{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A6QY2DI53WLM6RWJYNUYSOXNPN","short_pith_number":"pith:A6QY2DI5","canonical_record":{"source":{"id":"2209.06583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-14T12:03:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"aeffde39dbc0585f25119d6a9a73bc0549a6d6ce72aabead16fdb4ef6a3c4da3","abstract_canon_sha256":"a35b45f39f1e3c28aa171292d9eca8f97d41b608d78220945a7576093de909eb"},"schema_version":"1.0"},"canonical_sha256":"07a18d0d1ddd96cf46c9c369893aed7b5b1b8d2b0e3392334cfb74f99887a4a5","source":{"kind":"arxiv","id":"2209.06583","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06583","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06583v1","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06583","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"A6QY2DI53WLM","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"A6QY2DI53WLM6RWJ","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"A6QY2DI5","created_at":"2026-07-05T04:57:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A6QY2DI53WLM6RWJYNUYSOXNPN","target":"record","payload":{"canonical_record":{"source":{"id":"2209.06583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-14T12:03:31Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"aeffde39dbc0585f25119d6a9a73bc0549a6d6ce72aabead16fdb4ef6a3c4da3","abstract_canon_sha256":"a35b45f39f1e3c28aa171292d9eca8f97d41b608d78220945a7576093de909eb"},"schema_version":"1.0"},"canonical_sha256":"07a18d0d1ddd96cf46c9c369893aed7b5b1b8d2b0e3392334cfb74f99887a4a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:32.464646Z","signature_b64":"I/nqB5U6M+7+vrsOrYEjVFa0aAL3ZioW1uiqyAgmt3o3v1bxf+MU0mcR18Qa67OR2IDAFsN0OGqQsD/yV2S8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a18d0d1ddd96cf46c9c369893aed7b5b1b8d2b0e3392334cfb74f99887a4a5","last_reissued_at":"2026-07-05T04:57:32.464212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:32.464212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.06583","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":"2026-07-05T04:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lf64M0TaU/NcELX181LJEEBr2UZjmnOuFLjeizcPAWZnPE2KY2DIjGM61kEDGWNiH6jAkN4rnKV7iE9c/XkqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:32.376032Z"},"content_sha256":"58349d1cb22ce1853f66e2ad383f35272abd98efa0f15f8cb2b6b8603a2e3713","schema_version":"1.0","event_id":"sha256:58349d1cb22ce1853f66e2ad383f35272abd98efa0f15f8cb2b6b8603a2e3713"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A6QY2DI53WLM6RWJYNUYSOXNPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jiawen Wu, Ruofei Lai, Xinyu Zhang, Yongkang Wu, Yutao Zhu, Zhao Cao, Zhaoye Fei, Zheng Liu, Zhicheng Dou, Zikai Guo","submitted_at":"2022-09-14T12:03:31Z","abstract_excerpt":"Recent years have witnessed great progress on applying pre-trained language models, e.g., BERT, to information retrieval (IR) tasks. Hyperlinks, which are commonly used in Web pages, have been leveraged for designing pre-training objectives. For example, anchor texts of the hyperlinks have been used for simulating queries, thus constructing tremendous query-document pairs for pre-training. However, as a bridge across two web pages, the potential of hyperlinks has not been fully explored. In this work, we focus on modeling the relationship between two documents that are connected by hyperlinks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06583","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/2209.06583/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":"2026-07-05T04:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FTzghoOMdTbI3WIgytM1w9dosbvDulCUSeIx/VZcDYg+BVlsVG+sJDaHUCRRiPhBMwmBIHrZnpL5mmvF+lBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:32.376411Z"},"content_sha256":"5306b25e43c446fda438bf5b391fc44605feb0a0d422a46b8c5987e42c188f6e","schema_version":"1.0","event_id":"sha256:5306b25e43c446fda438bf5b391fc44605feb0a0d422a46b8c5987e42c188f6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6QY2DI53WLM6RWJYNUYSOXNPN/bundle.json","state_url":"https://pith.science