{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3Q7WB7SMMLUHHGCKQTZNRVR2ED","short_pith_number":"pith:3Q7WB7SM","canonical_record":{"source":{"id":"2401.00865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-12-29T21:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"e786f292aaadf2b0e018ac41752cbe261857a224bc95ee780d90f894c0feffbe","abstract_canon_sha256":"880761f618ba6298d93ac3a4b558f7b97b5eb82a93936f1f75c3f6eb1c6c0662"},"schema_version":"1.0"},"canonical_sha256":"dc3f60fe4c62e873984a84f2d8d63a20fc3c0c5f8133944f406fc945a7d5e36d","source":{"kind":"arxiv","id":"2401.00865","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00865","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00865v2","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00865","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"pith_short_12","alias_value":"3Q7WB7SMMLUH","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"pith_short_16","alias_value":"3Q7WB7SMMLUHHGCK","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"pith_short_8","alias_value":"3Q7WB7SM","created_at":"2026-07-05T07:57:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3Q7WB7SMMLUHHGCKQTZNRVR2ED","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-12-29T21:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"e786f292aaadf2b0e018ac41752cbe261857a224bc95ee780d90f894c0feffbe","abstract_canon_sha256":"880761f618ba6298d93ac3a4b558f7b97b5eb82a93936f1f75c3f6eb1c6c0662"},"schema_version":"1.0"},"canonical_sha256":"dc3f60fe4c62e873984a84f2d8d63a20fc3c0c5f8133944f406fc945a7d5e36d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:48.267239Z","signature_b64":"f97mBqVs7DjZz78RU6O9mOyeyxC9a20YrCNLg46BOPzFb2TDzHyECcghvbBHTuu89lhNdghHB656gQ3o2LPgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc3f60fe4c62e873984a84f2d8d63a20fc3c0c5f8133944f406fc945a7d5e36d","last_reissued_at":"2026-07-05T07:57:48.266741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:48.266741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00865","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":"2026-07-05T07:57:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R/9Tfp9dGkHy0/X8c9O6Y0LfdCG6kIhAbOfpdzw9Iyz+IRar08BT5rEkFMh8Rvjo1stxhfVZ8U9jwoISJmCsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:50:00.939216Z"},"content_sha256":"072e5f7e2b805e45050a8beade531f35080f30c1749806d2603c55cd666039c0","schema_version":"1.0","event_id":"sha256:072e5f7e2b805e45050a8beade531f35080f30c1749806d2603c55cd666039c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3Q7WB7SMMLUHHGCKQTZNRVR2ED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Xorbits: Automating Operator Tiling for Distributed Data Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Chengjie Li, Feng Zhang, Kaisheng He, Tao Yuan, Weizheng Lu, Xia Liao, Xiaoyong Du, Xuye Qin, Yueguo Chen, Zhong Wang","submitted_at":"2023-12-29T21:49:56Z","abstract_excerpt":"Data science pipelines commonly utilize dataframe and array operations for tasks such as data preprocessing, analysis, and machine learning. The most popular tools for these tasks are pandas and NumPy. However, these tools are limited to executing on a single node, making them unsuitable for processing large-scale data. Several systems have attempted to distribute data science applications to clusters while maintaining interfaces similar to single-node libraries, enabling data scientists to scale their workloads without significant effort. However, existing systems often struggle with processi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00865","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/2401.00865/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":"2026-07-05T07:57:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9iNKnAy9mtrvHh+L35uIg/Z6ajnEgM4X+WkkTekIT+J5sNenPD2ejiPQBD0NURHiHczrC2q9jyKRsWpFs6w9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:50:00.939588Z"},"content_sha256":"72d89740d66eda1d66e824daf1a829d17db15f7a4f05efd62a1cb2ed94da0c5d","schema_version":"1.0","event_id":"sha256:72d89740d66eda1d66e824daf1a829d17db15f7a4f05efd62a1cb2ed94da0c5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED/bundle.json","state_url":"https://pith.science