{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OW3UOVVURRAH6R347S6EKJ6XYK","short_pith_number":"pith:OW3UOVVU","canonical_record":{"source":{"id":"2405.17701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-27T23:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"dde74d97b021b64ef583fd114a918496eafad0f00666b276e6dc55da8cf8e934","abstract_canon_sha256":"8608cf479a9d6acd06fd085f6b0c81e22e63d3bf6dd15a1dca2ca03856714c17"},"schema_version":"1.0"},"canonical_sha256":"75b74756b48c407f477cfcbc4527d7c289f222dba43972bb77578f44518f13e7","source":{"kind":"arxiv","id":"2405.17701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17701","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17701v1","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17701","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"OW3UOVVURRAH","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"OW3UOVVURRAH6R34","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"OW3UOVVU","created_at":"2026-07-05T08:24:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OW3UOVVURRAH6R347S6EKJ6XYK","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-27T23:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"dde74d97b021b64ef583fd114a918496eafad0f00666b276e6dc55da8cf8e934","abstract_canon_sha256":"8608cf479a9d6acd06fd085f6b0c81e22e63d3bf6dd15a1dca2ca03856714c17"},"schema_version":"1.0"},"canonical_sha256":"75b74756b48c407f477cfcbc4527d7c289f222dba43972bb77578f44518f13e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:09.899393Z","signature_b64":"a2PAoKsg3fqm6sXTGhci0kCcbDOYgisNlrPeWgM5dFZXIP9vJFbVnwsK0XjyJc1n4EBsdLDbBiL7/YoHlU+fBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75b74756b48c407f477cfcbc4527d7c289f222dba43972bb77578f44518f13e7","last_reissued_at":"2026-07-05T08:24:09.898916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:09.898916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17701","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":"2026-07-05T08:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBuq8y8oJujjyhMRP7s1Cl8IN2+u+JBLOT/V0v8nLWoJs1CmCtu2eLmfQyyLeZab1k7oOf52+MuLZm1d+/93CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:19:26.094576Z"},"content_sha256":"408cc19a8c8be52e52238fcd32706d116a3b2f616831b7543f26b3a40ad74cb4","schema_version":"1.0","event_id":"sha256:408cc19a8c8be52e52238fcd32706d116a3b2f616831b7543f26b3a40ad74cb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OW3UOVVURRAH6R347S6EKJ6XYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compression and In-Situ Query Processing for Fine-Grained Array Lineage","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jinjin Zhao, Sanjay Krishnan","submitted_at":"2024-05-27T23:17:24Z","abstract_excerpt":"Tracking data lineage is important for data integrity, reproducibility, and debugging data science workflows. However, fine-grained lineage (i.e., at a cell level) is challenging to store, even for the smallest datasets. This paper introduces DSLog, a storage system that efficiently stores, indexes, and queries array data lineage, agnostic to capture methodology. A main contribution is our new compression algorithm, named ProvRC, that compresses captured lineage relationships. Using ProvRC for lineage compression result in a significant storage reduction over functions with simple spatial regu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17701","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.17701/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":"2026-07-05T08:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lt3gfa4FfqTFDFekZ9j+v1l2r87/SNfBUf3QGrBCuMQQqfsWtaQehm39CTOp9f42O61AkZ9srWSc85S6I0sNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:19:26.095157Z"},"content_sha256":"359f1eb98898b2288dc4c84b085940709f90ad6bb65639f36efa81d7b2bdde78","schema_version":"1.0","event_id":"sha256:359f1eb98898b2288dc4c84b085940709f90ad6bb65639f36efa81d7b2bdde78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OW3UOVVURRAH6R347S6EKJ6XYK/bundle.json","state_url":"https://pith.science/pith/OW3UOVVURRAH6R347S6EKJ6XYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OW3UOVVURRAH6R347S6EKJ6XYK/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":"2026-08-11T02:19:26Z","links":{"resolver":"https://pith.science/pith/OW3UOVVURRAH6R347S6EKJ6XYK","bundle":"https://pith.science/pith/OW3UOVVURRAH6R347S6EKJ6XYK/bundle.json","state":"https://pith.science/pith/OW3UOVVURRAH6R347S6EKJ6XYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OW3UOVVURRAH6R347S6EKJ6XYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OW3UOVVURRAH6R347S6EKJ6XYK","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":"8608cf479a9d6acd06fd085f6b0c81e22e63d3bf6dd15a1dca2ca03856714c17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-27T23:17:24Z","title_canon_sha256":"dde74d97b021b64ef583fd114a918496eafad0f00666b276e6dc55da8cf8e934"},"schema_version":"1.0","source":{"id":"2405.17701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17701","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17701v1","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17701","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"OW3UOVVURRAH","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"OW3UOVVURRAH6R34","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"OW3UOVVU","created_at":"2026-07-05T08:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:359f1eb98898b2288dc4c84b085940709f90ad6bb65639f36efa81d7b2bdde78","target":"graph","created_at":"2026-07-05T08:24:09Z","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/2405.17701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tracking data lineage is important for data integrity, reproducibility, and debugging data science workflows. However, fine-grained lineage (i.e., at a cell level) is challenging to store, even for the smallest datasets. This paper introduces DSLog, a storage system that efficiently stores, indexes, and queries array data lineage, agnostic to capture methodology. A main contribution is our new compression algorithm, named ProvRC, that compresses captured lineage relationships. Using ProvRC for lineage compression result in a significant storage reduction over functions with simple spatial regu","authors_text":"Jinjin Zhao, Sanjay Krishnan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-27T23:17:24Z","title":"Compression and In-Situ Query Processing for Fine-Grained Array Lineage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17701","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":"sha256:408cc19a8c8be52e52238fcd32706d116a3b2f616831b7543f26b3a40ad74cb4","target":"record","created_at":"2026-07-05T08:24:09Z","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":"8608cf479a9d6acd06fd085f6b0c81e22e63d3bf6dd15a1dca2ca03856714c17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-27T23:17:24Z","title_canon_sha256":"dde74d97b021b64ef583fd114a918496eafad0f00666b276e6dc55da8cf8e934"},"schema_version":"1.0","source":{"id":"2405.17701","kind":"arxiv","version":1}},"canonical_sha256":"75b74756b48c407f477cfcbc4527d7c289f222dba43972bb77578f44518f13e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75b74756b48c407f477cfcbc4527d7c289f222dba43972bb77578f44518f13e7","first_computed_at":"2026-07-05T08:24:09.898916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:09.898916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a2PAoKsg3fqm6sXTGhci0kCcbDOYgisNlrPeWgM5dFZXIP9vJFbVnwsK0XjyJc1n4EBsdLDbBiL7/YoHlU+fBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:09.899393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:408cc19a8c8be52e52238fcd32706d116a3b2f616831b7543f26b3a40ad74cb4","sha256:359f1eb98898b2288dc4c84b085940709f90ad6bb65639f36efa81d7b2bdde78"],"state_sha256":"41a7c4ffeb99ce7868d10ed7cbb0eb23f0b14c1029e020a0f9e0e7620e83b479"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aagmt4Zt1ThkxPnx6Tcp8MEZgoryg/RNfJcMoaj4q0mNh4RNlhHMAnUfdVYwBOqFcPMonJHrzduqF0hRntZaCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:19:26.101672Z","bundle_sha256":"9a318f0246c281a845d2fd32b7fd7fb6adc3e05d9beb9101d0b9f111e9012018"}}