{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:ZDSTK5W7MNQFHNBE3AYYV4CDHK","short_pith_number":"pith:ZDSTK5W7","schema_version":"1.0","canonical_sha256":"c8e53576df636053b424d8318af0433ab8c1d8144c914f0c6f7211d94bc4a3ee","source":{"kind":"arxiv","id":"1303.5367","version":3},"attestation_state":"computed","paper":{"title":"Taming the zoo - about algorithms implementation in the ecosystem of Apache Hadoop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.IR","authors_text":"Adam Kawa, Artur Czeczko, Lukasz Bolikowski, Mateusz Fedoryszak, Piotr Jan Dendek, Piotr Wendykier","submitted_at":"2013-03-21T18:56:06Z","abstract_excerpt":"Content Analysis System (CoAnSys) is a research framework for mining scientific publications using Apache Hadoop. This article describes the algorithms currently implemented in CoAnSys including classification, categorization and citation matching of scientific publications. The size of the input data classifies these algorithms in the range of big data problems, which can be efficiently solved on Hadoop clusters."},"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":"1303.5367","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-03-21T18:56:06Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"acac72b9d722120cba6380bb6537958177982bc458b696bb4125065f57bded04","abstract_canon_sha256":"cdbcbd047fd94b63b0991d3754490713fc9bb9971a53067606b758423a771b84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:19.236489Z","signature_b64":"sK0fjd1U6aiGH2LVZawhbk0DMKFG15CEDufYtYiSC7reiDqkQiD+dO1e2S0MMofy+vvpuLjakxb1C3ljHxnQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e53576df636053b424d8318af0433ab8c1d8144c914f0c6f7211d94bc4a3ee","last_reissued_at":"2026-05-18T02:56:19.235836Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:19.235836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming the zoo - about algorithms implementation in the ecosystem of Apache Hadoop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.IR","authors_text":"Adam Kawa, Artur Czeczko, Lukasz Bolikowski, Mateusz Fedoryszak, Piotr Jan Dendek, Piotr Wendykier","submitted_at":"2013-03-21T18:56:06Z","abstract_excerpt":"Content Analysis System (CoAnSys) is a research framework for mining scientific publications using Apache Hadoop. This article describes the algorithms currently implemented in CoAnSys including classification, categorization and citation matching of scientific publications. The size of the input data classifies these algorithms in the range of big data problems, which can be efficiently solved on Hadoop clusters."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.5367","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1303.5367","created_at":"2026-05-18T02:56:19.235922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1303.5367v3","created_at":"2026-05-18T02:56:19.235922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.5367","created_at":"2026-05-18T02:56:19.235922+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDSTK5W7MNQF","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDSTK5W7MNQFHNBE","created_at":"2026-05-18T12:28:09.283467+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDSTK5W7","created_at":"2026-05-18T12:28:09.283467+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/ZDSTK5W7MNQFHNBE3AYYV4CDHK","json":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK.json","graph_json":"https://pith.science/api/pith-number/ZDSTK5W7MNQFHNBE3AYYV4CDHK/graph.json","events_json":"https://pith.science/api/pith-number/ZDSTK5W7MNQFHNBE3AYYV4CDHK/events.json","paper":"https://pith.science/paper/ZDSTK5W7"},"agent_actions":{"view_html":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK","download_json":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK.json","view_paper":"https://pith.science/paper/ZDSTK5W7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1303.5367&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDSTK5W7MNQFHNBE3AYYV4CDHK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDSTK5W7MNQFHNBE3AYYV4CDHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK/action/storage_attestation","attest_author":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK/action/author_attestation","sign_citation":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK/action/citation_signature","submit_replication":"https://pith.science/pith/ZDSTK5W7MNQFHNBE3AYYV4CDHK/action/replication_record"}},"created_at":"2026-05-18T02:56:19.235922+00:00","updated_at":"2026-05-18T02:56:19.235922+00:00"}