{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:N5WT6ON3HVMWRX4GCGEWD56NEB","short_pith_number":"pith:N5WT6ON3","canonical_record":{"source":{"id":"2312.10661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-17T09:31:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f007abee2ad4de2f377d7e7fa90c5b4f54c2b5871c58a6b4f6c9bd65c3b9b2f6","abstract_canon_sha256":"0d4d91586db9374526b685e5d0c136ccddef1b938499b7d35520867e023b8c5d"},"schema_version":"1.0"},"canonical_sha256":"6f6d3f39bb3d5968df86118961f7cd20660c192b329988679f5500ed49a7b01a","source":{"kind":"arxiv","id":"2312.10661","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10661","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10661v2","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10661","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"pith_short_12","alias_value":"N5WT6ON3HVMW","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"pith_short_16","alias_value":"N5WT6ON3HVMWRX4G","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"pith_short_8","alias_value":"N5WT6ON3","created_at":"2026-07-05T07:29:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:N5WT6ON3HVMWRX4GCGEWD56NEB","target":"record","payload":{"canonical_record":{"source":{"id":"2312.10661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-17T09:31:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f007abee2ad4de2f377d7e7fa90c5b4f54c2b5871c58a6b4f6c9bd65c3b9b2f6","abstract_canon_sha256":"0d4d91586db9374526b685e5d0c136ccddef1b938499b7d35520867e023b8c5d"},"schema_version":"1.0"},"canonical_sha256":"6f6d3f39bb3d5968df86118961f7cd20660c192b329988679f5500ed49a7b01a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:13.867912Z","signature_b64":"KrIPMJysmsH5gTIZV2MWiIIk23eeXEFlRbLVZHFbce7XLDUWUZOq7yXXEnXu4uhCPDRmxldHSSQ3eisXImyaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f6d3f39bb3d5968df86118961f7cd20660c192b329988679f5500ed49a7b01a","last_reissued_at":"2026-07-05T07:29:13.867386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:13.867386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.10661","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":"2026-07-05T07:29:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7mMk/Zg8QPZUKn/VrtUIaZ3H0yFtnRSnzgqdY+86LpfrhAgotSL7qIQLD/WlmS5RM1Bv2bp8K9Cz61rnlrbtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:39:05.731686Z"},"content_sha256":"de940f6606b08e2430092178cd210ee6e6fe8d487b67ca0f375fb397b0e3791f","schema_version":"1.0","event_id":"sha256:de940f6606b08e2430092178cd210ee6e6fe8d487b67ca0f375fb397b0e3791f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:N5WT6ON3HVMWRX4GCGEWD56NEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jia Chen, Qingyao Ai, Shengluan Hou, Weihang Su, Xiangsheng Li, Xiaolong Wu, Yiqun Liu","submitted_at":"2023-12-17T09:31:47Z","abstract_excerpt":"With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems. Benefiting from the pre-training and fine-tuning paradigm, these models achieve state-of-the-art performance. In previous works, plain texts in Wikipedia have been widely used in the pre-training stage. However, the rich structured information in Wikipedia, such as the titles, abstracts, hierarchical heading (multi-level title) structure, relationship between articles, references, hyperlink structures, and the writing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10661","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/2312.10661/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":"2026-07-05T07:29:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wL7vMTCjKDA8wWj8NvqxPrF7r9fZ+LBG/UVYQqU0ojDhku2FA4gwE1vbp3Dw4BQZrSUSiVtQ9S5vD1FVqNyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T08:39:05.732161Z"},"content_sha256":"249d88d90ad3ddc16cacbc8b9de010ef07aa2b0440f25952f3e3a9d6e12a4e9f","schema_version":"1.0","event_id":"sha256:249d88d90ad3ddc16cacbc8b9de010ef07aa2b0440f25952f3e3a9d6e12a4e9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5WT6ON3HVMWRX4GCGEWD56NEB/bundle.json","state_url":"https