{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:65MWNSPUHLUBMQCOTJZCO3VKAC","short_pith_number":"pith:65MWNSPU","schema_version":"1.0","canonical_sha256":"f75966c9f43ae816404e9a72276eaa0095b07d18725db7f61e3d5e7fb52a746c","source":{"kind":"arxiv","id":"2108.02582","version":1},"attestation_state":"computed","paper":{"title":"An Abstract View of Big Data Processing Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.SE","authors_text":"Anamaria Martins Moreira, Genoveva Vargas-Solar, Joao Batista de Souza Neto, Martin A. Musicante","submitted_at":"2021-08-05T12:40:54Z","abstract_excerpt":"This paper proposes a model for specifying data flow based parallel data processing programs agnostic of target Big Data processing frameworks. The paper focuses on the formal abstract specification of non-iterative and iterative programs, generalizing the strategies adopted by data flow Big Data processing frameworks. The proposed model relies on monoid AlgebraandPetri Netstoabstract Big Data processing programs in two levels: a high level representing the program data flow and a lower level representing data transformation operations (e.g., filtering, aggregation, join). We extend the model "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2108.02582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2021-08-05T12:40:54Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"718469eca41d6cebbdc264f9a259ae9b9c9a8456d5a987bcac0229dd0737dd8b","abstract_canon_sha256":"a9214bd68d032c0c2d326b675590a633e1f25b0de2519f05ae686f9ac9abb702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:34.421795Z","signature_b64":"RO6RwHLUmX/bEmRYMJ3WF1/w7+1j1KTLpOMmbIrDTSXP6yEhqDyVKMvJuN2+YZ7xbHOzQmPJaZlZH9dZJMvfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f75966c9f43ae816404e9a72276eaa0095b07d18725db7f61e3d5e7fb52a746c","last_reissued_at":"2026-07-05T03:03:34.421271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:34.421271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Abstract View of Big Data Processing Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.SE","authors_text":"Anamaria Martins Moreira, Genoveva Vargas-Solar, Joao Batista de Souza Neto, Martin A. Musicante","submitted_at":"2021-08-05T12:40:54Z","abstract_excerpt":"This paper proposes a model for specifying data flow based parallel data processing programs agnostic of target Big Data processing frameworks. The paper focuses on the formal abstract specification of non-iterative and iterative programs, generalizing the strategies adopted by data flow Big Data processing frameworks. The proposed model relies on monoid AlgebraandPetri Netstoabstract Big Data processing programs in two levels: a high level representing the program data flow and a lower level representing data transformation operations (e.g., filtering, aggregation, join). We extend the model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02582","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/2108.02582/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2108.02582","created_at":"2026-07-05T03:03:34.421350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02582v1","created_at":"2026-07-05T03:03:34.421350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02582","created_at":"2026-07-05T03:03:34.421350+00:00"},{"alias_kind":"pith_short_12","alias_value":"65MWNSPUHLUB","created_at":"2026-07-05T03:03:34.421350+00:00"},{"alias_kind":"pith_short_16","alias_value":"65MWNSPUHLUBMQCO","created_at":"2026-07-05T03:03:34.421350+00:00"},{"alias_kind":"pith_short_8","alias_value":"65MWNSPU","created_at":"2026-07-05T03:03:34.421350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC","json":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC.json","graph_json":"https://pith.science/api/pith-number/65MWNSPUHLUBMQCOTJZCO3VKAC/graph.json","events_json":"https://pith.science/api/pith-number/65MWNSPUHLUBMQCOTJZCO3VKAC/events.json","paper":"https://pith.science/paper/65MWNSPU"},"agent_actions":{"view_html":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC","download_json":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC.json","view_paper":"https://pith.science/paper/65MWNSPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02582&json=true","fetch_graph":"https://pith.science/api/pith-number/65MWNSPUHLUBMQCOTJZCO3VKAC/graph.json","fetch_events":"https://pith.science/api/pith-number/65MWNSPUHLUBMQCOTJZCO3VKAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC/action/storage_attestation","attest_author":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC/action/author_attestation","sign_citation":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC/action/citation_signature","submit_replication":"https://pith.science/pith/65MWNSPUHLUBMQCOTJZCO3VKAC/action/replication_record"}},"created_at":"2026-07-05T03:03:34.421350+00:00","updated_at":"2026-07-05T03:03:34.421350+00:00"}