{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QPXHSH5JF3FFQBDZE53F5XOIMA","short_pith_number":"pith:QPXHSH5J","canonical_record":{"source":{"id":"2001.00888","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-03T16:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"fd330bdfedee2de9f8702db7039c2a9776e32aa0037fd309e9fab4b9d5b2807d","abstract_canon_sha256":"7a9604ec4cfabf6446048322180c8870c0d70f3e2c9b2eee8e73ef760b3f8f68"},"schema_version":"1.0"},"canonical_sha256":"83ee791fa92eca58047927765eddc8603983a4a80f317effe92978bcb851463b","source":{"kind":"arxiv","id":"2001.00888","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00888","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00888v4","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00888","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"QPXHSH5JF3FF","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"QPXHSH5JF3FFQBDZ","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"QPXHSH5J","created_at":"2026-07-05T01:07:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QPXHSH5JF3FFQBDZE53F5XOIMA","target":"record","payload":{"canonical_record":{"source":{"id":"2001.00888","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-03T16:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"fd330bdfedee2de9f8702db7039c2a9776e32aa0037fd309e9fab4b9d5b2807d","abstract_canon_sha256":"7a9604ec4cfabf6446048322180c8870c0d70f3e2c9b2eee8e73ef760b3f8f68"},"schema_version":"1.0"},"canonical_sha256":"83ee791fa92eca58047927765eddc8603983a4a80f317effe92978bcb851463b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:26.132762Z","signature_b64":"QNooeVG3PDpYagNFYpHx48WFApGBMyePNag/4HZ7etk2gmga0tYAOM4+hmLN7Xs6xRGFMqUkbsSI+tKE+5i1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ee791fa92eca58047927765eddc8603983a4a80f317effe92978bcb851463b","last_reissued_at":"2026-07-05T01:07:26.132220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:26.132220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.00888","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNKR1NcfPK2Br1SrlyptpZb3f6346DQjizHK6fShvj52VkJMWCRuSropfDhEQpkbXeu37ET4OD1l/z+ESIpbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:18:46.003904Z"},"content_sha256":"094fd63262f0504cbfe1d647f482c536c23cfa9241fd1cc95dbc22e778a33e84","schema_version":"1.0","event_id":"sha256:094fd63262f0504cbfe1d647f482c536c23cfa9241fd1cc95dbc22e778a33e84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QPXHSH5JF3FFQBDZE53F5XOIMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Scalable Dataframe Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aditya Parameswaran, Anthony D. Joseph, Devin Petersohn, Doris Lee, Doris Xin, Joseph E. Gonzalez, Joseph M. Hellerstein, Stephen Macke, William Ma, Xiangxi Mo","submitted_at":"2020-01-03T16:56:55Z","abstract_excerpt":"Dataframes are a popular abstraction to represent, prepare, and analyze data. Despite the remarkable success of dataframe libraries in Rand Python, dataframes face performance issues even on moderately large datasets. Moreover, there is significant ambiguity regarding dataframe semantics. In this paper we lay out a vision and roadmap for scalable dataframe systems. To demonstrate the potential in this area, we report on our experience building MODIN, a scaled-up implementation of the most widely-used and complex dataframe API today, Python's pandas. With pandas as a reference, we propose a sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00888","kind":"arxiv","version":4},"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/2001.00888/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":"2026-07-05T01:07:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0LmfUc9EZNUU3EcZyaowz1kGeAfs5W628bdy0foRkUS0ehdn9wPk6CZ9oilrEblWQEjQZTUR/bsia9OghCkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:18:46.004781Z"},"content_sha256":"0388dfcc1dabeb370d49b8b2c9c9002e5b010bc0d4ef0d64906fdfd8475bb9d1","schema_version":"1.0","event_id":"sha256:0388dfcc1dabeb370d49b8b2c9c9002e5b010bc0d4ef0d64906fdfd8475bb9d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPXHSH5JF3FFQBDZE53F5XOIMA/bundle.json","state_url":"https://pith.science/pith/QPXHSH5JF3FFQBDZE53F5XOIMