{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MAZQJ2WILDWMSBFZOTXEWVLKVN","short_pith_number":"pith:MAZQJ2WI","canonical_record":{"source":{"id":"2007.00655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-29T06:09:59Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"724a50cc47c92b0baf2ed81e17ae9ea72ad4b765b47fefe76462cd65b6f547c8","abstract_canon_sha256":"43012e67bb7b54ebc8e70749b1074eaab0c674a93e829c51e83b0b2372b12e5b"},"schema_version":"1.0"},"canonical_sha256":"603304eac858ecc904b974ee4b556aab784b0feb49b2bfb3d5415f0b59046238","source":{"kind":"arxiv","id":"2007.00655","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00655","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00655v2","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00655","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"MAZQJ2WILDWM","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"MAZQJ2WILDWMSBFZ","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"MAZQJ2WI","created_at":"2026-07-05T02:12:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MAZQJ2WILDWMSBFZOTXEWVLKVN","target":"record","payload":{"canonical_record":{"source":{"id":"2007.00655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-29T06:09:59Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"724a50cc47c92b0baf2ed81e17ae9ea72ad4b765b47fefe76462cd65b6f547c8","abstract_canon_sha256":"43012e67bb7b54ebc8e70749b1074eaab0c674a93e829c51e83b0b2372b12e5b"},"schema_version":"1.0"},"canonical_sha256":"603304eac858ecc904b974ee4b556aab784b0feb49b2bfb3d5415f0b59046238","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:41.902600Z","signature_b64":"3uxxowNN0fy+xHwsgzxGmUCpSrTaSSt0zncbkNkq6Ath6tFpS+2QvxYMc7oTsw1+pSmOj37dbkzPJ+egRKz0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"603304eac858ecc904b974ee4b556aab784b0feb49b2bfb3d5415f0b59046238","last_reissued_at":"2026-07-05T02:12:41.902064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:41.902064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.00655","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":"2026-07-05T02:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSx8qCcmdC+6QmR333V2Yoz0FfIzhsFY48Y+lw/LJIHnQ+5QhHMKzd52aoy8ZI8SnXngFlif+iEklT7Kopm9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:52.902986Z"},"content_sha256":"0e7bbc4b7d2a90b1d7c7186b8146985dd8fa91f17d9370a41088078aa19fcf69","schema_version":"1.0","event_id":"sha256:0e7bbc4b7d2a90b1d7c7186b8146985dd8fa91f17d9370a41088078aa19fcf69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MAZQJ2WILDWMSBFZOTXEWVLKVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge-Aware Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Chenyan Xiong, Corby Rosset, Minh Phan, Paul Bennett, Saurabh Tiwary, Xia Song","submitted_at":"2020-06-29T06:09:59Z","abstract_excerpt":"How much knowledge do pretrained language models hold? Recent research observed that pretrained transformers are adept at modeling semantics but it is unclear to what degree they grasp human knowledge, or how to ensure they do so. In this paper we incorporate knowledge-awareness in language model pretraining without changing the transformer architecture, inserting explicit knowledge layers, or adding external storage of semantic information. Rather, we simply signal the existence of entities to the input of the transformer in pretraining, with an entity-extended tokenizer; and at the output, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00655","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/2007.00655/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":"2026-07-05T02:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqa5m0BJdfTsNphzy0T1emTRpMf1jS8A0W+1EFTwgUrAIT0Bqh/tUiTG9CKAXtlLT/LhlCFg4XHuofveM9J9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:52.903518Z"},"content_sha256":"102861b632211667a5064629561aa438c7207130baff09f7cdb39f78fdb8c130","schema_version":"1.0","event_id":"sha256:102861b632211667a5064629561aa438c7207130baff09f7cdb39f78fdb8c130"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN/bundle.json","state_url":"https://pith.science/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN/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":"2026-08-04T19:05:52Z","links":{"resolver":"https://pith.science/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN","bundle":"https://pith.science/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN/bundle.json","state":"https://pith.science/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAZQJ2WILDWMSBFZOTXEWVLKVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MAZQJ2WILDWMSBFZOTXEWVLKVN","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":"43012e67bb7b54ebc8e70749b1074eaab0c674a93e829c51e83b0b2372b12e5b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-29T06:09:59Z","title_canon_sha256":"724a50cc47c92b0baf2ed81e17ae9ea72ad4b765b47fefe76462cd65b6f547c8"},"schema_version":"1.0","source":{"id":"2007.00655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00655","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00655v2","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00655","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"MAZQJ2WILDWM","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"MAZQJ2WILDWMSBFZ","created_at":"2026-07-05T02:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"MAZQJ2WI","created_at":"2026-07-05T02:12:41Z"}],"graph_snapshots":[{"event_id":"sha256:102861b632211667a5064629561aa438c7207130baff09f7cdb39f78fdb8c130","target":"graph","created_at":"2026-07-05T02:12:41Z","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/2007.00655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How much knowledge do pretrained language models hold? Recent research observed that pretrained transformers are adept at modeling semantics but it is unclear to what degree they grasp human knowledge, or how to ensure they do so. In this paper we incorporate knowledge-awareness in language model pretraining without changing the transformer architecture, inserting explicit knowledge layers, or adding external storage of semantic information. Rather, we simply signal the existence of entities to the input of the transformer in pretraining, with an entity-extended tokenizer; and at the output, w","authors_text":"Chenyan Xiong, Corby Rosset, Minh Phan, Paul Bennett, Saurabh Tiwary, Xia Song","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-29T06:09:59Z","title":"Knowledge-Aware Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00655","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":"sha256:0e7bbc4b7d2a90b1d7c7186b8146985dd8fa91f17d9370a41088078aa19fcf69","target":"record","created_at":"2026-07-05T02:12:41Z","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":"43012e67bb7b54ebc8e70749b1074eaab0c674a93e829c51e83b0b2372b12e5b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-29T06:09:59Z","title_canon_sha256":"724a50cc47c92b0baf2ed81e17ae9ea72ad4b765b47fefe76462cd65b6f547c8"},"schema_version":"1.0","source":{"id":"2007.00655","kind":"arxiv","version":2}},"canonical_sha256":"603304eac858ecc904b974ee4b556aab784b0feb49b2bfb3d5415f0b59046238","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"603304eac858ecc904b974ee4b556aab784b0feb49b2bfb3d5415f0b59046238","first_computed_at":"2026-07-05T02:12:41.902064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:41.902064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3uxxowNN0fy+xHwsgzxGmUCpSrTaSSt0zncbkNkq6Ath6tFpS+2QvxYMc7oTsw1+pSmOj37dbkzPJ+egRKz0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:41.902600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e7bbc4b7d2a90b1d7c7186b8146985dd8fa91f17d9370a41088078aa19fcf69","sha256:102861b632211667a5064629561aa438c7207130baff09f7cdb39f78fdb8c130"],"state_sha256":"dcb4d24ec5079c776736fbb5adab915f6a87e1eede07eddc1ffc84b6e2fb5247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xC0iWM1cf4h/n7eKuefnxXRDDb2VGvzJ5gm8jL7xJwPAAE/9qiOJY5WMy6ar4hiLA3nntZe/6PD93m4JmPPYDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:05:52.907283Z","bundle_sha256":"8e551e2570a6af5d69f342ba8cf2db667ded735b8492ef0e45ccabc7d1a24945"}}