{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5YABCWG7WX3OI3FW4LFK3QEZDN","short_pith_number":"pith:5YABCWG7","canonical_record":{"source":{"id":"1701.06093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-01-21T22:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"7cc14791d2538afd2fedd61e53fca483251d6eb78263016d63d15abd4be8381a","abstract_canon_sha256":"e33fba85c429cfd382eeec2c7d987c64f410123a38320b8e3dc92167cde46ef8"},"schema_version":"1.0"},"canonical_sha256":"ee001158dfb5f6e46cb6e2caadc0991b6a0373100aa871fb79c074549eabf560","source":{"kind":"arxiv","id":"1701.06093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.06093","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"arxiv_version","alias_value":"1701.06093v1","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.06093","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"pith_short_12","alias_value":"5YABCWG7WX3O","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"5YABCWG7WX3OI3FW","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"5YABCWG7","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5YABCWG7WX3OI3FW4LFK3QEZDN","target":"record","payload":{"canonical_record":{"source":{"id":"1701.06093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-01-21T22:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"7cc14791d2538afd2fedd61e53fca483251d6eb78263016d63d15abd4be8381a","abstract_canon_sha256":"e33fba85c429cfd382eeec2c7d987c64f410123a38320b8e3dc92167cde46ef8"},"schema_version":"1.0"},"canonical_sha256":"ee001158dfb5f6e46cb6e2caadc0991b6a0373100aa871fb79c074549eabf560","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:19.336115Z","signature_b64":"kfsn38OLg4Ui3m9Mc2TrNXyHkpYuJmQfVqsJG6f7Dde4PZL24M2xMQlqkpkdXqXvuvW3BLcpyVOeAn59dVNFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee001158dfb5f6e46cb6e2caadc0991b6a0373100aa871fb79c074549eabf560","last_reissued_at":"2026-05-18T00:52:19.335557Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:19.335557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.06093","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":"2026-05-18T00:52:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBvhNzJV8rBM8/4zxxjTAXX1A4aJT49fLnYRYmSUppxTFTP39pKTyTkvbRRplZQvLGDMnoNsUTQeWPaV17s0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:51:51.435766Z"},"content_sha256":"5caac1339bd80d752e1bef64fa7bd58240c5f38cab44961a6f04c9c462ee04ba","schema_version":"1.0","event_id":"sha256:5caac1339bd80d752e1bef64fa7bd58240c5f38cab44961a6f04c9c462ee04ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5YABCWG7WX3OI3FW4LFK3QEZDN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"INGESTBASE: A Declarative Data Ingestion System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alekh Jindal, Jorge-Arnulfo Quiane-Ruiz, Samuel Madden","submitted_at":"2017-01-21T22:34:47Z","abstract_excerpt":"Big data applications have fast arriving data that must be quickly ingested. At the same time, they have specific needs to preprocess and transform the data before it could be put to use. The current practice is to do these preparatory transformations once the data is already ingested, however, this is expensive to run and cumbersome to manage. As a result, there is a need to push data preprocessing down to the ingestion itself. In this paper, we present a declarative data ingestion system, called INGESTBASE, to allow application developers to plan and specify their data ingestion logic in a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.06093","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":"2026-05-18T00:52:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qp8E782rhKiw10OW0mCYvjuOrRxHOuHItnFiSaVeMz8kuJE4mo4EkqR9IElCABue8Z0de1T4IgbAYOBJurNSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:51:51.436112Z"},"content_sha256":"348cecd552beeabb6d066d3b704e69ec194f4403d2c2370f02bc2b816a92c942","schema_version":"1.0","event_id":"sha256:348cecd552beeabb6d066d3b704e69ec194f4403d2c2370f02bc2b816a92c942"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YABCWG7WX3OI3FW4LFK3QEZDN/bundle.json","state_url":"https://pith.science/pith/5YABCWG7WX3OI3FW4LFK3QEZDN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YABCWG7WX3OI3FW4LFK3QEZDN/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":"2026-06-02T02:51:51Z","links":{"resolver":"https://pith.science/pith/5YABCWG7WX3OI3FW4LFK3QEZDN","bundle":"https://pith.science/pith/5YABCWG7WX3OI3FW4LFK3QEZDN/bundle.json","state":"https://pith.science/pith/5YABCWG7WX3OI3FW4LFK3QEZDN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YABCWG7WX3OI3FW4LFK3QEZDN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5YABCWG7WX3OI3FW4LFK3QEZDN","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":"e33fba85c429cfd382eeec2c7d987c64f410123a38320b8e3dc92167cde46ef8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-01-21T22:34:47Z","title_canon_sha256":"7cc14791d2538afd2fedd61e53fca483251d6eb78263016d63d15abd4be8381a"},"schema_version":"1.0","source":{"id":"1701.06093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.06093","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"arxiv_version","alias_value":"1701.06093v1","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.06093","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"pith_short_12","alias_value":"5YABCWG7WX3O","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"5YABCWG7WX3OI3FW","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"5YABCWG7","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:348cecd552beeabb6d066d3b704e69ec194f4403d2c2370f02bc2b816a92c942","target":"graph","created_at":"2026-05-18T00:52:19Z","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":"Big data applications have fast arriving data that must be quickly ingested. At the same time, they have specific needs to preprocess and transform the data before it could be put to use. The current practice is to do these preparatory transformations once the data is already ingested, however, this is expensive to run and cumbersome to manage. As a result, there is a need to push data preprocessing down to the ingestion itself. In this paper, we present a declarative data ingestion system, called INGESTBASE, to allow application developers to plan and specify their data ingestion logic in a m","authors_text":"Alekh Jindal, Jorge-Arnulfo Quiane-Ruiz, Samuel Madden","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-01-21T22:34:47Z","title":"INGESTBASE: A Declarative Data Ingestion System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.06093","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":"sha256:5caac1339bd80d752e1bef64fa7bd58240c5f38cab44961a6f04c9c462ee04ba","target":"record","created_at":"2026-05-18T00:52:19Z","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":"e33fba85c429cfd382eeec2c7d987c64f410123a38320b8e3dc92167cde46ef8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-01-21T22:34:47Z","title_canon_sha256":"7cc14791d2538afd2fedd61e53fca483251d6eb78263016d63d15abd4be8381a"},"schema_version":"1.0","source":{"id":"1701.06093","kind":"arxiv","version":1}},"canonical_sha256":"ee001158dfb5f6e46cb6e2caadc0991b6a0373100aa871fb79c074549eabf560","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee001158dfb5f6e46cb6e2caadc0991b6a0373100aa871fb79c074549eabf560","first_computed_at":"2026-05-18T00:52:19.335557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:19.335557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kfsn38OLg4Ui3m9Mc2TrNXyHkpYuJmQfVqsJG6f7Dde4PZL24M2xMQlqkpkdXqXvuvW3BLcpyVOeAn59dVNFBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:19.336115Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.06093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5caac1339bd80d752e1bef64fa7bd58240c5f38cab44961a6f04c9c462ee04ba","sha256:348cecd552beeabb6d066d3b704e69ec194f4403d2c2370f02bc2b816a92c942"],"state_sha256":"d26759652360227c7acc190471feec0e71fe0980c42bb09b5d1cb4e3fe2c95d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"soaVxbyxrAeEv6mH/DDLVFjGBgX7uhYyb4Sn9ye7uzSgwHMLeQ33MHR2xBEIdhCFwBNTzN95Xz3HHPgUvfnIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T02:51:51.438082Z","bundle_sha256":"ac427dfcc899ce527538cb6038db1e5df6f909baddbd418ae1630afc68390db2"}}