{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:R2JMYDE7IVB65D55V4HDOV3KCC","short_pith_number":"pith:R2JMYDE7","schema_version":"1.0","canonical_sha256":"8e92cc0c9f4543ee8fbdaf0e37576a108d39d3b4de774e2b1bb97f914488171d","source":{"kind":"arxiv","id":"2101.11259","version":2},"attestation_state":"computed","paper":{"title":"Alaska: A Flexible Benchmark for Data Integration Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea De Angelis, Divesh Srivastava, Donatella Firmani, Federico Piai, Maurizio Mazzei, Paolo Merialdo, Valter Crescenzi","submitted_at":"2021-01-27T08:32:42Z","abstract_excerpt":"Data integration is a long-standing interest of the data management community and has many disparate applications, including business, science and government. We have recently witnessed impressive results in specific data integration tasks, such as Entity Resolution, thanks to the increasing availability of benchmarks. A limitation of such benchmarks is that they typically come with their own task definition and it can be difficult to leverage them for complex integration pipelines. As a result, evaluating end-to-end pipelines for the entire data integration process is still an elusive goal. I"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2101.11259","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2021-01-27T08:32:42Z","cross_cats_sorted":[],"title_canon_sha256":"bb3a0bb888c8b728cc961db3ae85e3e8b67086b9cbd3f655b892183314fd8ee6","abstract_canon_sha256":"0e71af3040ba082b89aa811e82c3eabf8e0d0462be23a8fbea7ff01e3a343121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:32.129197Z","signature_b64":"ARPigJsomDuOt9cz8RryX11k34AcUwvWgN6BoHqBZfpE0oW8jm7duUfMbM89QsWV6NsWQ0qp/cvxHhyFZyNdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e92cc0c9f4543ee8fbdaf0e37576a108d39d3b4de774e2b1bb97f914488171d","last_reissued_at":"2026-07-05T02:12:32.128809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:32.128809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alaska: A Flexible Benchmark for Data Integration Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea De Angelis, Divesh Srivastava, Donatella Firmani, Federico Piai, Maurizio Mazzei, Paolo Merialdo, Valter Crescenzi","submitted_at":"2021-01-27T08:32:42Z","abstract_excerpt":"Data integration is a long-standing interest of the data management community and has many disparate applications, including business, science and government. We have recently witnessed impressive results in specific data integration tasks, such as Entity Resolution, thanks to the increasing availability of benchmarks. A limitation of such benchmarks is that they typically come with their own task definition and it can be difficult to leverage them for complex integration pipelines. As a result, evaluating end-to-end pipelines for the entire data integration process is still an elusive goal. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11259","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.11259/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2101.11259","created_at":"2026-07-05T02:12:32.128864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11259v2","created_at":"2026-07-05T02:12:32.128864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11259","created_at":"2026-07-05T02:12:32.128864+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2JMYDE7IVB6","created_at":"2026-07-05T02:12:32.128864+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2JMYDE7IVB65D55","created_at":"2026-07-05T02:12:32.128864+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2JMYDE7","created_at":"2026-07-05T02:12:32.128864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24407","citing_title":"Entity Resolution via Batched Oracle Queries","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30371","citing_title":"MaDI-Bench: An End-to-End Data Integration Benchmark","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25814","citing_title":"Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC","json":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC.json","graph_json":"https://pith.science/api/pith-number/R2JMYDE7IVB65D55V4HDOV3KCC/graph.json","events_json":"https://pith.science/api/pith-number/R2JMYDE7IVB65D55V4HDOV3KCC/events.json","paper":"https://pith.science/paper/R2JMYDE7"},"agent_actions":{"view_html":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC","download_json":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC.json","view_paper":"https://pith.science/paper/R2JMYDE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11259&json=true","fetch_graph":"https://pith.science/api/pith-number/R2JMYDE7IVB65D55V4HDOV3KCC/graph.json","fetch_events":"https://pith.science/api/pith-number/R2JMYDE7IVB65D55V4HDOV3KCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC/action/storage_attestation","attest_author":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC/action/author_attestation","sign_citation":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC/action/citation_signature","submit_replication":"https://pith.science/pith/R2JMYDE7IVB65D55V4HDOV3KCC/action/replication_record"}},"created_at":"2026-07-05T02:12:32.128864+00:00","updated_at":"2026-07-05T02:12:32.128864+00:00"}