{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:I6SRPPU37XOLO7PZPLBZI5TI3J","short_pith_number":"pith:I6SRPPU3","canonical_record":{"source":{"id":"2111.07904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-11-15T16:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"9b9555e0a9058f8d3282b0f761122502ea398b6d33b8ed521ba9033ece22ea07","abstract_canon_sha256":"d07ffd722f2d9c43e955cdefce65e89ee5daf89df7177f2797da884e7c3f952c"},"schema_version":"1.0"},"canonical_sha256":"47a517be9bfddcb77df97ac3947668da5a77d150a26583ae02117d530f3fff52","source":{"kind":"arxiv","id":"2111.07904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07904","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07904v2","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07904","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"I6SRPPU37XOL","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"I6SRPPU37XOLO7PZ","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"I6SRPPU3","created_at":"2026-07-05T04:03:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:I6SRPPU37XOLO7PZPLBZI5TI3J","target":"record","payload":{"canonical_record":{"source":{"id":"2111.07904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-11-15T16:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"9b9555e0a9058f8d3282b0f761122502ea398b6d33b8ed521ba9033ece22ea07","abstract_canon_sha256":"d07ffd722f2d9c43e955cdefce65e89ee5daf89df7177f2797da884e7c3f952c"},"schema_version":"1.0"},"canonical_sha256":"47a517be9bfddcb77df97ac3947668da5a77d150a26583ae02117d530f3fff52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:56.433171Z","signature_b64":"lD1xfrHTWTNrdJ8TUZis/QpAVA3q/AOAN8dkZrEbXFTGZh/c1n+rBIrud/wsbl6f4E+pWL+TlVilqGV8PXOGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47a517be9bfddcb77df97ac3947668da5a77d150a26583ae02117d530f3fff52","last_reissued_at":"2026-07-05T04:03:56.432771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:56.432771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.07904","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:03:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0+VzYn04M1AdMHYYBJ9tbYMegiIEVI37tqnWFxiTs1IIbVxPVsgCkCRs5rkHSz/Dgago5UJ/Mo7ox6zeIVtsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:23:36.940515Z"},"content_sha256":"9b58c869f90332400175e6f20d4a017062f0146052b392408a9b6c2a05d67f8c","schema_version":"1.0","event_id":"sha256:9b58c869f90332400175e6f20d4a017062f0146052b392408a9b6c2a05d67f8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:I6SRPPU37XOLO7PZPLBZI5TI3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Data Reduction for Performance Models of Data Analytics Jobs in the Cloud","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Onur Arslan","submitted_at":"2021-11-15T16:57:17Z","abstract_excerpt":"Distributed dataflow systems like Apache Flink and Apache Spark simplify processing large amounts of data on clusters in a data-parallel manner. However, choosing suitable cluster resources for distributed dataflow jobs in both type and number is difficult, especially for users who do not have access to previous performance metrics. One approach to overcoming this issue is to have users share runtime metrics to train context-aware performance models that help find a suitable configuration for the job at hand. A problem when sharing runtime data instead of trained models or model parameters is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07904","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/2111.07904/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":"2026-07-05T04:03:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibPHn7Qy3GBpjnK24cIjkOyZcKv7xjrA0wg16n14shVh5C+njdx5ezq29BkjKeckzifpfo6PHVISRvE/ErguDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:23:36.941178Z"},"content_sha256":"0978ea58c853761179fc09e05fe43e067eb41f92438dca246145cff8ef095d91","schema_version":"1.0","event_id":"sha256:0978ea58c853761179fc09e05fe43e067eb41f92438dca246145cff8ef095d91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6SRPPU37XOLO7PZPLBZI5TI3J/bundle.json","state_url":"https://pith.science/pith/I6SRPPU37XOLO7PZPLBZI5TI3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6SRPPU37XOLO7PZPLBZI5TI3J/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":"2026-08-24T02:23:36Z","links":{"resolver":"https://pith.science/pith/I6SRPPU37XOLO7PZPLBZI5TI3J","bundle":"https://pith.science/pith/I6SRPPU37XOLO7PZPLBZI5TI3J/bundle.json","state":"https://pith.science/pith/I6SRPPU37XOLO7PZPLBZI5TI3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6SRPPU37XOLO7PZPLBZI5TI3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I6SRPPU37XOLO7PZPLBZI5TI3J","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":"d07ffd722f2d9c43e955cdefce65e89ee5daf89df7177f2797da884e7c3f952c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-11-15T16:57:17Z","title_canon_sha256":"9b9555e0a9058f8d3282b0f761122502ea398b6d33b8ed521ba9033ece22ea07"},"schema_version":"1.0","source":{"id":"2111.07904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07904","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07904v2","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07904","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"I6SRPPU37XOL","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"I6SRPPU37XOLO7PZ","created_at":"2026-07-05T04:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"I6SRPPU3","created_at":"2026-07-05T04:03:56Z"}],"graph_snapshots":[{"event_id":"sha256:0978ea58c853761179fc09e05fe43e067eb41f92438dca246145cff8ef095d91","target":"graph","created_at":"2026-07-05T04:03:56Z","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/2111.07904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed dataflow systems like Apache Flink and Apache Spark simplify processing large amounts of data on clusters in a data-parallel manner. However, choosing suitable cluster resources for distributed dataflow jobs in both type and number is difficult, especially for users who do not have access to previous performance metrics. One approach to overcoming this issue is to have users share runtime metrics to train context-aware performance models that help find a suitable configuration for the job at hand. A problem when sharing runtime data instead of trained models or model parameters is ","authors_text":"Dominik Scheinert, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Onur Arslan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-11-15T16:57:17Z","title":"Training Data Reduction for Performance Models of Data Analytics Jobs in the Cloud"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07904","kind":"arxiv","version":2},"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":"sha256:9b58c869f90332400175e6f20d4a017062f0146052b392408a9b6c2a05d67f8c","target":"record","created_at":"2026-07-05T04:03:56Z","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":"d07ffd722f2d9c43e955cdefce65e89ee5daf89df7177f2797da884e7c3f952c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2021-11-15T16:57:17Z","title_canon_sha256":"9b9555e0a9058f8d3282b0f761122502ea398b6d33b8ed521ba9033ece22ea07"},"schema_version":"1.0","source":{"id":"2111.07904","kind":"arxiv","version":2}},"canonical_sha256":"47a517be9bfddcb77df97ac3947668da5a77d150a26583ae02117d530f3fff52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47a517be9bfddcb77df97ac3947668da5a77d150a26583ae02117d530f3fff52","first_computed_at":"2026-07-05T04:03:56.432771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:03:56.432771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lD1xfrHTWTNrdJ8TUZis/QpAVA3q/AOAN8dkZrEbXFTGZh/c1n+rBIrud/wsbl6f4E+pWL+TlVilqGV8PXOGCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:03:56.433171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.07904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b58c869f90332400175e6f20d4a017062f0146052b392408a9b6c2a05d67f8c","sha256:0978ea58c853761179fc09e05fe43e067eb41f92438dca246145cff8ef095d91"],"state_sha256":"ae5ef27523430972ed203c69cf61849b949c3dca0a340581bcceab01bc1bea32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4S+PjtPtJudf3i5763WUEV2VUFcJ0JUho9vDc1B+M6zQgk8Sw8qz0k5Cjzfx+SKL6+ln/eFHyOi9uA0B7/YEBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T02:23:36.947061Z","bundle_sha256":"c1bba5c6ec859e6fa26ceb7b54c9b83c6ed2b353da0ac9a281eab931c42fa3b8"}}