{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:CW7NCLNJFMVSPLLQZI46KBHU5P","short_pith_number":"pith:CW7NCLNJ","canonical_record":{"source":{"id":"1207.4371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-18T13:21:10Z","cross_cats_sorted":["cs.DB","cs.DC"],"title_canon_sha256":"b7224f700f743d9a00671d700e560b164ecc9a2f2dd1c4e0b1ee767b6febaf1a","abstract_canon_sha256":"d5ef7e957e9dfb3cca2f1a0697c58d5730b443b8268ffe6b2ab673ec54a0804a"},"schema_version":"1.0"},"canonical_sha256":"15bed12da92b2b27ad70ca39e504f4ebd98b8ea06c9145b0c836e6167c281240","source":{"kind":"arxiv","id":"1207.4371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4371","created_at":"2026-05-18T03:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4371v1","created_at":"2026-05-18T03:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4371","created_at":"2026-05-18T03:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"CW7NCLNJFMVS","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"CW7NCLNJFMVSPLLQ","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"CW7NCLNJ","created_at":"2026-05-18T12:27:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:CW7NCLNJFMVSPLLQZI46KBHU5P","target":"record","payload":{"canonical_record":{"source":{"id":"1207.4371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-18T13:21:10Z","cross_cats_sorted":["cs.DB","cs.DC"],"title_canon_sha256":"b7224f700f743d9a00671d700e560b164ecc9a2f2dd1c4e0b1ee767b6febaf1a","abstract_canon_sha256":"d5ef7e957e9dfb3cca2f1a0697c58d5730b443b8268ffe6b2ab673ec54a0804a"},"schema_version":"1.0"},"canonical_sha256":"15bed12da92b2b27ad70ca39e504f4ebd98b8ea06c9145b0c836e6167c281240","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:46.892884Z","signature_b64":"Fv9L95XGe2eM1ED3Zhteclshhv+39K9FdT6UGacUCpZ88bLWneHzMI5KlZUeA5NdhdunQmAPU2uIXgF5u0t9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15bed12da92b2b27ad70ca39e504f4ebd98b8ea06c9145b0c836e6167c281240","last_reissued_at":"2026-05-18T03:50:46.892220Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:46.892220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1207.4371","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":"2026-05-18T03:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVxgZ6Z02nLsHNgaCJiv32onDs33ljcI7nbdZx6SbGy4YZvgknlUkPvSk8UfAX5P0HGhnNiizjiHBeNbx6YkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:30:57.484018Z"},"content_sha256":"a0b23aaf49d71a7208ccc2fb54eb5238de771d9a7bf2bc489606118026067ccc","schema_version":"1.0","event_id":"sha256:a0b23aaf49d71a7208ccc2fb54eb5238de771d9a7bf2bc489606118026067ccc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:CW7NCLNJFMVSPLLQZI46KBHU5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Computing n-Gram Statistics in MapReduce","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.DC"],"primary_cat":"cs.IR","authors_text":"Klaus Berberich, Srikanta Bedathur","submitted_at":"2012-07-18T13:21:10Z","abstract_excerpt":"Statistics about n-grams (i.e., sequences of contiguous words or other tokens in text documents or other string data) are an important building block in information retrieval and natural language processing. In this work, we study how n-gram statistics, optionally restricted by a maximum n-gram length and minimum collection frequency, can be computed efficiently harnessing MapReduce for distributed data processing. We describe different algorithms, ranging from an extension of word counting, via methods based on the Apriori principle, to a novel method Suffix-\\sigma that relies on sorting and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4371","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bp6HGJzXpyecgi+Zk9HQHosA01b5F7WLHNzN4R1qOBsE3ca1lXN+7WDgZpWFA8J5JNFS1BUu7W9rDVergCfbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T21:30:57.484660Z"},"content_sha256":"6695814f0ea3b251038499044565b401601cdf5897a160e4846a88788b1d78c1","schema_version":"1.0","event_id":"sha256:6695814f0ea3b251038499044565b401601cdf5897a160e4846a88788b1d78c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CW7NCLNJFMVSPLLQZI46KBHU5P/bundle.json","state_url":"https://pith.science/pith/CW7NCLNJFMVSPLLQZI46KBHU5