{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YHHTHBHXLEK4EONSCXFG3KPD34","short_pith_number":"pith:YHHTHBHX","canonical_record":{"source":{"id":"1610.04752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-10-15T16:08:22Z","cross_cats_sorted":[],"title_canon_sha256":"05b03af8aa143d59a016b6faa67c8d48192228088c116c7c85ea2480b24a430f","abstract_canon_sha256":"0f3eea68fadea2975f017dd50fe09eb2f0d265241b06ba705e4be31bc10a854f"},"schema_version":"1.0"},"canonical_sha256":"c1cf3384f75915c239b215ca6da9e3df027ff0f5e6ddb732ebd145b76bfe3849","source":{"kind":"arxiv","id":"1610.04752","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.04752","created_at":"2026-05-18T01:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"1610.04752v1","created_at":"2026-05-18T01:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.04752","created_at":"2026-05-18T01:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"YHHTHBHXLEK4","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YHHTHBHXLEK4EONS","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YHHTHBHX","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YHHTHBHXLEK4EONSCXFG3KPD34","target":"record","payload":{"canonical_record":{"source":{"id":"1610.04752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-10-15T16:08:22Z","cross_cats_sorted":[],"title_canon_sha256":"05b03af8aa143d59a016b6faa67c8d48192228088c116c7c85ea2480b24a430f","abstract_canon_sha256":"0f3eea68fadea2975f017dd50fe09eb2f0d265241b06ba705e4be31bc10a854f"},"schema_version":"1.0"},"canonical_sha256":"c1cf3384f75915c239b215ca6da9e3df027ff0f5e6ddb732ebd145b76bfe3849","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:07.189162Z","signature_b64":"j6ZOJsfnHbw9vyR5u+6JCIvmFexNMS9AD4SJlKn08uHUV7GEEVD0IoiBCQpJjOk0T6Kc+5+gPpsYwgA6p2krCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1cf3384f75915c239b215ca6da9e3df027ff0f5e6ddb732ebd145b76bfe3849","last_reissued_at":"2026-05-18T01:02:07.188515Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:07.188515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.04752","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":"2026-05-18T01:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eVDsFvvrlXVBqSBVpQfAaTA9/QEuT21arxBXHrSXbeOJd3fUlFeIF4Haci3HgTLibkrIwWJO9uvoJxrUxHKuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T05:38:41.031097Z"},"content_sha256":"fc38c4dd0056840b88a357c8533610bd43cb3fea83a1bdcf35045e08c4bd210c","schema_version":"1.0","event_id":"sha256:fc38c4dd0056840b88a357c8533610bd43cb3fea83a1bdcf35045e08c4bd210c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YHHTHBHXLEK4EONSCXFG3KPD34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preserving the value of large scale data analytics over time through selective re-computation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jacek Cala, Maisha Rathi, Paolo Missier","submitted_at":"2016-10-15T16:08:22Z","abstract_excerpt":"A pervasive problem in Data Science is that the knowledge generated by possibly expensive analytics processes is subject to decay over time, as the data used to compute it drifts, the algorithms used in the processes are improved, and the external knowledge embodied by reference datasets used in the computation evolves. Deciding when such knowledge outcomes should be refreshed, following a sequence of data change events, requires problem-specific functions to quantify their value and its decay over time, as well as models for estimating the cost of their re-computation. What makes this problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.04752","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":"2026-05-18T01:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ctYBfnazrURl7gMCTQAtOnFbau6TjLhKly+w39qqwMOOnt/h3Pg9gNLqZdb1QH1RspUe4nFn88m7elpod2obAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T05:38:41.031452Z"},"content_sha256":"e9b55ca7916d85070ff602da0d04c910173251f28eb658b6a4be91a5ba7052a5","schema_version":"1.0","event_id":"sha256:e9b55ca7916d85070ff602da0d04c910173251f28eb658b6a4be91a5ba7052a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHHTHBHXLEK4EONSCXFG3KPD34/bundle.json","state_url":"https://pith.science