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPXHSH5JF3FFQBDZE53F5XOIMA/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":"2026-08-08T01:18:46Z","links":{"resolver":"https://pith.science/pith/QPXHSH5JF3FFQBDZE53F5XOIMA","bundle":"https://pith.science/pith/QPXHSH5JF3FFQBDZE53F5XOIMA/bundle.json","state":"https://pith.science/pith/QPXHSH5JF3FFQBDZE53F5XOIMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPXHSH5JF3FFQBDZE53F5XOIMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QPXHSH5JF3FFQBDZE53F5XOIMA","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":"7a9604ec4cfabf6446048322180c8870c0d70f3e2c9b2eee8e73ef760b3f8f68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-03T16:56:55Z","title_canon_sha256":"fd330bdfedee2de9f8702db7039c2a9776e32aa0037fd309e9fab4b9d5b2807d"},"schema_version":"1.0","source":{"id":"2001.00888","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00888","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00888v4","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00888","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"QPXHSH5JF3FF","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"QPXHSH5JF3FFQBDZ","created_at":"2026-07-05T01:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"QPXHSH5J","created_at":"2026-07-05T01:07:26Z"}],"graph_snapshots":[{"event_id":"sha256:0388dfcc1dabeb370d49b8b2c9c9002e5b010bc0d4ef0d64906fdfd8475bb9d1","target":"graph","created_at":"2026-07-05T01:07:26Z","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/2001.00888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dataframes are a popular abstraction to represent, prepare, and analyze data. Despite the remarkable success of dataframe libraries in Rand Python, dataframes face performance issues even on moderately large datasets. Moreover, there is significant ambiguity regarding dataframe semantics. In this paper we lay out a vision and roadmap for scalable dataframe systems. To demonstrate the potential in this area, we report on our experience building MODIN, a scaled-up implementation of the most widely-used and complex dataframe API today, Python's pandas. With pandas as a reference, we propose a sim","authors_text":"Aditya Parameswaran, Anthony D. Joseph, Devin Petersohn, Doris Lee, Doris Xin, Joseph E. Gonzalez, Joseph M. Hellerstein, Stephen Macke, William Ma, Xiangxi Mo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-03T16:56:55Z","title":"Towards Scalable Dataframe Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00888","kind":"arxiv","version":4},"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":"sha256:094fd63262f0504cbfe1d647f482c536c23cfa9241fd1cc95dbc22e778a33e84","target":"record","created_at":"2026-07-05T01:07:26Z","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":"7a9604ec4cfabf6446048322180c8870c0d70f3e2c9b2eee8e73ef760b3f8f68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-01-03T16:56:55Z","title_canon_sha256":"fd330bdfedee2de9f8702db7039c2a9776e32aa0037fd309e9fab4b9d5b2807d"},"schema_version":"1.0","source":{"id":"2001.00888","kind":"arxiv","version":4}},"canonical_sha256":"83ee791fa92eca58047927765eddc8603983a4a80f317effe92978bcb851463b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83ee791fa92eca58047927765eddc8603983a4a80f317effe92978bcb851463b","first_computed_at":"2026-07-05T01:07:26.132220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:26.132220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QNooeVG3PDpYagNFYpHx48WFApGBMyePNag/4HZ7etk2gmga0tYAOM4+hmLN7Xs6xRGFMqUkbsSI+tKE+5i1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:26.132762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.00888","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:094fd63262f0504cbfe1d647f482c536c23cfa9241fd1cc95dbc22e778a33e84","sha256:0388dfcc1dabeb370d49b8b2c9c9002e5b010bc0d4ef0d64906fdfd8475bb9d1"],"state_sha256":"caaccd469080775c34fd1626b2a2d240600a779f8d24ece5b3c4f26bade4b1ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tohlRA9f23tD3zNDYHS+rAlIoZ8izUVV310T7rbx9gsgxZuqyOehluvR/i9DxoUm3sKqHHHJseKES8fypiu5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:18:46.016568Z","bundle_sha256":"e9606bae336cdde8db6c255eca99dcc9ac2a1b34eb59c45498d7953cc6eecde4"}}