{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NADABC5SYCEP5RN7IYNEW2U4PY","short_pith_number":"pith:NADABC5S","canonical_record":{"source":{"id":"2201.10547","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T18:56:16Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"4bdf4fcc5aa3b65eaa1d86e8718b222b418bbbdee004c0bb4e047422ede38342","abstract_canon_sha256":"c0d78feeb2e93961f47caf2f18ea8804e0db1e333b0a32997c3164c7f14a5671"},"schema_version":"1.0"},"canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","source":{"kind":"arxiv","id":"2201.10547","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10547","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10547v3","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10547","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"pith_short_12","alias_value":"NADABC5SYCEP","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"pith_short_16","alias_value":"NADABC5SYCEP5RN7","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"pith_short_8","alias_value":"NADABC5S","created_at":"2026-07-05T07:24:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NADABC5SYCEP5RN7IYNEW2U4PY","target":"record","payload":{"canonical_record":{"source":{"id":"2201.10547","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T18:56:16Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"4bdf4fcc5aa3b65eaa1d86e8718b222b418bbbdee004c0bb4e047422ede38342","abstract_canon_sha256":"c0d78feeb2e93961f47caf2f18ea8804e0db1e333b0a32997c3164c7f14a5671"},"schema_version":"1.0"},"canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:17.585128Z","signature_b64":"IUwipHX3i+Th6ehf2Uu5n4FzCscOp9Rp4aP5Y1hFiZ8DH9sBusVLh+1zY/IJrbpby7crwx+wOBJdt/o/4BDXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","last_reissued_at":"2026-07-05T07:24:17.584565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:17.584565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.10547","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":"2026-07-05T07:24:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gf5ezJH7K3urcizKBjvwJ7K7eQsgV/S70LicaLia6uPGoakNLqTByd26KkEwnuGLyOF+JMqAPhHUJZ1bGjoVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:24:34.363882Z"},"content_sha256":"2d090ef0419de843558befe4975f2677b283c8b089936d7f572cf5bc992e4133","schema_version":"1.0","event_id":"sha256:2d090ef0419de843558befe4975f2677b283c8b089936d7f572cf5bc992e4133"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NADABC5SYCEP5RN7IYNEW2U4PY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Data Selection: An Online Distributed View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Anastasios Angelopoulos, Mariel Werner, Michael I. Jordan, Stephen Bates","submitted_at":"2022-01-25T18:56:16Z","abstract_excerpt":"The blessing of ubiquitous data also comes with a curse: the communication, storage, and labeling of massive, mostly redundant datasets. We seek to solve this problem at its core, collecting only valuable data and throwing out the rest via submodular maximization. Specifically, we develop algorithms for the online and distributed version of the problem, where data selection occurs in an uncoordinated fashion across multiple data streams. We design a general and flexible core selection routine for our algorithms which, given any stream of data, any assessment of its value, and any formulation o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10547","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/2201.10547/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":"2026-07-05T07:24:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SGWGJUmLaK7KfVb6h15RjJ1PSh2/QW67rIljtrXk5LDsxv1417pM2EDvbuP5Djq2FyI7+IruFFlIDTq4vX4yAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T16:24:34.364268Z"},"content_sha256":"f1440304ed04401c1627dca1fcc8dd95d4bdadb18c4f5730ea2973cf5cc2cdfe","schema_version":"1.0","event_id":"sha256:f1440304ed04401c1627dca1fcc8dd95d4bdadb18c4f5730ea2973cf5cc2cdfe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/bundle.json","state_url":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NADABC5SYCEP5RN7IYNEW2U4PY/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":"2026-07-08T16:24:34Z","links":{"resolver":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY","bundle":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/bundle.json","state":"https://pith.science/pith/NADABC5SYCEP5RN7IYNEW2U4PY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NADABC5SYCEP5RN7IYNEW2U4PY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NADABC5SYCEP5RN7IYNEW2U4PY","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":"c0d78feeb2e93961f47caf2f18ea8804e0db1e333b0a32997c3164c7f14a5671","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T18:56:16Z","title_canon_sha256":"4bdf4fcc5aa3b65eaa1d86e8718b222b418bbbdee004c0bb4e047422ede38342"},"schema_version":"1.0","source":{"id":"2201.10547","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10547","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10547v3","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10547","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"pith_short_12","alias_value":"NADABC5SYCEP","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"pith_short_16","alias_value":"NADABC5SYCEP5RN7","created_at":"2026-07-05T07:24:17Z"},{"alias_kind":"pith_short_8","alias_value":"NADABC5S","created_at":"2026-07-05T07:24:17Z"}],"graph_snapshots":[{"event_id":"sha256:f1440304ed04401c1627dca1fcc8dd95d4bdadb18c4f5730ea2973cf5cc2cdfe","target":"graph","created_at":"2026-07-05T07:24:17Z","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/2201.10547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The blessing of ubiquitous data also comes with a curse: the communication, storage, and labeling of massive, mostly redundant datasets. We seek to solve this problem at its core, collecting only valuable data and throwing out the rest via submodular maximization. Specifically, we develop algorithms for the online and distributed version of the problem, where data selection occurs in an uncoordinated fashion across multiple data streams. We design a general and flexible core selection routine for our algorithms which, given any stream of data, any assessment of its value, and any formulation o","authors_text":"Anastasios Angelopoulos, Mariel Werner, Michael I. Jordan, Stephen Bates","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T18:56:16Z","title":"Optimal Data Selection: An Online Distributed View"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10547","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":"sha256:2d090ef0419de843558befe4975f2677b283c8b089936d7f572cf5bc992e4133","target":"record","created_at":"2026-07-05T07:24:17Z","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":"c0d78feeb2e93961f47caf2f18ea8804e0db1e333b0a32997c3164c7f14a5671","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T18:56:16Z","title_canon_sha256":"4bdf4fcc5aa3b65eaa1d86e8718b222b418bbbdee004c0bb4e047422ede38342"},"schema_version":"1.0","source":{"id":"2201.10547","kind":"arxiv","version":3}},"canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6806008bb2c088fec5bf461a4b6a9c7e246d25088f398c2c5a7606c9650b00cf","first_computed_at":"2026-07-05T07:24:17.584565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:17.584565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUwipHX3i+Th6ehf2Uu5n4FzCscOp9Rp4aP5Y1hFiZ8DH9sBusVLh+1zY/IJrbpby7crwx+wOBJdt/o/4BDXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:17.585128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.10547","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d090ef0419de843558befe4975f2677b283c8b089936d7f572cf5bc992e4133","sha256:f1440304ed04401c1627dca1fcc8dd95d4bdadb18c4f5730ea2973cf5cc2cdfe"],"state_sha256":"c3a638ea4e3e8be3ac005acce24507a6c94619d51a03d9faf3be41edd01fa139"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qtzacZ+eAyumgx3a2zghhj/NeSGHabUX6xC7YWHwoQJ/SVUvoEcM9vmuiX3g11cIFZXX/2kd6fczTK/jMoZEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T16:24:34.366911Z","bundle_sha256":"ffffc75cbfb458cc2e91edc740de0455aa32edf42ed3ed4ef517db1e6f55dc6c"}}