{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ULKHNXQ6VJ4H35I5US5SYI5V47","short_pith_number":"pith:ULKHNXQ6","canonical_record":{"source":{"id":"1802.05249","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:16:43Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"0a6a6a27d23508cac12197f995f420455a69fe8365784612ce01653b418e7c06","abstract_canon_sha256":"2fc05268e0ffdccf7f89f79f311cd0394c1fccaa5da484c4521b34062ae6653d"},"schema_version":"1.0"},"canonical_sha256":"a2d476de1eaa787df51da4bb2c23b5e7d3ff325a32add22d714e93de6efd2f3f","source":{"kind":"arxiv","id":"1802.05249","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05249","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05249v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05249","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"ULKHNXQ6VJ4H","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"ULKHNXQ6VJ4H35I5","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"ULKHNXQ6","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ULKHNXQ6VJ4H35I5US5SYI5V47","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05249","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:16:43Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"0a6a6a27d23508cac12197f995f420455a69fe8365784612ce01653b418e7c06","abstract_canon_sha256":"2fc05268e0ffdccf7f89f79f311cd0394c1fccaa5da484c4521b34062ae6653d"},"schema_version":"1.0"},"canonical_sha256":"a2d476de1eaa787df51da4bb2c23b5e7d3ff325a32add22d714e93de6efd2f3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.312779Z","signature_b64":"uBrzYhrgZZ3DUQUfb8b8ky2/oljFjzv/WTk6xdCKlDSiAeAJp4zuD4vZEYT5Acv2SBeoM7p8ZjdM6BW5a3h1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d476de1eaa787df51da4bb2c23b5e7d3ff325a32add22d714e93de6efd2f3f","last_reissued_at":"2026-05-18T00:14:06.312001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.312001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05249","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jx5SWXoh7Ufc901hJDAneg/QQP4DWGN/uCQKE/D/aOTARIKRWSRDcvMMSDc2lfrjCTm2/uicQPropf9XidZODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T13:15:02.148987Z"},"content_sha256":"8a1ccfa51a924bb88104539b1d037e56175c815372a17dc5c330331d83162d69","schema_version":"1.0","event_id":"sha256:8a1ccfa51a924bb88104539b1d037e56175c815372a17dc5c330331d83162d69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ULKHNXQ6VJ4H35I5US5SYI5V47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributionally Robust Submodular Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bryan Wilder, Matthew Staib, Stefanie Jegelka","submitted_at":"2018-02-14T18:16:43Z","abstract_excerpt":"Submodular functions have applications throughout machine learning, but in many settings, we do not have direct access to the underlying function $f$. We focus on stochastic functions that are given as an expectation of functions over a distribution $P$. In practice, we often have only a limited set of samples $f_i$ from $P$. The standard approach indirectly optimizes $f$ by maximizing the sum of $f_i$. However, this ignores generalization to the true (unknown) distribution. In this paper, we achieve better performance on the actual underlying function $f$ by directly optimizing a combination "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05249","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrO9mHZCsORbF5EMw3ZnrjL45CkJb+wazp7K/E1piClJFzWCxefiIaL2mFuJJo01su53qv4RX33lSNL+Z/ToDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T13:15:02.149352Z"},"content_sha256":"08dd8b7b5bc9dd50a038addb35e715497b86e039755cfdd870ffad9a3954f720","schema_version":"1.0","event_id":"sha256:08dd8b7b5bc9dd50a038addb35e715497b86e039755cfdd870ffad9a3954f720"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULKHNXQ6VJ4H35I5US5SYI5V47/bundle.json","state_url":"https://pith.science/pith/ULKHNXQ6VJ4H35I5US5SYI5V47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULKHNXQ6VJ4H35I5US5SYI5V47/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":"2026-06-04T13:15:02Z","links":{"resolver":"https://pith.science/pith/ULKHNXQ6VJ4H35I5US5SYI5V47","bundle":"https://pith.science/pith/ULKHNXQ6VJ4H35I5US5SYI5V47/bundle.json","state":"https://pith.science/pith/ULKHNXQ6VJ4H35I5US5SYI5V47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULKHNXQ6VJ4H35I5US5SYI5V47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ULKHNXQ6VJ4H35I5US5SYI5V47","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":"2fc05268e0ffdccf7f89f79f311cd0394c1fccaa5da484c4521b34062ae6653d","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:16:43Z","title_canon_sha256":"0a6a6a27d23508cac12197f995f420455a69fe8365784612ce01653b418e7c06"},"schema_version":"1.0","source":{"id":"1802.05249","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05249","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05249v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05249","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"ULKHNXQ6VJ4H","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"ULKHNXQ6VJ4H35I5","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"ULKHNXQ6","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:08dd8b7b5bc9dd50a038addb35e715497b86e039755cfdd870ffad9a3954f720","target":"graph","created_at":"2026-05-18T00:14:06Z","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"},"paper":{"abstract_excerpt":"Submodular functions have applications throughout machine learning, but in many settings, we do not have direct access to the underlying function $f$. We focus on stochastic functions that are given as an expectation of functions over a distribution $P$. In practice, we often have only a limited set of samples $f_i$ from $P$. The standard approach indirectly optimizes $f$ by maximizing the sum of $f_i$. However, this ignores generalization to the true (unknown) distribution. In this paper, we achieve better performance on the actual underlying function $f$ by directly optimizing a combination ","authors_text":"Bryan Wilder, Matthew Staib, Stefanie Jegelka","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:16:43Z","title":"Distributionally Robust Submodular Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05249","kind":"arxiv","version":2},"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":"sha256:8a1ccfa51a924bb88104539b1d037e56175c815372a17dc5c330331d83162d69","target":"record","created_at":"2026-05-18T00:14:06Z","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":"2fc05268e0ffdccf7f89f79f311cd0394c1fccaa5da484c4521b34062ae6653d","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T18:16:43Z","title_canon_sha256":"0a6a6a27d23508cac12197f995f420455a69fe8365784612ce01653b418e7c06"},"schema_version":"1.0","source":{"id":"1802.05249","kind":"arxiv","version":2}},"canonical_sha256":"a2d476de1eaa787df51da4bb2c23b5e7d3ff325a32add22d714e93de6efd2f3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2d476de1eaa787df51da4bb2c23b5e7d3ff325a32add22d714e93de6efd2f3f","first_computed_at":"2026-05-18T00:14:06.312001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:06.312001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBrzYhrgZZ3DUQUfb8b8ky2/oljFjzv/WTk6xdCKlDSiAeAJp4zuD4vZEYT5Acv2SBeoM7p8ZjdM6BW5a3h1Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:06.312779Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05249","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a1ccfa51a924bb88104539b1d037e56175c815372a17dc5c330331d83162d69","sha256:08dd8b7b5bc9dd50a038addb35e715497b86e039755cfdd870ffad9a3954f720"],"state_sha256":"17c37fd53726f9f64533f0d13f6882e33b7a5216ba160146ae8a08b35baf778e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEW9r5gY9jImSI/3ohzb16qijcRilIV5GN+H4tVM014gvz4m7cnAS3Nc5IUDmT1CCdCX8VGj4M+BZzqtnQt5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T13:15:02.151385Z","bundle_sha256":"ed8ba6f43db8e7806e570f2241e97d581384ac5dfdd1dd6814cc8d865f0af0cd"}}