{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JA5WCLCOQXHV6S4ZRLCUO7KNG2","short_pith_number":"pith:JA5WCLCO","canonical_record":{"source":{"id":"2112.09924","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-18T13:15:34Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"85e3beb15f5b981c01d53e51a7eec4fb6c04e11e3526abf95b971aa269c4fd66","abstract_canon_sha256":"0ebaee9595b1379006133c8a3226b051421097c3be6fc1d648ec31a3c131dd30"},"schema_version":"1.0"},"canonical_sha256":"483b612c4e85cf5f4b998ac5477d4d36a2bbbc6953ac2e610fbb0376592f7a2c","source":{"kind":"arxiv","id":"2112.09924","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.09924","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2112.09924v2","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09924","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"JA5WCLCOQXHV","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"JA5WCLCOQXHV6S4Z","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"JA5WCLCO","created_at":"2026-07-05T04:26:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JA5WCLCOQXHV6S4ZRLCUO7KNG2","target":"record","payload":{"canonical_record":{"source":{"id":"2112.09924","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-18T13:15:34Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"85e3beb15f5b981c01d53e51a7eec4fb6c04e11e3526abf95b971aa269c4fd66","abstract_canon_sha256":"0ebaee9595b1379006133c8a3226b051421097c3be6fc1d648ec31a3c131dd30"},"schema_version":"1.0"},"canonical_sha256":"483b612c4e85cf5f4b998ac5477d4d36a2bbbc6953ac2e610fbb0376592f7a2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:21.592878Z","signature_b64":"YuFnCyS/SdPoQ/aFtOhEjDO//HYiJJdc568A1mfvua7j6hGAkUdJRnoeztJN9oHAXPWpWu3otSVXvkosXRDBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"483b612c4e85cf5f4b998ac5477d4d36a2bbbc6953ac2e610fbb0376592f7a2c","last_reissued_at":"2026-07-05T04:26:21.592478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:21.592478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.09924","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/caXNIi8OBcWTNFSAaHwwTsVkX1ERxFTQU1QB201auRSu4etiKX/ZVKjLYTPZndD1frO9HWyt/2r3i7+FXQkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:59:48.541030Z"},"content_sha256":"460025828ab08dc375f8a0e113385b053cc4e08c61ce4a131b669697f68ce5db","schema_version":"1.0","event_id":"sha256:460025828ab08dc375f8a0e113385b053cc4e08c61ce4a131b669697f68ce5db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JA5WCLCOQXHV6S4ZRLCUO7KNG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandra Piktus, Barlas O\\u{g}uz, Dmytro Okhonko, Edouard Grave, Fabio Petroni, Gautier Izacard, Patrick Lewis, Samuel Broscheit, Sebastian Riedel, Vladimir Karpukhin, Wen-tau Yih","submitted_at":"2021-12-18T13:15:34Z","abstract_excerpt":"In order to address increasing demands of real-world applications, the research for knowledge-intensive NLP (KI-NLP) should advance by capturing the challenges of a truly open-domain environment: web-scale knowledge, lack of structure, inconsistent quality and noise. To this end, we propose a new setup for evaluating existing knowledge intensive tasks in which we generalize the background corpus to a universal web snapshot. We investigate a slate of NLP tasks which rely on knowledge - either factual or common sense, and ask systems to use a subset of CCNet - the Sphere corpus - as a knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09924","kind":"arxiv","version":2},"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/2112.09924/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":"2026-07-05T04:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dXIiSP/zEr5WZiYCxihUO2UbwT7q7WD1oeqjwcmNAm6MfpbNOYVdxUuTn+wCHYZy99jmfQOHf0dqMeqxSZ4YBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:59:48.541547Z"},"content_sha256":"db1218fc6763d075a0894472f38ca9a0e70f67f36febd1f48cd6966b125e92fd","schema_version":"1.0","event_id":"sha256:db1218fc6763d075a0894472f38ca9a0e70f67f36febd1f48cd6966b125e92fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2/bundle.json","state_url":"https://pith.science/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2/