{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7R72YQ7UHF7XF3VUR6BFE75FVB","short_pith_number":"pith:7R72YQ7U","canonical_record":{"source":{"id":"1710.00027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-29T18:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"26e17a0fefc8f45b1c289a27dc9cf923869c224507a78bd35a63ebe48ff5aec0","abstract_canon_sha256":"cea25332c355304b9bedef2086098b755ca38ae57c3e50d4f34490f6dfd01520"},"schema_version":"1.0"},"canonical_sha256":"fc7fac43f4397f72eeb48f82527fa5a86343ed13d510783b1fccada0fc0c060e","source":{"kind":"arxiv","id":"1710.00027","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00027","created_at":"2026-05-18T00:33:58Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00027v1","created_at":"2026-05-18T00:33:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00027","created_at":"2026-05-18T00:33:58Z"},{"alias_kind":"pith_short_12","alias_value":"7R72YQ7UHF7X","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7R72YQ7UHF7XF3VU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7R72YQ7U","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7R72YQ7UHF7XF3VUR6BFE75FVB","target":"record","payload":{"canonical_record":{"source":{"id":"1710.00027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-29T18:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"26e17a0fefc8f45b1c289a27dc9cf923869c224507a78bd35a63ebe48ff5aec0","abstract_canon_sha256":"cea25332c355304b9bedef2086098b755ca38ae57c3e50d4f34490f6dfd01520"},"schema_version":"1.0"},"canonical_sha256":"fc7fac43f4397f72eeb48f82527fa5a86343ed13d510783b1fccada0fc0c060e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:58.079768Z","signature_b64":"7SJZK9bP9rROGz4jCKJUkPnjSTiVvpXtuaSTe34TywOu4hsSbfNnPzdcIsKa3KLQIFdGw86rkgY365uxXCT+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7fac43f4397f72eeb48f82527fa5a86343ed13d510783b1fccada0fc0c060e","last_reissued_at":"2026-05-18T00:33:58.079027Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:58.079027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.00027","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":"2026-05-18T00:33:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yUCozqMOxuNprYjNA83jXIJMPvAXkQtO0L0nSa1QHhFxpK0t+UeUV40SGtNFm1XZdwdzh7SIea7QLGfZNWjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:40:35.386686Z"},"content_sha256":"a00615b8f3b82090249c741191a67d5be8891c802c87c11a25f45ff95bc16ea7","schema_version":"1.0","event_id":"sha256:a00615b8f3b82090249c741191a67d5be8891c802c87c11a25f45ff95bc16ea7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7R72YQ7UHF7XF3VUR6BFE75FVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward a System Building Agenda for Data Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Adel Ardalan, AnHai Doan, Erik Paulson, Han Li, Haojun Zhang, Jeffrey R. Ballard, Paul Suganthan G.C., Pradap Konda, Sanjib Das, Yash Govind","submitted_at":"2017-09-29T18:43:23Z","abstract_excerpt":"In this paper we argue that the data management community should devote far more effort to building data integration (DI) systems, in order to truly advance the field. Toward this goal, we make three contributions. First, we draw on our recent industrial experience to discuss the limitations of current DI systems. Second, we propose an agenda to build a new kind of DI systems to address these limitations. These systems guide users through the DI workflow, step by step. They provide tools to address the \"pain points\" of the steps, and tools are built on top of the Python data science and Big Da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00027","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":"2026-05-18T00:33:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VByxT6gQZUrO/BoofTXNQHMvkJuOjNdcCjwEAKEuzvv4+bzuDsqX2pLoTzhopCT7/8Fz8UO3XtZ7ID0Rff4lAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:40:35.387373Z"},"content_sha256":"b33a1b0eb39a5456046a5f4e8a364007ab4143016e559e8c51666d0df7c86a27","schema_version":"1.0","event_id":"sha256:b33a1b0eb39a5456046a5f4e8a364007ab4143016e559e8c51666d0df7c86a27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7R72YQ7UHF7XF3VUR6BFE75FVB/bundle.json","state_url":"https://pith.science/pith/7R72YQ7UHF7XF3VUR6BFE75FVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7R72YQ7UHF7XF3VUR6BFE75FVB/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":"2026-05-27T03:40:35Z","links":{"resolver":"https://pith.science/pith/7R72YQ7UHF7XF3VUR6BFE75FVB","bundle":"https://pith.science/pith/7R72YQ7UHF7XF3VUR6BFE75FVB/bundle.json","state":"https://pith.science/pith/7R72YQ7UHF7XF3VUR6BFE75FVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7R72YQ7UHF7XF3VUR6BFE75FVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7R72YQ7UHF7XF3VUR6BFE75FVB","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":"cea25332c355304b9bedef2086098b755ca38ae57c3e50d4f34490f6dfd01520","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-29T18:43:23Z","title_canon_sha256":"26e17a0fefc8f45b1c289a27dc9cf923869c224507a78bd35a63ebe48ff5aec0"},"schema_version":"1.0","source":{"id":"1710.00027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00027","created_at":"2026-05-18T00:33:58Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00027v1","created_at":"2026-05-18T00:33:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00027","created_at":"2026-05-18T00:33:58Z"},{"alias_kind":"pith_short_12","alias_value":"7R72YQ7UHF7X","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7R72YQ7UHF7XF3VU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7R72YQ7U","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b33a1b0eb39a5456046a5f4e8a364007ab4143016e559e8c51666d0df7c86a27","target":"graph","created_at":"2026-05-18T00:33:58Z","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":"In this paper we argue that the data management community should devote far more effort to building data integration (DI) systems, in order to truly advance the field. Toward this goal, we make three contributions. First, we draw on our recent industrial experience to discuss the limitations of current DI systems. Second, we propose an agenda to build a new kind of DI systems to address these limitations. These systems guide users through the DI workflow, step by step. They provide tools to address the \"pain points\" of the steps, and tools are built on top of the Python data science and Big Da","authors_text":"Adel Ardalan, AnHai Doan, Erik Paulson, Han Li, Haojun Zhang, Jeffrey R. Ballard, Paul Suganthan G.C., Pradap Konda, Sanjib Das, Yash Govind","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-29T18:43:23Z","title":"Toward a System Building Agenda for Data Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00027","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:a00615b8f3b82090249c741191a67d5be8891c802c87c11a25f45ff95bc16ea7","target":"record","created_at":"2026-05-18T00:33:58Z","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":"cea25332c355304b9bedef2086098b755ca38ae57c3e50d4f34490f6dfd01520","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-09-29T18:43:23Z","title_canon_sha256":"26e17a0fefc8f45b1c289a27dc9cf923869c224507a78bd35a63ebe48ff5aec0"},"schema_version":"1.0","source":{"id":"1710.00027","kind":"arxiv","version":1}},"canonical_sha256":"fc7fac43f4397f72eeb48f82527fa5a86343ed13d510783b1fccada0fc0c060e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc7fac43f4397f72eeb48f82527fa5a86343ed13d510783b1fccada0fc0c060e","first_computed_at":"2026-05-18T00:33:58.079027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:58.079027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7SJZK9bP9rROGz4jCKJUkPnjSTiVvpXtuaSTe34TywOu4hsSbfNnPzdcIsKa3KLQIFdGw86rkgY365uxXCT+Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:58.079768Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.00027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a00615b8f3b82090249c741191a67d5be8891c802c87c11a25f45ff95bc16ea7","sha256:b33a1b0eb39a5456046a5f4e8a364007ab4143016e559e8c51666d0df7c86a27"],"state_sha256":"399abcfbec7a628f59357c502bf3412e2d29cdd7b1fdc319c12e751145ba8e6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jb0OnVQRUcztjua4xl2jnLhr+6iVu1VYFCHiwV3smxAB1bS5URwBjPgiWW0iSMVJeNk6jV+IaPhRZzwlt+ddAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T03:40:35.390729Z","bundle_sha256":"803b8bb227aebc849eefc6a775fe7524f41f12322066a05f837416a19dabcdb6"}}