_12","alias_value":"H2HRLEBQE7GH","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_16","alias_value":"H2HRLEBQE7GH6PFT","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_8","alias_value":"H2HRLEBQ","created_at":"2026-07-05T05:36:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H2HRLEBQE7GH6PFTVHGU6GXTHG","target":"record","payload":{"canonical_record":{"source":{"id":"2301.12052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:07:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"943efe77296ec5f06f0b6f83ba3641a87c22bfc79834840a6c74f1c990b0c5a5","abstract_canon_sha256":"5ef885a3b9f8c7e9d9853f1de215a3a3d7255b28b77976988a531169a58ec204"},"schema_version":"1.0"},"canonical_sha256":"3e8f15903027cc7f3cb3a9cd4f1af339a74f65c5f437a5323eea704d763fa5df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:34.697595Z","signature_b64":"HomT2bRFRkQrRjmdYt1b2QTrX19s48E2BWo2B+ABFy3ukXd685On0WKne7ZhwQcJLW4n8j9y2YougWPiMqq1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8f15903027cc7f3cb3a9cd4f1af339a74f65c5f437a5323eea704d763fa5df","last_reissued_at":"2026-07-05T05:36:34.697102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:34.697102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.12052","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mkJtI8G+tUqkjzW4aVFnDRToz6wtRJYwETX7aHKv6j0TAs9nYany7SxhFUtlVjVP8Xb5+EST4qhz2Rt9iPBrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:36:42.450850Z"},"content_sha256":"a2610aab5a32971a3d0cede1b317356a7b288b1d5df574c6c3d3e1e9db7e31d0","schema_version":"1.0","event_id":"sha256:a2610aab5a32971a3d0cede1b317356a7b288b1d5df574c6c3d3e1e9db7e31d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H2HRLEBQE7GH6PFTVHGU6GXTHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Importance Weights in Subset Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Giulia DeSalvo, Gui Citovsky, Sanjiv Kumar, Srikumar Ramalingam, Yunjuan Wang","submitted_at":"2023-01-28T02:07:31Z","abstract_excerpt":"We present a subset selection algorithm designed to work with arbitrary model families in a practical batch setting. In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i.e. further train model weights) once a large enough batch of examples is selected. Our algorithm, IWeS, selects examples by importance sampling where the sampling probability assigned to each example is based on the entropy of models trained on previously selected batches. IWeS admits significant performance improvement compared to other su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12052","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/2301.12052/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3v+uBuPWgsNngQsIcnpI0b4H7v9jc3+ioQCUESLe+xO2WlsI043q2/4x+J+xBC4eRdi7upIUqcYB9Q/1TwByCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:36:42.451342Z"},"content_sha256":"b0725f38e3f16552d102114907958597d99f7c69b4c946d7e57e551a9137a8c0","schema_version":"1.0","event_id":"sha256:b0725f38e3f16552d102114907958597d99f7c69b4c946d7e57e551a9137a8c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG/bundle.json","state_url":"https://pith.science/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T04:36:42Z","links":{"resolver":"https://pith.science/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG","bundle":"https://pith.science/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG/bundle.json","state":"https://pith.science/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2HRLEBQE7GH6PFTVHGU6GXTHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H2HRLEBQE7GH6PFTVHGU6GXTHG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5ef885a3b9f8c7e9d9853f1de215a3a3d7255b28b77976988a531169a58ec204","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:07:31Z","title_canon_sha256":"943efe77296ec5f06f0b6f83ba3641a87c22bfc79834840a6c74f1c990b0c5a5"},"schema_version":"1.0","source":{"id":"2301.12052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12052","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12052v1","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12052","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_12","alias_value":"H2HRLEBQE7GH","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_16","alias_value":"H2HRLEBQE7GH6PFT","created_at":"2026-07-05T05:36:34Z"},{"alias_kind":"pith_short_8","alias_value":"H2HRLEBQ","created_at":"2026-07-05T05:36:34Z"}],"graph_snapshots":[{"event_id":"sha256:b0725f38e3f16552d102114907958597d99f7c69b4c946d7e57e551a9137a8c0","target":"graph","created_at":"2026-07-05T05:36:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.12052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a subset selection algorithm designed to work with arbitrary model families in a practical batch setting. In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i.e. further train model weights) once a large enough batch of examples is selected. Our algorithm, IWeS, selects examples by importance sampling where the sampling probability assigned to each example is based on the entropy of models trained on previously selected batches. IWeS admits significant performance improvement compared to other su","authors_text":"Afshin Rostamizadeh, Giulia DeSalvo, Gui Citovsky, Sanjiv Kumar, Srikumar Ramalingam, Yunjuan Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:07:31Z","title":"Leveraging Importance Weights in Subset Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12052","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a2610aab5a32971a3d0cede1b317356a7b288b1d5df574c6c3d3e1e9db7e31d0","target":"record","created_at":"2026-07-05T05:36:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5ef885a3b9f8c7e9d9853f1de215a3a3d7255b28b77976988a531169a58ec204","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-28T02:07:31Z","title_canon_sha256":"943efe77296ec5f06f0b6f83ba3641a87c22bfc79834840a6c74f1c990b0c5a5"},"schema_version":"1.0","source":{"id":"2301.12052","kind":"arxiv","version":1}},"canonical_sha256":"3e8f15903027cc7f3cb3a9cd4f1af339a74f65c5f437a5323eea704d763fa5df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e8f15903027cc7f3cb3a9cd4f1af339a74f65c5f437a5323eea704d763fa5df","first_computed_at":"2026-07-05T05:36:34.697102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:34.697102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HomT2bRFRkQrRjmdYt1b2QTrX19s48E2BWo2B+ABFy3ukXd685On0WKne7ZhwQcJLW4n8j9y2YougWPiMqq1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:34.697595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2610aab5a32971a3d0cede1b317356a7b288b1d5df574c6c3d3e1e9db7e31d0","sha256:b0725f38e3f16552d102114907958597d99f7c69b4c946d7e57e551a9137a8c0"],"state_sha256":"bcb24465cab6a73ec07e662872338a8389fe1835da0aac0b665ef80d12b89fe9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Otsy2LcoF8BGikL94xBrLrzNS8/98ro+sGfkzw1HXa36megB/ET8sARpSzSnOF1m0h45tnQ+hgPE5eGiDT6UBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:36:42.456232Z","bundle_sha256":"b960b9acede23e35c5547b2f26d63bd1fcf720953331ccf0f65bc8b1ef1aa69e"}}