/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED/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":"2026-07-17T05:50:00Z","links":{"resolver":"https://pith.science/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED","bundle":"https://pith.science/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED/bundle.json","state":"https://pith.science/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3Q7WB7SMMLUHHGCKQTZNRVR2ED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3Q7WB7SMMLUHHGCKQTZNRVR2ED","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":"880761f618ba6298d93ac3a4b558f7b97b5eb82a93936f1f75c3f6eb1c6c0662","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-12-29T21:49:56Z","title_canon_sha256":"e786f292aaadf2b0e018ac41752cbe261857a224bc95ee780d90f894c0feffbe"},"schema_version":"1.0","source":{"id":"2401.00865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00865","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00865v2","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00865","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"pith_short_12","alias_value":"3Q7WB7SMMLUH","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"pith_short_16","alias_value":"3Q7WB7SMMLUHHGCK","created_at":"2026-07-05T07:57:48Z"},{"alias_kind":"pith_short_8","alias_value":"3Q7WB7SM","created_at":"2026-07-05T07:57:48Z"}],"graph_snapshots":[{"event_id":"sha256:72d89740d66eda1d66e824daf1a829d17db15f7a4f05efd62a1cb2ed94da0c5d","target":"graph","created_at":"2026-07-05T07:57:48Z","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/2401.00865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data science pipelines commonly utilize dataframe and array operations for tasks such as data preprocessing, analysis, and machine learning. The most popular tools for these tasks are pandas and NumPy. However, these tools are limited to executing on a single node, making them unsuitable for processing large-scale data. Several systems have attempted to distribute data science applications to clusters while maintaining interfaces similar to single-node libraries, enabling data scientists to scale their workloads without significant effort. However, existing systems often struggle with processi","authors_text":"Chengjie Li, Feng Zhang, Kaisheng He, Tao Yuan, Weizheng Lu, Xia Liao, Xiaoyong Du, Xuye Qin, Yueguo Chen, Zhong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-12-29T21:49:56Z","title":"Xorbits: Automating Operator Tiling for Distributed Data Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00865","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":"sha256:072e5f7e2b805e45050a8beade531f35080f30c1749806d2603c55cd666039c0","target":"record","created_at":"2026-07-05T07:57:48Z","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":"880761f618ba6298d93ac3a4b558f7b97b5eb82a93936f1f75c3f6eb1c6c0662","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-12-29T21:49:56Z","title_canon_sha256":"e786f292aaadf2b0e018ac41752cbe261857a224bc95ee780d90f894c0feffbe"},"schema_version":"1.0","source":{"id":"2401.00865","kind":"arxiv","version":2}},"canonical_sha256":"dc3f60fe4c62e873984a84f2d8d63a20fc3c0c5f8133944f406fc945a7d5e36d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc3f60fe4c62e873984a84f2d8d63a20fc3c0c5f8133944f406fc945a7d5e36d","first_computed_at":"2026-07-05T07:57:48.266741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:48.266741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f97mBqVs7DjZz78RU6O9mOyeyxC9a20YrCNLg46BOPzFb2TDzHyECcghvbBHTuu89lhNdghHB656gQ3o2LPgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:48.267239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:072e5f7e2b805e45050a8beade531f35080f30c1749806d2603c55cd666039c0","sha256:72d89740d66eda1d66e824daf1a829d17db15f7a4f05efd62a1cb2ed94da0c5d"],"state_sha256":"92217f0f84d037acb6989aa97744d91933fd6984760d671f1fd55e5508534a2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6Vmb7FJ5w0ZDMPE1GYrHybgl7A3wvlmGHiCiQ6xPHh/sM0/iiACmNrzAZwKW5pAdBOh3YnFhRHZMPi9gd2qAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T05:50:00.941749Z","bundle_sha256":"5dbab98d391be4d427b35d2d6f4148cdff7a03b19dd9c3e03e620609e1325763"}}