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":"2026-08-10T10:59:48Z","links":{"resolver":"https://pith.science/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2","bundle":"https://pith.science/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2/bundle.json","state":"https://pith.science/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JA5WCLCOQXHV6S4ZRLCUO7KNG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JA5WCLCOQXHV6S4ZRLCUO7KNG2","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":"0ebaee9595b1379006133c8a3226b051421097c3be6fc1d648ec31a3c131dd30","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-18T13:15:34Z","title_canon_sha256":"85e3beb15f5b981c01d53e51a7eec4fb6c04e11e3526abf95b971aa269c4fd66"},"schema_version":"1.0","source":{"id":"2112.09924","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.09924","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"2112.09924v2","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09924","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"JA5WCLCOQXHV","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"pith_short_16","alias_value":"JA5WCLCOQXHV6S4Z","created_at":"2026-07-05T04:26:21Z"},{"alias_kind":"pith_short_8","alias_value":"JA5WCLCO","created_at":"2026-07-05T04:26:21Z"}],"graph_snapshots":[{"event_id":"sha256:db1218fc6763d075a0894472f38ca9a0e70f67f36febd1f48cd6966b125e92fd","target":"graph","created_at":"2026-07-05T04:26:21Z","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/2112.09924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order to address increasing demands of real-world applications, the research for knowledge-intensive NLP (KI-NLP) should advance by capturing the challenges of a truly open-domain environment: web-scale knowledge, lack of structure, inconsistent quality and noise. To this end, we propose a new setup for evaluating existing knowledge intensive tasks in which we generalize the background corpus to a universal web snapshot. We investigate a slate of NLP tasks which rely on knowledge - either factual or common sense, and ask systems to use a subset of CCNet - the Sphere corpus - as a knowledge ","authors_text":"Aleksandra Piktus, Barlas O\\u{g}uz, Dmytro Okhonko, Edouard Grave, Fabio Petroni, Gautier Izacard, Patrick Lewis, Samuel Broscheit, Sebastian Riedel, Vladimir Karpukhin, Wen-tau Yih","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-18T13:15:34Z","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09924","kind":"arxiv","version":2},"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":"sha256:460025828ab08dc375f8a0e113385b053cc4e08c61ce4a131b669697f68ce5db","target":"record","created_at":"2026-07-05T04:26:21Z","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":"0ebaee9595b1379006133c8a3226b051421097c3be6fc1d648ec31a3c131dd30","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-18T13:15:34Z","title_canon_sha256":"85e3beb15f5b981c01d53e51a7eec4fb6c04e11e3526abf95b971aa269c4fd66"},"schema_version":"1.0","source":{"id":"2112.09924","kind":"arxiv","version":2}},"canonical_sha256":"483b612c4e85cf5f4b998ac5477d4d36a2bbbc6953ac2e610fbb0376592f7a2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"483b612c4e85cf5f4b998ac5477d4d36a2bbbc6953ac2e610fbb0376592f7a2c","first_computed_at":"2026-07-05T04:26:21.592478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:21.592478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YuFnCyS/SdPoQ/aFtOhEjDO//HYiJJdc568A1mfvua7j6hGAkUdJRnoeztJN9oHAXPWpWu3otSVXvkosXRDBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:21.592878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.09924","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:460025828ab08dc375f8a0e113385b053cc4e08c61ce4a131b669697f68ce5db","sha256:db1218fc6763d075a0894472f38ca9a0e70f67f36febd1f48cd6966b125e92fd"],"state_sha256":"364a421852da6570bc489aa8f66e1c8f015e47c11c2b760a98b4a6f4c5b798eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtme1jShp9V4Wk1TYEKRdnfpTT/eQBDPEfdzLAXxux7L7zj8WTSEcXdv0C6fOYdigAEXmX8C20U4DZAPnTBNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:59:48.547542Z","bundle_sha256":"93874ae8b339da6d766ba52fcdcb0e13ef126df18cf89cadafa7fa67b8699f08"}}