{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XN3DY2S547FNGB54JTI7OZJYPW","short_pith_number":"pith:XN3DY2S5","canonical_record":{"source":{"id":"2401.05712","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-11T07:27:58Z","cross_cats_sorted":[],"title_canon_sha256":"71bef45e6ce9190408a354bc8c45e3174fabc5911ef81b3d398413419921b4d8","abstract_canon_sha256":"abc368bc52b6a571e2572949b83c1af515d357986334c3616377aedf4b73c1ad"},"schema_version":"1.0"},"canonical_sha256":"bb763c6a5de7cad307bc4cd1f765387d8d953dd7f8d8a50b0bdac3a3840efaae","source":{"kind":"arxiv","id":"2401.05712","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05712","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05712v3","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05712","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"XN3DY2S547FN","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"XN3DY2S547FNGB54","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"XN3DY2S5","created_at":"2026-07-05T08:56:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XN3DY2S547FNGB54JTI7OZJYPW","target":"record","payload":{"canonical_record":{"source":{"id":"2401.05712","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-11T07:27:58Z","cross_cats_sorted":[],"title_canon_sha256":"71bef45e6ce9190408a354bc8c45e3174fabc5911ef81b3d398413419921b4d8","abstract_canon_sha256":"abc368bc52b6a571e2572949b83c1af515d357986334c3616377aedf4b73c1ad"},"schema_version":"1.0"},"canonical_sha256":"bb763c6a5de7cad307bc4cd1f765387d8d953dd7f8d8a50b0bdac3a3840efaae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:16.412612Z","signature_b64":"C/mXmFHcXwE4jNARKP5JwQRAsdzZfJs77OxypRqDHi/Ll4z6kj2DmtLTFhVLw6zruldG4eh+qwiGtGfCHNcvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb763c6a5de7cad307bc4cd1f765387d8d953dd7f8d8a50b0bdac3a3840efaae","last_reissued_at":"2026-07-05T08:56:16.412174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:16.412174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.05712","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":"2026-07-05T08:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PqXk0J5BIvq0F20vSSUbmSYbVIYhPJ4tostGteEjQdPo+q8r75inat8iUP0j1BQy5bPv32bMsnlOiQSOftRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:31:53.144328Z"},"content_sha256":"7fac7adbb4a9d31a830fe34c6bbf79d5079fb25b7fe33256278d7cd972919707","schema_version":"1.0","event_id":"sha256:7fac7adbb4a9d31a830fe34c6bbf79d5079fb25b7fe33256278d7cd972919707"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XN3DY2S547FNGB54JTI7OZJYPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BOD: Blindly Optimal Data Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Thomas Hoang","submitted_at":"2024-01-11T07:27:58Z","abstract_excerpt":"Combining discovery and augmentation is important in the era of data usage when it comes to predicting the outcome of tasks. However, having to ask the user the utility function to discover the goal to achieve the optimal small rightful dataset is not an optimal solution. The existing solutions do not make good use of this combination, hence underutilizing the data. In this paper, we introduce a novel goal-oriented framework, called BOD: Blindly Optimal Data Discovery, that involves humans in the loop and comparing utility scores every time querying in the process without knowing the utility f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05712","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/2401.05712/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":"2026-07-05T08:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCDN4xBk1Ey/tcvQzqCVYefv6lBKXaEB2OMyGZYNUrxrBsqRhbuesfIJgyqesFXgq1gEfbXhTwcTV0blwADyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:31:53.144829Z"},"content_sha256":"b5c60da7e3463f5fb2c970fb2dc715d5988e7dbdc33c4b153699e2e147bd990a","schema_version":"1.0","event_id":"sha256:b5c60da7e3463f5fb2c970fb2dc715d5988e7dbdc33c4b153699e2e147bd990a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XN3DY2S547FNGB54JTI7OZJYPW/bundle.json","state_url":"https://pith.science/pith/XN3DY2S547FNGB54JTI7OZJYPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XN3DY2S547FNGB54JTI7OZJYPW/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":"2026-08-20T22:31:53Z","links":{"resolver":"https://pith.science/pith/XN3DY2S547FNGB54JTI7OZJYPW","bundle":"https://pith.science/pith/XN3DY2S547FNGB54JTI7OZJYPW/bundle.json","state":"https://pith.science/pith/XN3DY2S547FNGB54JTI7OZJYPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XN3DY2S547FNGB54JTI7OZJYPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XN3DY2S547FNGB54JTI7OZJYPW","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":"abc368bc52b6a571e2572949b83c1af515d357986334c3616377aedf4b73c1ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-11T07:27:58Z","title_canon_sha256":"71bef45e6ce9190408a354bc8c45e3174fabc5911ef81b3d398413419921b4d8"},"schema_version":"1.0","source":{"id":"2401.05712","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05712","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05712v3","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05712","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"XN3DY2S547FN","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"XN3DY2S547FNGB54","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"XN3DY2S5","created_at":"2026-07-05T08:56:16Z"}],"graph_snapshots":[{"event_id":"sha256:b5c60da7e3463f5fb2c970fb2dc715d5988e7dbdc33c4b153699e2e147bd990a","target":"graph","created_at":"2026-07-05T08:56:16Z","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/2401.05712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combining discovery and augmentation is important in the era of data usage when it comes to predicting the outcome of tasks. However, having to ask the user the utility function to discover the goal to achieve the optimal small rightful dataset is not an optimal solution. The existing solutions do not make good use of this combination, hence underutilizing the data. In this paper, we introduce a novel goal-oriented framework, called BOD: Blindly Optimal Data Discovery, that involves humans in the loop and comparing utility scores every time querying in the process without knowing the utility f","authors_text":"Thomas Hoang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-11T07:27:58Z","title":"BOD: Blindly Optimal Data Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05712","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":"sha256:7fac7adbb4a9d31a830fe34c6bbf79d5079fb25b7fe33256278d7cd972919707","target":"record","created_at":"2026-07-05T08:56:16Z","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":"abc368bc52b6a571e2572949b83c1af515d357986334c3616377aedf4b73c1ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-11T07:27:58Z","title_canon_sha256":"71bef45e6ce9190408a354bc8c45e3174fabc5911ef81b3d398413419921b4d8"},"schema_version":"1.0","source":{"id":"2401.05712","kind":"arxiv","version":3}},"canonical_sha256":"bb763c6a5de7cad307bc4cd1f765387d8d953dd7f8d8a50b0bdac3a3840efaae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb763c6a5de7cad307bc4cd1f765387d8d953dd7f8d8a50b0bdac3a3840efaae","first_computed_at":"2026-07-05T08:56:16.412174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:16.412174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C/mXmFHcXwE4jNARKP5JwQRAsdzZfJs77OxypRqDHi/Ll4z6kj2DmtLTFhVLw6zruldG4eh+qwiGtGfCHNcvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:16.412612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05712","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fac7adbb4a9d31a830fe34c6bbf79d5079fb25b7fe33256278d7cd972919707","sha256:b5c60da7e3463f5fb2c970fb2dc715d5988e7dbdc33c4b153699e2e147bd990a"],"state_sha256":"4acdd8a7efa9602667996094da775efccb5cbbce7f82933cf280ecb0c0705eb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"toQhk0hoYhnCoZnn+3Kzo8biIpQodysQv8/l6WlqMIxMvzjRHPFFgWZ1K5gFXM9lVKIQi6O0IvMgbQGyC30ZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:31:53.149387Z","bundle_sha256":"4337a87b26de7803aefbc1365700eba713f446637d822bdf42bb804beabb9fcb"}}