/pith/A6QY2DI53WLM6RWJYNUYSOXNPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6QY2DI53WLM6RWJYNUYSOXNPN/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":"2026-07-07T08:43:32Z","links":{"resolver":"https://pith.science/pith/A6QY2DI53WLM6RWJYNUYSOXNPN","bundle":"https://pith.science/pith/A6QY2DI53WLM6RWJYNUYSOXNPN/bundle.json","state":"https://pith.science/pith/A6QY2DI53WLM6RWJYNUYSOXNPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6QY2DI53WLM6RWJYNUYSOXNPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A6QY2DI53WLM6RWJYNUYSOXNPN","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":"a35b45f39f1e3c28aa171292d9eca8f97d41b608d78220945a7576093de909eb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-14T12:03:31Z","title_canon_sha256":"aeffde39dbc0585f25119d6a9a73bc0549a6d6ce72aabead16fdb4ef6a3c4da3"},"schema_version":"1.0","source":{"id":"2209.06583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06583","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06583v1","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06583","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"A6QY2DI53WLM","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"A6QY2DI53WLM6RWJ","created_at":"2026-07-05T04:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"A6QY2DI5","created_at":"2026-07-05T04:57:32Z"}],"graph_snapshots":[{"event_id":"sha256:5306b25e43c446fda438bf5b391fc44605feb0a0d422a46b8c5987e42c188f6e","target":"graph","created_at":"2026-07-05T04:57:32Z","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/2209.06583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have witnessed great progress on applying pre-trained language models, e.g., BERT, to information retrieval (IR) tasks. Hyperlinks, which are commonly used in Web pages, have been leveraged for designing pre-training objectives. For example, anchor texts of the hyperlinks have been used for simulating queries, thus constructing tremendous query-document pairs for pre-training. However, as a bridge across two web pages, the potential of hyperlinks has not been fully explored. In this work, we focus on modeling the relationship between two documents that are connected by hyperlinks ","authors_text":"Jiawen Wu, Ruofei Lai, Xinyu Zhang, Yongkang Wu, Yutao Zhu, Zhao Cao, Zhaoye Fei, Zheng Liu, Zhicheng Dou, Zikai Guo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-14T12:03:31Z","title":"Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06583","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":"sha256:58349d1cb22ce1853f66e2ad383f35272abd98efa0f15f8cb2b6b8603a2e3713","target":"record","created_at":"2026-07-05T04:57:32Z","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":"a35b45f39f1e3c28aa171292d9eca8f97d41b608d78220945a7576093de909eb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-14T12:03:31Z","title_canon_sha256":"aeffde39dbc0585f25119d6a9a73bc0549a6d6ce72aabead16fdb4ef6a3c4da3"},"schema_version":"1.0","source":{"id":"2209.06583","kind":"arxiv","version":1}},"canonical_sha256":"07a18d0d1ddd96cf46c9c369893aed7b5b1b8d2b0e3392334cfb74f99887a4a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07a18d0d1ddd96cf46c9c369893aed7b5b1b8d2b0e3392334cfb74f99887a4a5","first_computed_at":"2026-07-05T04:57:32.464212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:32.464212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I/nqB5U6M+7+vrsOrYEjVFa0aAL3ZioW1uiqyAgmt3o3v1bxf+MU0mcR18Qa67OR2IDAFsN0OGqQsD/yV2S8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:32.464646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58349d1cb22ce1853f66e2ad383f35272abd98efa0f15f8cb2b6b8603a2e3713","sha256:5306b25e43c446fda438bf5b391fc44605feb0a0d422a46b8c5987e42c188f6e"],"state_sha256":"d4dfbd938db379e87cc9e90d070dc53c0d8765d82209ab915f80cdc849183f53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wA3ohEHEbTGJFKFezu8ncJyQ0VNxYDjs/pw22eEbnijLA8xkuHpezMzkH+n0Syn0WMbKzP7EpgJsK/smLWKtAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:43:32.378270Z","bundle_sha256":"901e1de530aff9ba01ef69bc3c9b2992cd11a7c1e8c73ea35afe0ede242d7afc"}}