{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4FVA2KWM5LZK47QDLK2LDQLS5B","short_pith_number":"pith:4FVA2KWM","canonical_record":{"source":{"id":"2209.14881","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T15:49:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db0d05881d3f01752b29d6edf900150b5919ca3ef5f7adf9773cba3add352a16","abstract_canon_sha256":"3773e37f7ab6681160489203159866b5011af06180d02bcee46ed28cd392f106"},"schema_version":"1.0"},"canonical_sha256":"e16a0d2acceaf2ae7e035ab4b1c172e84edabd205509cee7ac87ba90b48e330e","source":{"kind":"arxiv","id":"2209.14881","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14881","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14881v3","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14881","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"4FVA2KWM5LZK","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"4FVA2KWM5LZK47QD","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"4FVA2KWM","created_at":"2026-07-05T08:32:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4FVA2KWM5LZK47QDLK2LDQLS5B","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14881","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T15:49:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db0d05881d3f01752b29d6edf900150b5919ca3ef5f7adf9773cba3add352a16","abstract_canon_sha256":"3773e37f7ab6681160489203159866b5011af06180d02bcee46ed28cd392f106"},"schema_version":"1.0"},"canonical_sha256":"e16a0d2acceaf2ae7e035ab4b1c172e84edabd205509cee7ac87ba90b48e330e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:58.781299Z","signature_b64":"mZ8fvlfR9zAhUJTsgdSK/LKS+q/q6DkizRkQI5esC5KtCSPJtJalZQ9cY5zIdy6LwGzqWevCAbqPZFW9daG/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e16a0d2acceaf2ae7e035ab4b1c172e84edabd205509cee7ac87ba90b48e330e","last_reissued_at":"2026-07-05T08:32:58.780806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:58.780806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14881","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTGVNiZpvy1DvCXymwBpxCyvblFLXa5khppM7+xUlEdlyC4TJnacfBtmhNX8qPkNGtZ2Zn5J1vmHUwqlKJmdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:34:50.963960Z"},"content_sha256":"9413517913a6f461e5198124f2ea1e8ad60813d25a3f7ba3460bd667676f7ed3","schema_version":"1.0","event_id":"sha256:9413517913a6f461e5198124f2ea1e8ad60813d25a3f7ba3460bd667676f7ed3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4FVA2KWM5LZK47QDLK2LDQLS5B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sequential Attention for Feature Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Fu, Lin Chen, Matthew Fahrbach, MohammadHossein Bateni, Taisuke Yasuda, Vahab Mirrokni","submitted_at":"2022-09-29T15:49:06Z","abstract_excerpt":"Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint. For neural networks, prior methods, including those based on $\\ell_1$ regularization, attention, and other techniques, typically select the entire feature subset in one evaluation round, ignoring the residual value of features during selection, i.e., the marginal contribution of a feature given that other features have already been selected. We propose a feature selection algorithm called Sequential Attention that achieves state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14881","kind":"arxiv","version":3},"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/2209.14881/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":"2026-07-05T08:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNWXWaEalK4y53pfJbrA+mGtoxnN7FCmPjwJGttrw2VIyC0Jx24LFzFV3poZZBj0+88ILddS+UUNHhN+JvAUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:34:50.964346Z"},"content_sha256":"1e7eb6cce1fb8adfdca875fab558346f27c8c2141a6a3940cd9f6b698813e692","schema_version":"1.0","event_id":"sha256:1e7eb6cce1fb8adfdca875fab558346f27c8c2141a6a3940cd9f6b698813e692"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FVA2KWM5LZK47QDLK2LDQLS5B/bundle.json","state_url":"https://pith.science/pith/4FVA2KWM5LZK47QDLK2LDQLS5B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FVA2KWM5LZK47QDLK2LDQLS5B/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":"2026-07-07T05:34:50Z","links":{"resolver":"https://pith.science/pith/4FVA2KWM5LZK47QDLK2LDQLS5B","bundle":"https://pith.science/pith/4FVA2KWM5LZK47QDLK2LDQLS5B/bundle.json","state":"https://pith.science/pith/4FVA2KWM5LZK47QDLK2LDQLS5B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FVA2KWM5LZK47QDLK2LDQLS5B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4FVA2KWM5LZK47QDLK2LDQLS5B","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":"3773e37f7ab6681160489203159866b5011af06180d02bcee46ed28cd392f106","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T15:49:06Z","title_canon_sha256":"db0d05881d3f01752b29d6edf900150b5919ca3ef5f7adf9773cba3add352a16"},"schema_version":"1.0","source":{"id":"2209.14881","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14881","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14881v3","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14881","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"4FVA2KWM5LZK","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"4FVA2KWM5LZK47QD","created_at":"2026-07-05T08:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"4FVA2KWM","created_at":"2026-07-05T08:32:58Z"}],"graph_snapshots":[{"event_id":"sha256:1e7eb6cce1fb8adfdca875fab558346f27c8c2141a6a3940cd9f6b698813e692","target":"graph","created_at":"2026-07-05T08:32:58Z","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/2209.14881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint. For neural networks, prior methods, including those based on $\\ell_1$ regularization, attention, and other techniques, typically select the entire feature subset in one evaluation round, ignoring the residual value of features during selection, i.e., the marginal contribution of a feature given that other features have already been selected. We propose a feature selection algorithm called Sequential Attention that achieves state-of-the-art","authors_text":"Gang Fu, Lin Chen, Matthew Fahrbach, MohammadHossein Bateni, Taisuke Yasuda, Vahab Mirrokni","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T15:49:06Z","title":"Sequential Attention for Feature Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14881","kind":"arxiv","version":3},"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":"sha256:9413517913a6f461e5198124f2ea1e8ad60813d25a3f7ba3460bd667676f7ed3","target":"record","created_at":"2026-07-05T08:32:58Z","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":"3773e37f7ab6681160489203159866b5011af06180d02bcee46ed28cd392f106","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T15:49:06Z","title_canon_sha256":"db0d05881d3f01752b29d6edf900150b5919ca3ef5f7adf9773cba3add352a16"},"schema_version":"1.0","source":{"id":"2209.14881","kind":"arxiv","version":3}},"canonical_sha256":"e16a0d2acceaf2ae7e035ab4b1c172e84edabd205509cee7ac87ba90b48e330e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e16a0d2acceaf2ae7e035ab4b1c172e84edabd205509cee7ac87ba90b48e330e","first_computed_at":"2026-07-05T08:32:58.780806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:58.780806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mZ8fvlfR9zAhUJTsgdSK/LKS+q/q6DkizRkQI5esC5KtCSPJtJalZQ9cY5zIdy6LwGzqWevCAbqPZFW9daG/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:58.781299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14881","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9413517913a6f461e5198124f2ea1e8ad60813d25a3f7ba3460bd667676f7ed3","sha256:1e7eb6cce1fb8adfdca875fab558346f27c8c2141a6a3940cd9f6b698813e692"],"state_sha256":"95ea4b59e3348e279041772c2d3adcc5aee07d1dbb79e046102801c1c611ecae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7l3p3Q1mpe+hUfUCTjmzihoEwIGQyfQ7luleB3q96CBw26Yc6NUD4uuzJnd1Vw/KiVFuzF6rGjmowJmfH3RkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:34:50.966908Z","bundle_sha256":"c446af32c50032ca0ecc56626ee2bc27c5c3f8e212363be38737162040e332ba"}}