{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FGQ2RATS6QH5YR6XIYAKGECSVG","short_pith_number":"pith:FGQ2RATS","canonical_record":{"source":{"id":"2504.14314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-19T14:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"4e369dba0070db746d55e0921a1a3961fdce3fb47e173408bebfd9dc9a123806","abstract_canon_sha256":"acb0cca14d48ee7840b0a7f587290a9b072765ca09b7df3cae32b0bf89aa7a27"},"schema_version":"1.0"},"canonical_sha256":"29a1a88272f40fdc47d74600a31052a98c0ae95d65cd49554d8de46f1b5b49b0","source":{"kind":"arxiv","id":"2504.14314","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14314","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14314v1","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14314","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"FGQ2RATS6QH5","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"FGQ2RATS6QH5YR6X","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"FGQ2RATS","created_at":"2026-07-05T10:51:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FGQ2RATS6QH5YR6XIYAKGECSVG","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-19T14:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"4e369dba0070db746d55e0921a1a3961fdce3fb47e173408bebfd9dc9a123806","abstract_canon_sha256":"acb0cca14d48ee7840b0a7f587290a9b072765ca09b7df3cae32b0bf89aa7a27"},"schema_version":"1.0"},"canonical_sha256":"29a1a88272f40fdc47d74600a31052a98c0ae95d65cd49554d8de46f1b5b49b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:41.646351Z","signature_b64":"UxZ7qzRFIerUfStbrmJ2WElKwK2ZLGDrU71eNkS/C6YlIqam9O8VR5Ka7L5xksEx6NZ9EKL3osr5z+aNFo6gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a1a88272f40fdc47d74600a31052a98c0ae95d65cd49554d8de46f1b5b49b0","last_reissued_at":"2026-07-05T10:51:41.645940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:41.645940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14314","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":"2026-07-05T10:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"czoy5L0NfdZguWUSJ1PYp0ZtAE1L/6QtR0Oj4tqHugamcUByvUeSqoqIgWfqq1PwqmMqKKTEG2TTZ/H/Cw01CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:03:41.409702Z"},"content_sha256":"8ffbbc4c7cc01113b9069af6ce2fb12bdf1e3ca5ae0da3fb5140af63442d759a","schema_version":"1.0","event_id":"sha256:8ffbbc4c7cc01113b9069af6ce2fb12bdf1e3ca5ae0da3fb5140af63442d759a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FGQ2RATS6QH5YR6XIYAKGECSVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Polyglot Data Processing in Social Networks using the Hadoop-Spark ecosystem","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Antony Seabra, Sergio Lifschitz","submitted_at":"2025-04-19T14:33:55Z","abstract_excerpt":"This article explores the use of the Hadoop-Spark ecosystem for social media data processing, adopting a polyglot approach with the integration of various computation and storage technologies, such as Hive, HBase and GraphX. We discuss specific tasks involved in processing social network data, such as calculating user influence, counting the most frequent terms in messages and identifying social relationships among users and groups. We conducted a series of empirical performance assessments, focusing on executing selected tasks and measuring their execution time within the Hadoop-Spark cluster"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14314","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/2504.14314/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":"2026-07-05T10:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJ41TAKvU4kilNy6BKWBUxkrGS1ac+Jnrn//CrLDPYH20yBNvvgcvga1qDAmjyKQnVotKcv5/VQNi3t8/pY0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:03:41.410411Z"},"content_sha256":"564b806390dd2971cec70895fc4db8c82c8e0c0d6a76a2bc36e492af142851c4","schema_version":"1.0","event_id":"sha256:564b806390dd2971cec70895fc4db8c82c8e0c0d6a76a2bc36e492af142851c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGQ2RATS6QH5YR6XIYAKGECSVG/bundle.json","state_url":"https://pith.science/pith/FGQ2RATS6QH5YR6XIYAKGECSVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGQ2RATS6QH5YR6XIYAKGECSVG/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":"2026-07-07T13:03:41Z","links":{"resolver":"https://pith.science/pith/FGQ2RATS6QH5YR6XIYAKGECSVG","bundle":"https://pith.science/pith/FGQ2RATS6QH5YR6XIYAKGECSVG/bundle.json","state":"https://pith.science/pith/FGQ2RATS6QH5YR6XIYAKGECSVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGQ2RATS6QH5YR6XIYAKGECSVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FGQ2RATS6QH5YR6XIYAKGECSVG","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":"acb0cca14d48ee7840b0a7f587290a9b072765ca09b7df3cae32b0bf89aa7a27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-19T14:33:55Z","title_canon_sha256":"4e369dba0070db746d55e0921a1a3961fdce3fb47e173408bebfd9dc9a123806"},"schema_version":"1.0","source":{"id":"2504.14314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14314","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14314v1","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14314","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"FGQ2RATS6QH5","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"FGQ2RATS6QH5YR6X","created_at":"2026-07-05T10:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"FGQ2RATS","created_at":"2026-07-05T10:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:564b806390dd2971cec70895fc4db8c82c8e0c0d6a76a2bc36e492af142851c4","target":"graph","created_at":"2026-07-05T10:51:41Z","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/2504.14314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article explores the use of the Hadoop-Spark ecosystem for social media data processing, adopting a polyglot approach with the integration of various computation and storage technologies, such as Hive, HBase and GraphX. We discuss specific tasks involved in processing social network data, such as calculating user influence, counting the most frequent terms in messages and identifying social relationships among users and groups. We conducted a series of empirical performance assessments, focusing on executing selected tasks and measuring their execution time within the Hadoop-Spark cluster","authors_text":"Antony Seabra, Sergio Lifschitz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-19T14:33:55Z","title":"Towards Polyglot Data Processing in Social Networks using the Hadoop-Spark ecosystem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14314","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":"sha256:8ffbbc4c7cc01113b9069af6ce2fb12bdf1e3ca5ae0da3fb5140af63442d759a","target":"record","created_at":"2026-07-05T10:51:41Z","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":"acb0cca14d48ee7840b0a7f587290a9b072765ca09b7df3cae32b0bf89aa7a27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2025-04-19T14:33:55Z","title_canon_sha256":"4e369dba0070db746d55e0921a1a3961fdce3fb47e173408bebfd9dc9a123806"},"schema_version":"1.0","source":{"id":"2504.14314","kind":"arxiv","version":1}},"canonical_sha256":"29a1a88272f40fdc47d74600a31052a98c0ae95d65cd49554d8de46f1b5b49b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29a1a88272f40fdc47d74600a31052a98c0ae95d65cd49554d8de46f1b5b49b0","first_computed_at":"2026-07-05T10:51:41.645940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:41.645940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UxZ7qzRFIerUfStbrmJ2WElKwK2ZLGDrU71eNkS/C6YlIqam9O8VR5Ka7L5xksEx6NZ9EKL3osr5z+aNFo6gAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:41.646351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ffbbc4c7cc01113b9069af6ce2fb12bdf1e3ca5ae0da3fb5140af63442d759a","sha256:564b806390dd2971cec70895fc4db8c82c8e0c0d6a76a2bc36e492af142851c4"],"state_sha256":"c28ef6cda63d7faa8a2cb335c592007892a9cd090051b37be395875ed83233e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mb5ODLD20Uq3OofJBZ5x6UIEGexySam51cOi/vIEzz2fTDtJCElMVXxtmMI2mLvy68yAxH4BJDWlvd4JRq2fBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:03:41.414352Z","bundle_sha256":"9616d4ae16b35d9fe2331886709cba9e92d215e37b242b1667643236d348bf6b"}}