{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:26Y5RJYMP57NVZN45WYYHSLW7V","short_pith_number":"pith:26Y5RJYM","canonical_record":{"source":{"id":"2401.00659","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-01-01T04:14:00Z","cross_cats_sorted":[],"title_canon_sha256":"a234d051dedbd9b111988fdd12bcb3de7d2c6193a478d606805a02f7a38193a3","abstract_canon_sha256":"e75c251734633efba0c70ccf1d16ee8a9ea0976303a16f56be4f6716428a3d9d"},"schema_version":"1.0"},"canonical_sha256":"d7b1d8a70c7f7edae5bcedb183c976fd5e6b348688ae28293b46ba625d30912a","source":{"kind":"arxiv","id":"2401.00659","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00659","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00659v4","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00659","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"26Y5RJYMP57N","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"26Y5RJYMP57NVZN4","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"26Y5RJYM","created_at":"2026-07-05T10:20:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:26Y5RJYMP57NVZN45WYYHSLW7V","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00659","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-01-01T04:14:00Z","cross_cats_sorted":[],"title_canon_sha256":"a234d051dedbd9b111988fdd12bcb3de7d2c6193a478d606805a02f7a38193a3","abstract_canon_sha256":"e75c251734633efba0c70ccf1d16ee8a9ea0976303a16f56be4f6716428a3d9d"},"schema_version":"1.0"},"canonical_sha256":"d7b1d8a70c7f7edae5bcedb183c976fd5e6b348688ae28293b46ba625d30912a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:35.252558Z","signature_b64":"Z/0JT5667Rkrc8wdX7ZpDvkdG13ZjiA3ayD++/Y7H8pMt30lW/RBoZLpF4u6psVD11kQ9fu5FIV+CTzNxBV3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b1d8a70c7f7edae5bcedb183c976fd5e6b348688ae28293b46ba625d30912a","last_reissued_at":"2026-07-05T10:20:35.252059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:35.252059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00659","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7YgU6ldBTmvXVJYDu4QGJ5w7Swv46LUNk4VX7irQLJsLrn47Qm/OVKR9mOskTs+1puEzYUvVV7nbpFZP8FPLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:29:39.321826Z"},"content_sha256":"2f2ee4c9104389a39c94aff830c8cd8bee271345cf711fd7f6d409013c20ae00","schema_version":"1.0","event_id":"sha256:2f2ee4c9104389a39c94aff830c8cd8bee271345cf711fd7f6d409013c20ae00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:26Y5RJYMP57NVZN45WYYHSLW7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distinctiveness Maximization in Datasets Assemblage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"J. Shane Culpepper, Reza Arablouei, Shixun Huang, Tingting Wang, Volkan Dedeoglu, Zhifeng Bao","submitted_at":"2024-01-01T04:14:00Z","abstract_excerpt":"In this paper, given a user's query set and budget, we aim to use the limited budget to help users assemble a set of datasets that can enrich a base dataset by introducing the maximum number of distinct tuples (i.e., maximizing distinctiveness). We prove this problem to be NP-hard. A greedy algorithm using exact distinctiveness computation attains an approximation ratio of (1-1/e)/2, but it lacks efficiency and scalability due to its frequent computation of the exact distinctiveness marginal gain of any candidate dataset for selection. This requires scanning through every tuple in candidate da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00659","kind":"arxiv","version":4},"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/2401.00659/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":"2026-07-05T10:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yA+HiQBn4tcOWOY8W0pqEr5o7CS2kiOgpXVjWCsJpIu/knTWlSd7JroiVMIBvEkmSMF8jpYc6LanAXuBGnNWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:29:39.322612Z"},"content_sha256":"7cf594aa1853cb84a3710ca9330180152db13195fb06470cc516264a25d0c4b2","schema_version":"1.0","event_id":"sha256:7cf594aa1853cb84a3710ca9330180152db13195fb06470cc516264a25d0c4b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26Y5RJYMP57NVZN45WYYHSLW7V/bundle.json","state_url":"https://pith.science/pith/26Y5RJYMP57NVZN45WYYHSLW7