{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NAOVRXFM4ESOGQ4JDXCMZZAWDI","short_pith_number":"pith:NAOVRXFM","canonical_record":{"source":{"id":"2007.08709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-17T01:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"360ece59a4f659b3278ef32eac4444af8ce3ed734cbc992430341e347edba74d","abstract_canon_sha256":"9e70291ec8b8847f6ecd384b85ecf85b2807523d0183f2e2fcf1fa084387702b"},"schema_version":"1.0"},"canonical_sha256":"681d58dcace124e343891dc4cce4161a37ebd4bec44787a35b2e4ab0b93b3b5c","source":{"kind":"arxiv","id":"2007.08709","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.08709","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2007.08709v1","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08709","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"NAOVRXFM4ESO","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"NAOVRXFM4ESOGQ4J","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"NAOVRXFM","created_at":"2026-07-05T01:19:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NAOVRXFM4ESOGQ4JDXCMZZAWDI","target":"record","payload":{"canonical_record":{"source":{"id":"2007.08709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-17T01:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"360ece59a4f659b3278ef32eac4444af8ce3ed734cbc992430341e347edba74d","abstract_canon_sha256":"9e70291ec8b8847f6ecd384b85ecf85b2807523d0183f2e2fcf1fa084387702b"},"schema_version":"1.0"},"canonical_sha256":"681d58dcace124e343891dc4cce4161a37ebd4bec44787a35b2e4ab0b93b3b5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:56.469882Z","signature_b64":"StABEDtBjoBoB/mwrcH53bpk6kUvhmlh7KaYcSUJ6BWVwynxkUvsczGiDeKSiavwGc07ZpkB+pWUjNYOPvbNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681d58dcace124e343891dc4cce4161a37ebd4bec44787a35b2e4ab0b93b3b5c","last_reissued_at":"2026-07-05T01:19:56.469481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:56.469481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.08709","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":"2026-07-05T01:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s3Q7LMsp1JfgMwBqi0zpb2hhL8RuHUkoIcPAtcOnAtsVEITxYV9HTw/Jfffx1B7aMQG69vmsBAOIq2mUoE0mCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:12:10.031600Z"},"content_sha256":"b0b308b003a0fc23e9578a68b7eaa145c932d7bb65851a4a8249e1142d65ecaf","schema_version":"1.0","event_id":"sha256:b0b308b003a0fc23e9578a68b7eaa145c932d7bb65851a4a8249e1142d65ecaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NAOVRXFM4ESOGQ4JDXCMZZAWDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Methods for Calculating Term Co-Occurrence Frequencies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bodo Billerbeck, Justin Zobel, Nicholas Lester, Nick Craswell","submitted_at":"2020-07-17T01:21:40Z","abstract_excerpt":"Search techniques make use of elementary information such as term frequencies and document lengths in computation of similarity weighting. They can also exploit richer statistics, in particular the number of documents in which any two terms co-occur. In this paper we propose alternative methods for computing this statistic, a challenging task because the number of distinct pairs of terms is vast -- around 100,000 in a typical 1000-word news article, for example. In contrast, we do not employ approximation algorithms, as we want to be able to find exact counts. We explore their efficiency, find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08709","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/2007.08709/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nHbDJvog06mJNmxTgD+C5xnvvW1on2QSiWp/jMMJO60KZ9P0LW6gN3KfCabYQPbTF66sAEhlb7ivfA/GSePQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:12:10.031974Z"},"content_sha256":"9f4b31283fd8eb5dd22aaec79e78df51ad9bb026d10df2b9f9f2c0631bbff22e","schema_version":"1.0","event_id":"sha256:9f4b31283fd8eb5dd22aaec79e78df51ad9bb026d10df2b9f9f2c0631bbff22e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI/bundle.json","state_url":"https://pith.science/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI/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":"2026-07-06T08:12:10Z","links":{"resolver":"https://pith.science/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI","bundle":"https://pith.science/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI/bundle.json","state":"https://pith.science/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NAOVRXFM4ESOGQ4JDXCMZZAWDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NAOVRXFM4ESOGQ4JDXCMZZAWDI","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":"9e70291ec8b8847f6ecd384b85ecf85b2807523d0183f2e2fcf1fa084387702b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-17T01:21:40Z","title_canon_sha256":"360ece59a4f659b3278ef32eac4444af8ce3ed734cbc992430341e347edba74d"},"schema_version":"1.0","source":{"id":"2007.08709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.08709","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2007.08709v1","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08709","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"NAOVRXFM4ESO","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"NAOVRXFM4ESOGQ4J","created_at":"2026-07-05T01:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"NAOVRXFM","created_at":"2026-07-05T01:19:56Z"}],"graph_snapshots":[{"event_id":"sha256:9f4b31283fd8eb5dd22aaec79e78df51ad9bb026d10df2b9f9f2c0631bbff22e","target":"graph","created_at":"2026-07-05T01:19:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.08709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Search techniques make use of elementary information such as term frequencies and document lengths in computation of similarity weighting. They can also exploit richer statistics, in particular the number of documents in which any two terms co-occur. In this paper we propose alternative methods for computing this statistic, a challenging task because the number of distinct pairs of terms is vast -- around 100,000 in a typical 1000-word news article, for example. In contrast, we do not employ approximation algorithms, as we want to be able to find exact counts. We explore their efficiency, find","authors_text":"Bodo Billerbeck, Justin Zobel, Nicholas Lester, Nick Craswell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-17T01:21:40Z","title":"Scalable Methods for Calculating Term Co-Occurrence Frequencies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08709","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:b0b308b003a0fc23e9578a68b7eaa145c932d7bb65851a4a8249e1142d65ecaf","target":"record","created_at":"2026-07-05T01:19:56Z","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":"9e70291ec8b8847f6ecd384b85ecf85b2807523d0183f2e2fcf1fa084387702b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-07-17T01:21:40Z","title_canon_sha256":"360ece59a4f659b3278ef32eac4444af8ce3ed734cbc992430341e347edba74d"},"schema_version":"1.0","source":{"id":"2007.08709","kind":"arxiv","version":1}},"canonical_sha256":"681d58dcace124e343891dc4cce4161a37ebd4bec44787a35b2e4ab0b93b3b5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"681d58dcace124e343891dc4cce4161a37ebd4bec44787a35b2e4ab0b93b3b5c","first_computed_at":"2026-07-05T01:19:56.469481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:19:56.469481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"StABEDtBjoBoB/mwrcH53bpk6kUvhmlh7KaYcSUJ6BWVwynxkUvsczGiDeKSiavwGc07ZpkB+pWUjNYOPvbNDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:19:56.469882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.08709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0b308b003a0fc23e9578a68b7eaa145c932d7bb65851a4a8249e1142d65ecaf","sha256:9f4b31283fd8eb5dd22aaec79e78df51ad9bb026d10df2b9f9f2c0631bbff22e"],"state_sha256":"1a4aebd1698de089c0894ae850cd6caa57a364800e5b774ea1840698030dcde2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtGznbybpiQXU322pW/X/gkNmTP46yl9YsR1rSpl9bC9WYHfBkQBFSq+1vA0LqUPQIMQJpoopO2kYGYORIhNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:12:10.033910Z","bundle_sha256":"95d1a3eca3407a8135da0195062a7e09e5cda2574ec3e30f3451c7a73761e639"}}