{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:X55SAUYBMC7J43GVAENHODVXVN","short_pith_number":"pith:X55SAUYB","schema_version":"1.0","canonical_sha256":"bf7b20530160be9e6cd5011a770eb7ab4b2ba3c8d262b7840bdf2c9e711c15e3","source":{"kind":"arxiv","id":"1601.06919","version":1},"attestation_state":"computed","paper":{"title":"BUbiNG: Massive Crawling for the Masses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Andrea Marino, Massimo Santini, Paolo Boldi, Sebastiano Vigna","submitted_at":"2016-01-26T08:22:37Z","abstract_excerpt":"Although web crawlers have been around for twenty years by now, there is virtually no freely available, opensource crawling software that guarantees high throughput, overcomes the limits of single-machine systems and at the same time scales linearly with the amount of resources available. This paper aims at filling this gap, through the description of BUbiNG, our next-generation web crawler built upon the authors' experience with UbiCrawler [Boldi et al. 2004] and on the last ten years of research on the topic. BUbiNG is an opensource Java fully distributed crawler; a single BUbiNG agent, usin"},"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":"1601.06919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-01-26T08:22:37Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"400353677725c7f0ed7a0196a82f88831399b6cb30672d5d82930281d6d4cc11","abstract_canon_sha256":"3b48d89c7f15905f66f2bafb8627dc083501ebee2892a7a7f45599ea432e078a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:59.534873Z","signature_b64":"WNWKPtcLONtFbVi+3+EmEzAEr66PBZ0HxSHc4dgrsGC20klFurt2mSLcJV+wxQ8FiZgw3iR28bjbdZSxQwA5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7b20530160be9e6cd5011a770eb7ab4b2ba3c8d262b7840bdf2c9e711c15e3","last_reissued_at":"2026-05-18T01:21:59.534273Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:59.534273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BUbiNG: Massive Crawling for the Masses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.IR","authors_text":"Andrea Marino, Massimo Santini, Paolo Boldi, Sebastiano Vigna","submitted_at":"2016-01-26T08:22:37Z","abstract_excerpt":"Although web crawlers have been around for twenty years by now, there is virtually no freely available, opensource crawling software that guarantees high throughput, overcomes the limits of single-machine systems and at the same time scales linearly with the amount of resources available. This paper aims at filling this gap, through the description of BUbiNG, our next-generation web crawler built upon the authors' experience with UbiCrawler [Boldi et al. 2004] and on the last ten years of research on the topic. BUbiNG is an opensource Java fully distributed crawler; a single BUbiNG agent, usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.06919","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":""},"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":"1601.06919","created_at":"2026-05-18T01:21:59.534367+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.06919v1","created_at":"2026-05-18T01:21:59.534367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.06919","created_at":"2026-05-18T01:21:59.534367+00:00"},{"alias_kind":"pith_short_12","alias_value":"X55SAUYBMC7J","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"X55SAUYBMC7J43GV","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"X55SAUYB","created_at":"2026-05-18T12:30:51.357362+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/X55SAUYBMC7J43GVAENHODVXVN","json":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN.json","graph_json":"https://pith.science/api/pith-number/X55SAUYBMC7J43GVAENHODVXVN/graph.json","events_json":"https://pith.science/api/pith-number/X55SAUYBMC7J43GVAENHODVXVN/events.json","paper":"https://pith.science/paper/X55SAUYB"},"agent_actions":{"view_html":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN","download_json":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN.json","view_paper":"https://pith.science/paper/X55SAUYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.06919&json=true","fetch_graph":"https://pith.science/api/pith-number/X55SAUYBMC7J43GVAENHODVXVN/graph.json","fetch_events":"https://pith.science/api/pith-number/X55SAUYBMC7J43GVAENHODVXVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN/action/storage_attestation","attest_author":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN/action/author_attestation","sign_citation":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN/action/citation_signature","submit_replication":"https://pith.science/pith/X55SAUYBMC7J43GVAENHODVXVN/action/replication_record"}},"created_at":"2026-05-18T01:21:59.534367+00:00","updated_at":"2026-05-18T01:21:59.534367+00:00"}