{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:G2WP4D6B6BVW5QGFIXHJUXS4FS","short_pith_number":"pith:G2WP4D6B","canonical_record":{"source":{"id":"2206.02743","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-06T16:56:52Z","cross_cats_sorted":[],"title_canon_sha256":"b0bf8363b9a5b1bffe01a9d1e0bf858c2a9e52053ce85f2c161624e55b69b190","abstract_canon_sha256":"2458d5ea4236de90a83a4fc4daccdecd749bfba1c634f1f6647752090a87972d"},"schema_version":"1.0"},"canonical_sha256":"36acfe0fc1f06b6ec0c545ce9a5e5c2c841dcc3e6c5285defa5d9057a5a911ba","source":{"kind":"arxiv","id":"2206.02743","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02743","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02743v3","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02743","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"pith_short_12","alias_value":"G2WP4D6B6BVW","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"pith_short_16","alias_value":"G2WP4D6B6BVW5QGF","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"pith_short_8","alias_value":"G2WP4D6B","created_at":"2026-07-05T05:40:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:G2WP4D6B6BVW5QGFIXHJUXS4FS","target":"record","payload":{"canonical_record":{"source":{"id":"2206.02743","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-06T16:56:52Z","cross_cats_sorted":[],"title_canon_sha256":"b0bf8363b9a5b1bffe01a9d1e0bf858c2a9e52053ce85f2c161624e55b69b190","abstract_canon_sha256":"2458d5ea4236de90a83a4fc4daccdecd749bfba1c634f1f6647752090a87972d"},"schema_version":"1.0"},"canonical_sha256":"36acfe0fc1f06b6ec0c545ce9a5e5c2c841dcc3e6c5285defa5d9057a5a911ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:46.864540Z","signature_b64":"l7SrgYhwfWzZNBYu/Y9rIOkOyR5xatMtVy0ioGRXaW4nhYnxDijCbLjhawY0xlbhXgenUS23dttQyOQUlQpiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36acfe0fc1f06b6ec0c545ce9a5e5c2c841dcc3e6c5285defa5d9057a5a911ba","last_reissued_at":"2026-07-05T05:40:46.864018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:46.864018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.02743","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D72YGaU65vmD/+qSlJNwKPLNjC2pspWDbovyf96MBuyv1h9P4VwwPAEPXZM3qOnt9N/JVt221zO0MlPeuEkDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:54:28.189322Z"},"content_sha256":"770e7f9802363aa38e9883c97deedfb14b146900a48e482e6d5869dd5ee0269b","schema_version":"1.0","event_id":"sha256:770e7f9802363aa38e9883c97deedfb14b146900a48e482e6d5869dd5ee0269b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:G2WP4D6B6BVW5QGFIXHJUXS4FS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Neural Corpus Indexer for Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chengmin Chi, Guoshuai Zhao, Hao Allen Sun, Haonan Wang, Hao Sun, Mao Yang, Qi Chen, Qi Zhang, Shibin Wu, Weiwei Deng, Xing Xie, Yingyan Hou, Yujing Wang, Yuqing Xia, Zheng Liu, Ziming Miao","submitted_at":"2022-06-06T16:56:52Z","abstract_excerpt":"Current state-of-the-art document retrieval solutions mainly follow an index-retrieve paradigm, where the index is hard to be directly optimized for the final retrieval target. In this paper, we aim to show that an end-to-end deep neural network unifying training and indexing stages can significantly improve the recall performance of traditional methods. To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query. To optimize the recall performance of NCI, we invent a prefix-aware weight-adapti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02743","kind":"arxiv","version":3},"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/2206.02743/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":"2026-07-05T05:40:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8HUYHzcAsUlbVoU9fzVoDehrMQaAMhD8eGWzHeayuYWJmP6jcG0K8b8xpjcxO970rkERsj3IqZ8SWTxS/wXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:54:28.189829Z"},"content_sha256":"a3479d441eff639b7ea95d3431db674311c705c4293085eb1167357e2e71fee9","schema_version":"1.0","event_id":"sha256:a3479d441eff639b7ea95d3431db674311c705c4293085eb1167357e2e71fee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS/bundle.json","state_url":"https://pith.science/