{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:X55SAUYBMC7J43GVAENHODVXVN","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":"3b48d89c7f15905f66f2bafb8627dc083501ebee2892a7a7f45599ea432e078a","cross_cats_sorted":["cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-01-26T08:22:37Z","title_canon_sha256":"400353677725c7f0ed7a0196a82f88831399b6cb30672d5d82930281d6d4cc11"},"schema_version":"1.0","source":{"id":"1601.06919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.06919","created_at":"2026-05-18T01:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"1601.06919v1","created_at":"2026-05-18T01:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.06919","created_at":"2026-05-18T01:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"X55SAUYBMC7J","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X55SAUYBMC7J43GV","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X55SAUYB","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:158ed5b7d593f1b697e6f8128ea1a2187680af77a81d4c124214e136c76d8582","target":"graph","created_at":"2026-05-18T01:21:59Z","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"},"paper":{"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","authors_text":"Andrea Marino, Massimo Santini, Paolo Boldi, Sebastiano Vigna","cross_cats":["cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-01-26T08:22:37Z","title":"BUbiNG: Massive Crawling for the Masses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.06919","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":"sha256:1cc630f758306302359bcc29b3badd0f29f3fe054480b5f27afb3487138c39d2","target":"record","created_at":"2026-05-18T01:21:59Z","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":"3b48d89c7f15905f66f2bafb8627dc083501ebee2892a7a7f45599ea432e078a","cross_cats_sorted":["cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-01-26T08:22:37Z","title_canon_sha256":"400353677725c7f0ed7a0196a82f88831399b6cb30672d5d82930281d6d4cc11"},"schema_version":"1.0","source":{"id":"1601.06919","kind":"arxiv","version":1}},"canonical_sha256":"bf7b20530160be9e6cd5011a770eb7ab4b2ba3c8d262b7840bdf2c9e711c15e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf7b20530160be9e6cd5011a770eb7ab4b2ba3c8d262b7840bdf2c9e711c15e3","first_computed_at":"2026-05-18T01:21:59.534273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:21:59.534273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WNWKPtcLONtFbVi+3+EmEzAEr66PBZ0HxSHc4dgrsGC20klFurt2mSLcJV+wxQ8FiZgw3iR28bjbdZSxQwA5Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:21:59.534873Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.06919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cc630f758306302359bcc29b3badd0f29f3fe054480b5f27afb3487138c39d2","sha256:158ed5b7d593f1b697e6f8128ea1a2187680af77a81d4c124214e136c76d8582"],"state_sha256":"9fdbe0409ef4fc29c5d70755ff1ac42bca000d0565e259355776f75246c57e81"}