://pith.science/pith/N5WT6ON3HVMWRX4GCGEWD56NEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5WT6ON3HVMWRX4GCGEWD56NEB/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":"2026-08-15T08:39:05Z","links":{"resolver":"https://pith.science/pith/N5WT6ON3HVMWRX4GCGEWD56NEB","bundle":"https://pith.science/pith/N5WT6ON3HVMWRX4GCGEWD56NEB/bundle.json","state":"https://pith.science/pith/N5WT6ON3HVMWRX4GCGEWD56NEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5WT6ON3HVMWRX4GCGEWD56NEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:N5WT6ON3HVMWRX4GCGEWD56NEB","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":"0d4d91586db9374526b685e5d0c136ccddef1b938499b7d35520867e023b8c5d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-17T09:31:47Z","title_canon_sha256":"f007abee2ad4de2f377d7e7fa90c5b4f54c2b5871c58a6b4f6c9bd65c3b9b2f6"},"schema_version":"1.0","source":{"id":"2312.10661","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10661","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10661v2","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10661","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"pith_short_12","alias_value":"N5WT6ON3HVMW","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"pith_short_16","alias_value":"N5WT6ON3HVMWRX4G","created_at":"2026-07-05T07:29:13Z"},{"alias_kind":"pith_short_8","alias_value":"N5WT6ON3","created_at":"2026-07-05T07:29:13Z"}],"graph_snapshots":[{"event_id":"sha256:249d88d90ad3ddc16cacbc8b9de010ef07aa2b0440f25952f3e3a9d6e12a4e9f","target":"graph","created_at":"2026-07-05T07:29:13Z","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/2312.10661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems. Benefiting from the pre-training and fine-tuning paradigm, these models achieve state-of-the-art performance. In previous works, plain texts in Wikipedia have been widely used in the pre-training stage. However, the rich structured information in Wikipedia, such as the titles, abstracts, hierarchical heading (multi-level title) structure, relationship between articles, references, hyperlink structures, and the writing ","authors_text":"Jia Chen, Qingyao Ai, Shengluan Hou, Weihang Su, Xiangsheng Li, Xiaolong Wu, Yiqun Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-17T09:31:47Z","title":"Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10661","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:de940f6606b08e2430092178cd210ee6e6fe8d487b67ca0f375fb397b0e3791f","target":"record","created_at":"2026-07-05T07:29:13Z","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":"0d4d91586db9374526b685e5d0c136ccddef1b938499b7d35520867e023b8c5d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-17T09:31:47Z","title_canon_sha256":"f007abee2ad4de2f377d7e7fa90c5b4f54c2b5871c58a6b4f6c9bd65c3b9b2f6"},"schema_version":"1.0","source":{"id":"2312.10661","kind":"arxiv","version":2}},"canonical_sha256":"6f6d3f39bb3d5968df86118961f7cd20660c192b329988679f5500ed49a7b01a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f6d3f39bb3d5968df86118961f7cd20660c192b329988679f5500ed49a7b01a","first_computed_at":"2026-07-05T07:29:13.867386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:13.867386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KrIPMJysmsH5gTIZV2MWiIIk23eeXEFlRbLVZHFbce7XLDUWUZOq7yXXEnXu4uhCPDRmxldHSSQ3eisXImyaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:13.867912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10661","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de940f6606b08e2430092178cd210ee6e6fe8d487b67ca0f375fb397b0e3791f","sha256:249d88d90ad3ddc16cacbc8b9de010ef07aa2b0440f25952f3e3a9d6e12a4e9f"],"state_sha256":"722cc68a606722a82f4af912e9fbb4acd549d8ea9d6b9a5739aceedec562d775"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pimye6pQBqhtBK77G2E7SP4xkh10dUd9/f2OwIX5EaeyXVYkb3BnnPirLAf80SeSe57qMObLQYDp9oC/1ogADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T08:39:05.735977Z","bundle_sha256":"4073eccd1cdd30756a03481d262e7c9d32d51a04f73cdaf410596c0adb48a393"}}