{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OH7METSJ7IZ4IRW3U3U5R33JEA","short_pith_number":"pith:OH7METSJ","canonical_record":{"source":{"id":"1906.03543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T23:53:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a499534ae7b024847a6eedd5b1d77cbac93833bdaaeb1ef922b57c8957800c6","abstract_canon_sha256":"b363bf33b745483c07557a28a176d2ca44cba50ff6c82a6158e106f06e143f7d"},"schema_version":"1.0"},"canonical_sha256":"71fec24e49fa33c446dba6e9d8ef692014125acfed8be9366c159678fbbc0fad","source":{"kind":"arxiv","id":"1906.03543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03543","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03543v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03543","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"OH7METSJ7IZ4","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OH7METSJ7IZ4IRW3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OH7METSJ","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OH7METSJ7IZ4IRW3U3U5R33JEA","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T23:53:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a499534ae7b024847a6eedd5b1d77cbac93833bdaaeb1ef922b57c8957800c6","abstract_canon_sha256":"b363bf33b745483c07557a28a176d2ca44cba50ff6c82a6158e106f06e143f7d"},"schema_version":"1.0"},"canonical_sha256":"71fec24e49fa33c446dba6e9d8ef692014125acfed8be9366c159678fbbc0fad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:48.153447Z","signature_b64":"KmCeRflYKDPFZ86Qf3zNlwCupaDz50JzOFg7NkC73lGT1b1KNCwXaRZBtg4Jub22+Rs9X/OiWXEi6nl3Hs+cBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71fec24e49fa33c446dba6e9d8ef692014125acfed8be9366c159678fbbc0fad","last_reissued_at":"2026-05-17T23:43:48.152766Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:48.152766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03543","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":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4beOpg52m0h1F5JFxhVJZmzgdBIZ7DjU4STitnKtKAiH0tLvn8Zb3h1wEovpKWTs3UTML8jHo2D9lAF4SsjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T05:58:16.276123Z"},"content_sha256":"3097a54e8a736cd028b49623d6ae3121fb2c7736090945ad43ab3beab6b1275f","schema_version":"1.0","event_id":"sha256:3097a54e8a736cd028b49623d6ae3121fb2c7736090945ad43ab3beab6b1275f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OH7METSJ7IZ4IRW3U3U5R33JEA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"apricot: Submodular selection for data summarization in Python","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Schreiber, Jeffrey Bilmes, William Stafford Noble","submitted_at":"2019-06-08T23:53:57Z","abstract_excerpt":"We present apricot, an open source Python package for selecting representative subsets from large data sets using submodular optimization. The package implements an efficient greedy selection algorithm that offers strong theoretical guarantees on the quality of the selected set. Two submodular set functions are implemented in apricot: facility location, which is broadly applicable but requires memory quadratic in the number of examples in the data set, and a feature-based function that is less broadly applicable but can scale to millions of examples. Apricot is extremely efficient, using both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03543","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":""},"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":"2026-05-17T23:43:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"511laMJxqDln+m+3x4YQnKLKmKVHlPWd+oHUYdNX0wbe5GNutCQeIWF0DXTE7UTrlPJj6X/Ze2LjfEBscybfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T05:58:16.276644Z"},"content_sha256":"6f04ef5b9a350dc4352c276712ddb7fcd5b320cd486de41d10b295f6281a29e5","schema_version":"1.0","event_id":"sha256:6f04ef5b9a350dc4352c276712ddb7fcd5b320cd486de41d10b295f6281a29e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OH7METSJ7IZ4IRW3U3U5R33JEA/bundle.json","state_url":"https://pith.science/pith/OH7METSJ7IZ4IRW3U3U5R33JEA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OH7METSJ7IZ4IRW3U3U5R33JEA/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":"2026-06-05T05:58:16Z","links":{"resolver":"https://pith.science/pith/OH7METSJ7IZ4IRW3U3U5R33JEA","bundle":"https://pith.science/pith/OH7METSJ7IZ4IRW3U3U5R33JEA/bundle.json","state":"https://pith.science/pith/OH7METSJ7IZ4IRW3U3U5R33JEA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OH7METSJ7IZ4IRW3U3U5R33JEA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OH7METSJ7IZ4IRW3U3U5R33JEA","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":"b363bf33b745483c07557a28a176d2ca44cba50ff6c82a6158e106f06e143f7d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T23:53:57Z","title_canon_sha256":"9a499534ae7b024847a6eedd5b1d77cbac93833bdaaeb1ef922b57c8957800c6"},"schema_version":"1.0","source":{"id":"1906.03543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03543","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03543v1","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03543","created_at":"2026-05-17T23:43:48Z"},{"alias_kind":"pith_short_12","alias_value":"OH7METSJ7IZ4","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OH7METSJ7IZ4IRW3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OH7METSJ","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:6f04ef5b9a350dc4352c276712ddb7fcd5b320cd486de41d10b295f6281a29e5","target":"graph","created_at":"2026-05-17T23:43:48Z","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":"We present apricot, an open source Python package for selecting representative subsets from large data sets using submodular optimization. The package implements an efficient greedy selection algorithm that offers strong theoretical guarantees on the quality of the selected set. Two submodular set functions are implemented in apricot: facility location, which is broadly applicable but requires memory quadratic in the number of examples in the data set, and a feature-based function that is less broadly applicable but can scale to millions of examples. Apricot is extremely efficient, using both ","authors_text":"Jacob Schreiber, Jeffrey Bilmes, William Stafford Noble","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T23:53:57Z","title":"apricot: Submodular selection for data summarization in Python"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03543","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":"sha256:3097a54e8a736cd028b49623d6ae3121fb2c7736090945ad43ab3beab6b1275f","target":"record","created_at":"2026-05-17T23:43:48Z","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":"b363bf33b745483c07557a28a176d2ca44cba50ff6c82a6158e106f06e143f7d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-08T23:53:57Z","title_canon_sha256":"9a499534ae7b024847a6eedd5b1d77cbac93833bdaaeb1ef922b57c8957800c6"},"schema_version":"1.0","source":{"id":"1906.03543","kind":"arxiv","version":1}},"canonical_sha256":"71fec24e49fa33c446dba6e9d8ef692014125acfed8be9366c159678fbbc0fad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71fec24e49fa33c446dba6e9d8ef692014125acfed8be9366c159678fbbc0fad","first_computed_at":"2026-05-17T23:43:48.152766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:48.152766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KmCeRflYKDPFZ86Qf3zNlwCupaDz50JzOFg7NkC73lGT1b1KNCwXaRZBtg4Jub22+Rs9X/OiWXEi6nl3Hs+cBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:48.153447Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3097a54e8a736cd028b49623d6ae3121fb2c7736090945ad43ab3beab6b1275f","sha256:6f04ef5b9a350dc4352c276712ddb7fcd5b320cd486de41d10b295f6281a29e5"],"state_sha256":"b0a57a43a1c46d6794eaf85881718353bc7e68d17d220706e996995409aff0db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyXEw7FA993VVnQ9yC6EZHAXGpg7HR3UcdwbOyEK6uI3uczDNS744Ep0IhyoSsQ+qLIWGhcWW5oJqyModRX3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T05:58:16.280587Z","bundle_sha256":"3b4f7c04ce99545dabeea1e6c1523cccb4fab83829a209bbc8d16e60d98274f7"}}