{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JCORMHNJVN3TW24ONXDTEWUJK6","short_pith_number":"pith:JCORMHNJ","canonical_record":{"source":{"id":"2301.00303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-31T22:35:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a8b14187f90a29e05870ce709e67860482b22b438658e15a54125295ded9d9d","abstract_canon_sha256":"c11205e946e319f253e8a96cf4f72536e461582145369947537d92ee69ca2072"},"schema_version":"1.0"},"canonical_sha256":"489d161da9ab773b6b8e6dc7325a89578b082eb4b6bd9a848a1a7785f0e691c6","source":{"kind":"arxiv","id":"2301.00303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.00303","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"2301.00303v1","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.00303","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"JCORMHNJVN3T","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"JCORMHNJVN3TW24O","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"JCORMHNJ","created_at":"2026-07-05T05:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JCORMHNJVN3TW24ONXDTEWUJK6","target":"record","payload":{"canonical_record":{"source":{"id":"2301.00303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-31T22:35:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a8b14187f90a29e05870ce709e67860482b22b438658e15a54125295ded9d9d","abstract_canon_sha256":"c11205e946e319f253e8a96cf4f72536e461582145369947537d92ee69ca2072"},"schema_version":"1.0"},"canonical_sha256":"489d161da9ab773b6b8e6dc7325a89578b082eb4b6bd9a848a1a7785f0e691c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:44.984758Z","signature_b64":"cq9TTztqjN190X0LziKtvICznaQgjE2xewV4hk++Tr7mmy68PVJegVzYBqL24RQENrwGVKGtIcU/OMr7vEkyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"489d161da9ab773b6b8e6dc7325a89578b082eb4b6bd9a848a1a7785f0e691c6","last_reissued_at":"2026-07-05T05:29:44.984236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:44.984236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.00303","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":"2026-07-05T05:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"km5taxeHuydA6Pke99CI6MvoQQG5R3+oBZFrFD/FCoySy0CML7wtLjror49jKsitaYKHeqblYFClxuJG5OmQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:05:40.642840Z"},"content_sha256":"077a5066e798c6bbee88c02beee15673b7eaff37d8721bc91f892e22b2a3d653","schema_version":"1.0","event_id":"sha256:077a5066e798c6bbee88c02beee15673b7eaff37d8721bc91f892e22b2a3d653"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JCORMHNJVN3TW24ONXDTEWUJK6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking with Retrieval: Faithful Large Language Model Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Roth, Hangfeng He, Hongming Zhang","submitted_at":"2022-12-31T22:35:34Z","abstract_excerpt":"Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.00303","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/2301.00303/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":"2026-07-05T05:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMYbWp9nITD6g7aH2Fxwh8lrmGtEHiP+Kyi/+/u9cKNyjROR1ieRS9ayMElEVv1VZSgmMb9S5TP0TWv4H13hBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:05:40.643342Z"},"content_sha256":"f988b9167b3338844fa29d55ea5c48dde24fb34710054c83a2de1130fa871d59","schema_version":"1.0","event_id":"sha256:f988b9167b3338844fa29d55ea5c48dde24fb34710054c83a2de1130fa871d59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCORMHNJVN3TW24ONXDTEWUJK6/bundle.json","state_url":"https://pith.science/pith/JCORMHNJVN3TW24ONXDTEWUJK6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCORMHNJVN3TW24ONXDTEWUJK6/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":"2026-08-05T01:05:40Z","links":{"resolver":"https://pith.science/pith/JCORMHNJVN3TW24ONXDTEWUJK6","bundle":"https://pith.science/pith/JCORMHNJVN3TW24ONXDTEWUJK6/bundle.json","state":"https://pith.science/pith/JCORMHNJVN3TW24ONXDTEWUJK6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCORMHNJVN3TW24ONXDTEWUJK6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JCORMHNJVN3TW24ONXDTEWUJK6","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":"c11205e946e319f253e8a96cf4f72536e461582145369947537d92ee69ca2072","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-31T22:35:34Z","title_canon_sha256":"5a8b14187f90a29e05870ce709e67860482b22b438658e15a54125295ded9d9d"},"schema_version":"1.0","source":{"id":"2301.00303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.00303","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"2301.00303v1","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.00303","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"JCORMHNJVN3T","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"JCORMHNJVN3TW24O","created_at":"2026-07-05T05:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"JCORMHNJ","created_at":"2026-07-05T05:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:f988b9167b3338844fa29d55ea5c48dde24fb34710054c83a2de1130fa871d59","target":"graph","created_at":"2026-07-05T05:29:44Z","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/2301.00303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the dec","authors_text":"Dan Roth, Hangfeng He, Hongming Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-31T22:35:34Z","title":"Rethinking with Retrieval: Faithful Large Language Model Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.00303","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":"sha256:077a5066e798c6bbee88c02beee15673b7eaff37d8721bc91f892e22b2a3d653","target":"record","created_at":"2026-07-05T05:29:44Z","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":"c11205e946e319f253e8a96cf4f72536e461582145369947537d92ee69ca2072","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-31T22:35:34Z","title_canon_sha256":"5a8b14187f90a29e05870ce709e67860482b22b438658e15a54125295ded9d9d"},"schema_version":"1.0","source":{"id":"2301.00303","kind":"arxiv","version":1}},"canonical_sha256":"489d161da9ab773b6b8e6dc7325a89578b082eb4b6bd9a848a1a7785f0e691c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"489d161da9ab773b6b8e6dc7325a89578b082eb4b6bd9a848a1a7785f0e691c6","first_computed_at":"2026-07-05T05:29:44.984236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:44.984236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cq9TTztqjN190X0LziKtvICznaQgjE2xewV4hk++Tr7mmy68PVJegVzYBqL24RQENrwGVKGtIcU/OMr7vEkyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:44.984758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.00303","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:077a5066e798c6bbee88c02beee15673b7eaff37d8721bc91f892e22b2a3d653","sha256:f988b9167b3338844fa29d55ea5c48dde24fb34710054c83a2de1130fa871d59"],"state_sha256":"3b83524c298e58bfd55762265af8b87626fc4c0a2bc6ed7e7f0e21a4a55e478c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LxpU+5zYKNOn1qb9jp4tx3OR7xLu1YbEzpJbYLg9dP591pAiehGlYfTi+Yiz930zkG91eW0Wohj65R16XZZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:05:40.649583Z","bundle_sha256":"a371792fa9572a4b2c057a9a9ef581f8a53f32ed20da15eaf60435fe1d258abd"}}