{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WMGOVNE6A6HLD5LSRNDOTVBFFS","short_pith_number":"pith:WMGOVNE6","canonical_record":{"source":{"id":"2308.15711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T02:22:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23479cda7989b6003a3ccff871867cbb71109ffd339c35d5f6d3cea41f853097","abstract_canon_sha256":"cd2508f9686100fc06da2e9587dae106fd4bc7c493c3114c9db24fdf0dc9adc5"},"schema_version":"1.0"},"canonical_sha256":"b30ceab49e078eb1f5728b46e9d4252cb90a0868295f693de024baf8dd968422","source":{"kind":"arxiv","id":"2308.15711","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15711","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15711v1","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15711","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"WMGOVNE6A6HL","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"WMGOVNE6A6HLD5LS","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"WMGOVNE6","created_at":"2026-07-05T06:46:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WMGOVNE6A6HLD5LSRNDOTVBFFS","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T02:22:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23479cda7989b6003a3ccff871867cbb71109ffd339c35d5f6d3cea41f853097","abstract_canon_sha256":"cd2508f9686100fc06da2e9587dae106fd4bc7c493c3114c9db24fdf0dc9adc5"},"schema_version":"1.0"},"canonical_sha256":"b30ceab49e078eb1f5728b46e9d4252cb90a0868295f693de024baf8dd968422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:12.234075Z","signature_b64":"MKCvKw5BMebaPgtBHee94OsavczgEpRgIOU1shH8yjrsbF+ulF7P6DAN23yXmYrmzctzZwqfHmhpFjg38kIxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b30ceab49e078eb1f5728b46e9d4252cb90a0868295f693de024baf8dd968422","last_reissued_at":"2026-07-05T06:46:12.233583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:12.233583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15711","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":"2026-07-05T06:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/4hr+ADgQQkQ0m6P041a4Jx8pmlz7qvE4Jbfhoe8+0aHq8Rd/aBvkWgTX4eJTCkNNyem7ePtSgmqFV8N34aCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:52.008444Z"},"content_sha256":"1ce69cca7b0dcbd093ca5d0b8c41c8cee926b59c18fdee2f00b46d659a90f601","schema_version":"1.0","event_id":"sha256:1ce69cca7b0dcbd093ca5d0b8c41c8cee926b59c18fdee2f00b46d659a90f601"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WMGOVNE6A6HLD5LSRNDOTVBFFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haonan Chen, Haoqi Gu, Hongjin Qian, Jiejun Tan, Ji-Rong Wen, Ruofei Lai, Xinyu Zhang, Zhao Cao, Zhicheng Dou","submitted_at":"2023-08-30T02:22:40Z","abstract_excerpt":"Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text, raising concerns about their reliability. Previous methods use external knowledge as references for text generation to enhance factuality but often struggle with the knowledge mix-up(e.g., entity mismatch) of irrelevant references. Besides,as the length of the output text grows, the randomness of sampling can escalate, detrimentally impacting the factual accuracy of the generated text. In this paper, we present DKGen, which divide the text generation process into an iterativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15711","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/2308.15711/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":"2026-07-05T06:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAaR+mJRKIrSgsbjUmzCmi5M/wtFcYOo7oKQDCVpjqkWFLcPlDfJ/STpvfAHEcJB2oEJSA95Ro6Wo0d1KUm2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:52.008824Z"},"content_sha256":"4caa58da50bb43e7cbefb029c271f40dab53f20209a75ef3ab9e460dec9914a9","schema_version":"1.0","event_id":"sha256:4caa58da50bb43e7cbefb029c271f40dab53f20209a75ef3ab9e460dec9914a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS/bundle.json","state_url":"https://pith.science/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS/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":"2026-07-06T15:09:52Z","links":{"resolver":"https://pith.science/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS","bundle":"https://pith.science/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS/bundle.json","state":"https://pith.science/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMGOVNE6A6HLD5LSRNDOTVBFFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WMGOVNE6A6HLD5LSRNDOTVBFFS","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":"cd2508f9686100fc06da2e9587dae106fd4bc7c493c3114c9db24fdf0dc9adc5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T02:22:40Z","title_canon_sha256":"23479cda7989b6003a3ccff871867cbb71109ffd339c35d5f6d3cea41f853097"},"schema_version":"1.0","source":{"id":"2308.15711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15711","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15711v1","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15711","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"WMGOVNE6A6HL","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"WMGOVNE6A6HLD5LS","created_at":"2026-07-05T06:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"WMGOVNE6","created_at":"2026-07-05T06:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:4caa58da50bb43e7cbefb029c271f40dab53f20209a75ef3ab9e460dec9914a9","target":"graph","created_at":"2026-07-05T06:46:12Z","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/2308.15711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text, raising concerns about their reliability. Previous methods use external knowledge as references for text generation to enhance factuality but often struggle with the knowledge mix-up(e.g., entity mismatch) of irrelevant references. Besides,as the length of the output text grows, the randomness of sampling can escalate, detrimentally impacting the factual accuracy of the generated text. In this paper, we present DKGen, which divide the text generation process into an iterativ","authors_text":"Haonan Chen, Haoqi Gu, Hongjin Qian, Jiejun Tan, Ji-Rong Wen, Ruofei Lai, Xinyu Zhang, Zhao Cao, Zhicheng Dou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T02:22:40Z","title":"Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15711","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":"sha256:1ce69cca7b0dcbd093ca5d0b8c41c8cee926b59c18fdee2f00b46d659a90f601","target":"record","created_at":"2026-07-05T06:46:12Z","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":"cd2508f9686100fc06da2e9587dae106fd4bc7c493c3114c9db24fdf0dc9adc5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T02:22:40Z","title_canon_sha256":"23479cda7989b6003a3ccff871867cbb71109ffd339c35d5f6d3cea41f853097"},"schema_version":"1.0","source":{"id":"2308.15711","kind":"arxiv","version":1}},"canonical_sha256":"b30ceab49e078eb1f5728b46e9d4252cb90a0868295f693de024baf8dd968422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b30ceab49e078eb1f5728b46e9d4252cb90a0868295f693de024baf8dd968422","first_computed_at":"2026-07-05T06:46:12.233583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:12.233583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MKCvKw5BMebaPgtBHee94OsavczgEpRgIOU1shH8yjrsbF+ulF7P6DAN23yXmYrmzctzZwqfHmhpFjg38kIxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:12.234075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ce69cca7b0dcbd093ca5d0b8c41c8cee926b59c18fdee2f00b46d659a90f601","sha256:4caa58da50bb43e7cbefb029c271f40dab53f20209a75ef3ab9e460dec9914a9"],"state_sha256":"567139515d25bcc0b7d57731788778f66ae69f92bcd92013e167a6648ec3d555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5DSxRyfGQLl+HmDQAclitCW+G8C/oz9TKcbOPPKS0hzomBsA0+4ELYTj0vwvetGpAPEXc5RhBOlNv0ppoiWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:09:52.010733Z","bundle_sha256":"34acfe0f8ebfa08a22ba3e3e711066bcd665b0f90889d081d23a3a2de2fce0be"}}