/pith/YHHTHBHXLEK4EONSCXFG3KPD34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHHTHBHXLEK4EONSCXFG3KPD34/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":"2026-06-24T05:38:41Z","links":{"resolver":"https://pith.science/pith/YHHTHBHXLEK4EONSCXFG3KPD34","bundle":"https://pith.science/pith/YHHTHBHXLEK4EONSCXFG3KPD34/bundle.json","state":"https://pith.science/pith/YHHTHBHXLEK4EONSCXFG3KPD34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHHTHBHXLEK4EONSCXFG3KPD34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YHHTHBHXLEK4EONSCXFG3KPD34","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":"0f3eea68fadea2975f017dd50fe09eb2f0d265241b06ba705e4be31bc10a854f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-10-15T16:08:22Z","title_canon_sha256":"05b03af8aa143d59a016b6faa67c8d48192228088c116c7c85ea2480b24a430f"},"schema_version":"1.0","source":{"id":"1610.04752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.04752","created_at":"2026-05-18T01:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"1610.04752v1","created_at":"2026-05-18T01:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.04752","created_at":"2026-05-18T01:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"YHHTHBHXLEK4","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YHHTHBHXLEK4EONS","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YHHTHBHX","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:e9b55ca7916d85070ff602da0d04c910173251f28eb658b6a4be91a5ba7052a5","target":"graph","created_at":"2026-05-18T01:02:07Z","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":"A pervasive problem in Data Science is that the knowledge generated by possibly expensive analytics processes is subject to decay over time, as the data used to compute it drifts, the algorithms used in the processes are improved, and the external knowledge embodied by reference datasets used in the computation evolves. Deciding when such knowledge outcomes should be refreshed, following a sequence of data change events, requires problem-specific functions to quantify their value and its decay over time, as well as models for estimating the cost of their re-computation. What makes this problem","authors_text":"Jacek Cala, Maisha Rathi, Paolo Missier","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-10-15T16:08:22Z","title":"Preserving the value of large scale data analytics over time through selective re-computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.04752","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:fc38c4dd0056840b88a357c8533610bd43cb3fea83a1bdcf35045e08c4bd210c","target":"record","created_at":"2026-05-18T01:02:07Z","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":"0f3eea68fadea2975f017dd50fe09eb2f0d265241b06ba705e4be31bc10a854f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-10-15T16:08:22Z","title_canon_sha256":"05b03af8aa143d59a016b6faa67c8d48192228088c116c7c85ea2480b24a430f"},"schema_version":"1.0","source":{"id":"1610.04752","kind":"arxiv","version":1}},"canonical_sha256":"c1cf3384f75915c239b215ca6da9e3df027ff0f5e6ddb732ebd145b76bfe3849","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1cf3384f75915c239b215ca6da9e3df027ff0f5e6ddb732ebd145b76bfe3849","first_computed_at":"2026-05-18T01:02:07.188515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:02:07.188515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j6ZOJsfnHbw9vyR5u+6JCIvmFexNMS9AD4SJlKn08uHUV7GEEVD0IoiBCQpJjOk0T6Kc+5+gPpsYwgA6p2krCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:02:07.189162Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.04752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc38c4dd0056840b88a357c8533610bd43cb3fea83a1bdcf35045e08c4bd210c","sha256:e9b55ca7916d85070ff602da0d04c910173251f28eb658b6a4be91a5ba7052a5"],"state_sha256":"8845ad2222c48f1538b5cad4cb26c595f52d166f90199c4d016fee22d1fe104d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDqM1VWX5SpGDEr8OvVBs6PWlHeVAcKde5aLljiD4B/3H8lzO1RIJvNQrtzAxYcw5IhbmjAL5IVurjpJ4xk/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T05:38:41.033472Z","bundle_sha256":"fcbc665d1eb13485e697099648d0e38a67f3abf39841fa14dc885e9f75300a3d"}}