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26Y5RJYMP57NVZN45WYYHSLW7V/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":"2026-08-03T17:29:39Z","links":{"resolver":"https://pith.science/pith/26Y5RJYMP57NVZN45WYYHSLW7V","bundle":"https://pith.science/pith/26Y5RJYMP57NVZN45WYYHSLW7V/bundle.json","state":"https://pith.science/pith/26Y5RJYMP57NVZN45WYYHSLW7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26Y5RJYMP57NVZN45WYYHSLW7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:26Y5RJYMP57NVZN45WYYHSLW7V","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":"e75c251734633efba0c70ccf1d16ee8a9ea0976303a16f56be4f6716428a3d9d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-01-01T04:14:00Z","title_canon_sha256":"a234d051dedbd9b111988fdd12bcb3de7d2c6193a478d606805a02f7a38193a3"},"schema_version":"1.0","source":{"id":"2401.00659","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00659","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00659v4","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00659","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"26Y5RJYMP57N","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"26Y5RJYMP57NVZN4","created_at":"2026-07-05T10:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"26Y5RJYM","created_at":"2026-07-05T10:20:35Z"}],"graph_snapshots":[{"event_id":"sha256:7cf594aa1853cb84a3710ca9330180152db13195fb06470cc516264a25d0c4b2","target":"graph","created_at":"2026-07-05T10:20:35Z","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/2401.00659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, given a user's query set and budget, we aim to use the limited budget to help users assemble a set of datasets that can enrich a base dataset by introducing the maximum number of distinct tuples (i.e., maximizing distinctiveness). We prove this problem to be NP-hard. A greedy algorithm using exact distinctiveness computation attains an approximation ratio of (1-1/e)/2, but it lacks efficiency and scalability due to its frequent computation of the exact distinctiveness marginal gain of any candidate dataset for selection. This requires scanning through every tuple in candidate da","authors_text":"J. Shane Culpepper, Reza Arablouei, Shixun Huang, Tingting Wang, Volkan Dedeoglu, Zhifeng Bao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-01-01T04:14:00Z","title":"Distinctiveness Maximization in Datasets Assemblage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00659","kind":"arxiv","version":4},"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":"sha256:2f2ee4c9104389a39c94aff830c8cd8bee271345cf711fd7f6d409013c20ae00","target":"record","created_at":"2026-07-05T10:20:35Z","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":"e75c251734633efba0c70ccf1d16ee8a9ea0976303a16f56be4f6716428a3d9d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-01-01T04:14:00Z","title_canon_sha256":"a234d051dedbd9b111988fdd12bcb3de7d2c6193a478d606805a02f7a38193a3"},"schema_version":"1.0","source":{"id":"2401.00659","kind":"arxiv","version":4}},"canonical_sha256":"d7b1d8a70c7f7edae5bcedb183c976fd5e6b348688ae28293b46ba625d30912a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7b1d8a70c7f7edae5bcedb183c976fd5e6b348688ae28293b46ba625d30912a","first_computed_at":"2026-07-05T10:20:35.252059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:35.252059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/0JT5667Rkrc8wdX7ZpDvkdG13ZjiA3ayD++/Y7H8pMt30lW/RBoZLpF4u6psVD11kQ9fu5FIV+CTzNxBV3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:35.252558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00659","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f2ee4c9104389a39c94aff830c8cd8bee271345cf711fd7f6d409013c20ae00","sha256:7cf594aa1853cb84a3710ca9330180152db13195fb06470cc516264a25d0c4b2"],"state_sha256":"29e067c8d560e72ee6a79252fe6d666483d314342fada43788074cbfda8a0945"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmsXx0E9stydoghXW4aUlMUdoRI+8jHd/eC6GyROnBwybCziAuAUZEKtdfFl6BVJxbE8OkFsHCCxSo9YycrCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:29:39.328422Z","bundle_sha256":"2e1b9eed9b196a50bdfc1c9d11c520e390615fc1ac09f72bf2b33288a26003aa"}}