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CW7NCLNJFMVSPLLQZI46KBHU5P/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":"2026-05-30T21:30:57Z","links":{"resolver":"https://pith.science/pith/CW7NCLNJFMVSPLLQZI46KBHU5P","bundle":"https://pith.science/pith/CW7NCLNJFMVSPLLQZI46KBHU5P/bundle.json","state":"https://pith.science/pith/CW7NCLNJFMVSPLLQZI46KBHU5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CW7NCLNJFMVSPLLQZI46KBHU5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:CW7NCLNJFMVSPLLQZI46KBHU5P","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":"d5ef7e957e9dfb3cca2f1a0697c58d5730b443b8268ffe6b2ab673ec54a0804a","cross_cats_sorted":["cs.DB","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-18T13:21:10Z","title_canon_sha256":"b7224f700f743d9a00671d700e560b164ecc9a2f2dd1c4e0b1ee767b6febaf1a"},"schema_version":"1.0","source":{"id":"1207.4371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1207.4371","created_at":"2026-05-18T03:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"1207.4371v1","created_at":"2026-05-18T03:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4371","created_at":"2026-05-18T03:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"CW7NCLNJFMVS","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"CW7NCLNJFMVSPLLQ","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"CW7NCLNJ","created_at":"2026-05-18T12:27:01Z"}],"graph_snapshots":[{"event_id":"sha256:6695814f0ea3b251038499044565b401601cdf5897a160e4846a88788b1d78c1","target":"graph","created_at":"2026-05-18T03:50:46Z","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":"Statistics about n-grams (i.e., sequences of contiguous words or other tokens in text documents or other string data) are an important building block in information retrieval and natural language processing. In this work, we study how n-gram statistics, optionally restricted by a maximum n-gram length and minimum collection frequency, can be computed efficiently harnessing MapReduce for distributed data processing. We describe different algorithms, ranging from an extension of word counting, via methods based on the Apriori principle, to a novel method Suffix-\\sigma that relies on sorting and ","authors_text":"Klaus Berberich, Srikanta Bedathur","cross_cats":["cs.DB","cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-18T13:21:10Z","title":"Computing n-Gram Statistics in MapReduce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4371","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:a0b23aaf49d71a7208ccc2fb54eb5238de771d9a7bf2bc489606118026067ccc","target":"record","created_at":"2026-05-18T03:50:46Z","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":"d5ef7e957e9dfb3cca2f1a0697c58d5730b443b8268ffe6b2ab673ec54a0804a","cross_cats_sorted":["cs.DB","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-07-18T13:21:10Z","title_canon_sha256":"b7224f700f743d9a00671d700e560b164ecc9a2f2dd1c4e0b1ee767b6febaf1a"},"schema_version":"1.0","source":{"id":"1207.4371","kind":"arxiv","version":1}},"canonical_sha256":"15bed12da92b2b27ad70ca39e504f4ebd98b8ea06c9145b0c836e6167c281240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15bed12da92b2b27ad70ca39e504f4ebd98b8ea06c9145b0c836e6167c281240","first_computed_at":"2026-05-18T03:50:46.892220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:50:46.892220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fv9L95XGe2eM1ED3Zhteclshhv+39K9FdT6UGacUCpZ88bLWneHzMI5KlZUeA5NdhdunQmAPU2uIXgF5u0t9CA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:50:46.892884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1207.4371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0b23aaf49d71a7208ccc2fb54eb5238de771d9a7bf2bc489606118026067ccc","sha256:6695814f0ea3b251038499044565b401601cdf5897a160e4846a88788b1d78c1"],"state_sha256":"d5d11a5386ca11f488af375be513172ad56948796aba2bce5ee5e94ab8fc5c28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5KI44z5xarztoH9mai3eY6PUwVvll90S4zOWTyVySbzYWrjEx/u2p+ABa0goXWaiXG/D22a1KfFjFuqvwV7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T21:30:57.489332Z","bundle_sha256":"2dc782dbe41bba6a05e542a52e9b01f6b96e6f172229edcf9f2f575bbe7f0759"}}