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS/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":"2026-08-07T10:54:28Z","links":{"resolver":"https://pith.science/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS","bundle":"https://pith.science/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS/bundle.json","state":"https://pith.science/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2WP4D6B6BVW5QGFIXHJUXS4FS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G2WP4D6B6BVW5QGFIXHJUXS4FS","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":"2458d5ea4236de90a83a4fc4daccdecd749bfba1c634f1f6647752090a87972d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-06T16:56:52Z","title_canon_sha256":"b0bf8363b9a5b1bffe01a9d1e0bf858c2a9e52053ce85f2c161624e55b69b190"},"schema_version":"1.0","source":{"id":"2206.02743","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02743","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02743v3","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02743","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"pith_short_12","alias_value":"G2WP4D6B6BVW","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"pith_short_16","alias_value":"G2WP4D6B6BVW5QGF","created_at":"2026-07-05T05:40:46Z"},{"alias_kind":"pith_short_8","alias_value":"G2WP4D6B","created_at":"2026-07-05T05:40:46Z"}],"graph_snapshots":[{"event_id":"sha256:a3479d441eff639b7ea95d3431db674311c705c4293085eb1167357e2e71fee9","target":"graph","created_at":"2026-07-05T05:40:46Z","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/2206.02743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current state-of-the-art document retrieval solutions mainly follow an index-retrieve paradigm, where the index is hard to be directly optimized for the final retrieval target. In this paper, we aim to show that an end-to-end deep neural network unifying training and indexing stages can significantly improve the recall performance of traditional methods. To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query. To optimize the recall performance of NCI, we invent a prefix-aware weight-adapti","authors_text":"Chengmin Chi, Guoshuai Zhao, Hao Allen Sun, Haonan Wang, Hao Sun, Mao Yang, Qi Chen, Qi Zhang, Shibin Wu, Weiwei Deng, Xing Xie, Yingyan Hou, Yujing Wang, Yuqing Xia, Zheng Liu, Ziming Miao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-06T16:56:52Z","title":"A Neural Corpus Indexer for Document Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02743","kind":"arxiv","version":3},"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":"sha256:770e7f9802363aa38e9883c97deedfb14b146900a48e482e6d5869dd5ee0269b","target":"record","created_at":"2026-07-05T05:40:46Z","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":"2458d5ea4236de90a83a4fc4daccdecd749bfba1c634f1f6647752090a87972d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-06T16:56:52Z","title_canon_sha256":"b0bf8363b9a5b1bffe01a9d1e0bf858c2a9e52053ce85f2c161624e55b69b190"},"schema_version":"1.0","source":{"id":"2206.02743","kind":"arxiv","version":3}},"canonical_sha256":"36acfe0fc1f06b6ec0c545ce9a5e5c2c841dcc3e6c5285defa5d9057a5a911ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36acfe0fc1f06b6ec0c545ce9a5e5c2c841dcc3e6c5285defa5d9057a5a911ba","first_computed_at":"2026-07-05T05:40:46.864018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:46.864018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l7SrgYhwfWzZNBYu/Y9rIOkOyR5xatMtVy0ioGRXaW4nhYnxDijCbLjhawY0xlbhXgenUS23dttQyOQUlQpiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:46.864540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02743","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:770e7f9802363aa38e9883c97deedfb14b146900a48e482e6d5869dd5ee0269b","sha256:a3479d441eff639b7ea95d3431db674311c705c4293085eb1167357e2e71fee9"],"state_sha256":"18fa101330bef7f3d3e8ab9d45f4fb140832c774b4179dc68dd129357e62fa32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xlhJRS585cF7T8rVr2XGVKzhVV6lLh++X4KRQozlhXfnHf41Us4DlHwEYlNkrwMNllV5cKbc0mAqEMGOJv4wCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:54:28.194622Z","bundle_sha256":"974de71aeb68e79a85da3ba69c651c940299c74f0a6dbe6f2a72afb78a0cde7c"}}