{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PDZIM2VJNR2HFKP5EVFKSXYSSB","short_pith_number":"pith:PDZIM2VJ","canonical_record":{"source":{"id":"2605.16474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T15:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a4bd550581a91b0cebd406dbfa7b4bd4e876dbc07bfc14eac9dc4b841ea2d55","abstract_canon_sha256":"c0e6899192d86eedfa53dc0864ba55582516ef68e5f80ff21c2a80b1e5502267"},"schema_version":"1.0"},"canonical_sha256":"78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d","source":{"kind":"arxiv","id":"2605.16474","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16474","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16474v1","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16474","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"PDZIM2VJNR2H","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"PDZIM2VJNR2HFKP5","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"PDZIM2VJ","created_at":"2026-05-20T00:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PDZIM2VJNR2HFKP5EVFKSXYSSB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T15:39:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a4bd550581a91b0cebd406dbfa7b4bd4e876dbc07bfc14eac9dc4b841ea2d55","abstract_canon_sha256":"c0e6899192d86eedfa53dc0864ba55582516ef68e5f80ff21c2a80b1e5502267"},"schema_version":"1.0"},"canonical_sha256":"78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:23.876541Z","signature_b64":"LFBJMzFTw/1XJ0B/GR3X6FRtB/R+4yskKEg+/nceDINVoMAoAxDdG053tAYbOvdXkhNUgsbOAlemg2OkygQjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d","last_reissued_at":"2026-05-20T00:02:23.875842Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:23.875842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16474","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":"2026-05-20T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/JcLhQEXb1Nf98CHzQ5z4QULP0VvmD1xMReZ9knGbTjLlEXgi6UFnfXx6wyWN8luz3sO5vJ53RNoTAc42rIpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:20:03.358511Z"},"content_sha256":"130142e5dab7b185ec695367a600c2735c1c3a441f270cb8c9a90870fb2324e5","schema_version":"1.0","event_id":"sha256:130142e5dab7b185ec695367a600c2735c1c3a441f270cb8c9a90870fb2324e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PDZIM2VJNR2HFKP5EVFKSXYSSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots.","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Chuan Yu, Haoran Sun, Jian Xu, Xiaotie Deng, Xinrui Song, Xinyu Zhang, Xu Chu, Zhaohua Chen, Zhilin Zhang","submitted_at":"2026-05-15T15:39:30Z","abstract_excerpt":"The integration of advertising auction mechanisms into large language model (LLM)-based chatbots presents a significant opportunity for commercialization, yet poses unique challenges in balancing relevance, efficiency, and user experience. Recently, Feizi et al.~\\citep{feizi2023online} and Hajiaghayi et al.~\\citep{hajiaghayi2024ad} outlined a retrieve-then-generate paradigm that decouples retrieval and generation, offering lightweight ad insertion and payment determination. However, current retrieval relies solely on text embedding similarity, which may lead to commercial misinterpretation and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The LERA framework ensures truthfulness for utility-maximizing advertisers by using a critical-value payment rule that accounts for both the coarse-filtering and fine-ranking thresholds.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that logits produced by a carefully designed prompt to the LLM constitute reliable, unbiased organic relevance scores that can be directly combined with bids without introducing new commercial misinterpretation or repetitive insertion problems.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LERA is a retrieve-then-generate auction system that refines ad candidate ranking with LLM logits and applies a threshold-aware critical-value payment rule to maintain truthfulness in chatbot ad insertion.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"74a48ea5d2d18a37b6aade6c2e04c9558ee9196d91c698805959acca467a9223"},"source":{"id":"2605.16474","kind":"arxiv","version":1},"verdict":{"id":"deebf04f-bf18-474a-8c47-067ca0d9fdd4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:57:22.540052Z","strongest_claim":"The LERA framework ensures truthfulness for utility-maximizing advertisers by using a critical-value payment rule that accounts for both the coarse-filtering and fine-ranking thresholds.","one_line_summary":"LERA is a retrieve-then-generate auction system that refines ad candidate ranking with LLM logits and applies a threshold-aware critical-value payment rule to maintain truthfulness in chatbot ad insertion.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that logits produced by a carefully designed prompt to the LLM constitute reliable, unbiased organic relevance scores that can be directly combined with bids without introducing new commercial misinterpretation or repetitive insertion problems.","pith_extraction_headline":"LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16474/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.635838Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:12:41.363236Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:23.114895Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.046034Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6894cf608585feb40842220e38cb0ef6e3b1e783ea76d7070ace36e13f1ba44e"},"references":{"count":66,"sample":[{"doi":"","year":2025,"title":"Position auctions in ai-generated content.arXiv preprint arXiv:2506.03309, 2025","work_id":"1f1dd137-a287-48ff-b2fd-315a3736c796","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Uncovering chatgpt’s capabilities in recommender systems","work_id":"3cbe0ad0-f18e-44b4-af95-808e87884753","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Deepseek-v3.2: Pushing the frontier of open large language models","work_id":"a8309cf7-193a-4534-bf54-fa1d763fecfb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Auctions with llm summaries","work_id":"d097e048-c8a8-43e7-a645-2a1f8e58cefe","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Mechanism design for large language models","work_id":"cf0ee41a-ec23-4b62-93d5-9535dbdad391","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":66,"snapshot_sha256":"34a6da9c8db8e687cd33a7a24e319151e642fadc437f50218dc6603d1d048d91","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bdc2644db1667f093e0973863331f648713f39daee49752da275381e4bf36a38"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"deebf04f-bf18-474a-8c47-067ca0d9fdd4"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hnzPNseTtwOeFiLyNFphtJEnoWH6kUmVmgmZhBShS+A6Mq07h7QBEwgzsPcPmYmzjSAdS0WcaQFgixhtCw2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:20:03.360039Z"},"content_sha256":"57491fd3f6d2a04b56c39e15f327b8ec1da84273bf3e0e48c60a6cb732455336","schema_version":"1.0","event_id":"sha256:57491fd3f6d2a04b56c39e15f327b8ec1da84273bf3e0e48c60a6cb732455336"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB/bundle.json","state_url":"https://pith.science/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB/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":"2026-05-27T22:20:03Z","links":{"resolver":"https://pith.science/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB","bundle":"https://pith.science/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB/bundle.json","state":"https://pith.science/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PDZIM2VJNR2HFKP5EVFKSXYSSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PDZIM2VJNR2HFKP5EVFKSXYSSB","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":"c0e6899192d86eedfa53dc0864ba55582516ef68e5f80ff21c2a80b1e5502267","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T15:39:30Z","title_canon_sha256":"3a4bd550581a91b0cebd406dbfa7b4bd4e876dbc07bfc14eac9dc4b841ea2d55"},"schema_version":"1.0","source":{"id":"2605.16474","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16474","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16474v1","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16474","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"PDZIM2VJNR2H","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"PDZIM2VJNR2HFKP5","created_at":"2026-05-20T00:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"PDZIM2VJ","created_at":"2026-05-20T00:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:57491fd3f6d2a04b56c39e15f327b8ec1da84273bf3e0e48c60a6cb732455336","target":"graph","created_at":"2026-05-20T00:02:23Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The LERA framework ensures truthfulness for utility-maximizing advertisers by using a critical-value payment rule that accounts for both the coarse-filtering and fine-ranking thresholds."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that logits produced by a carefully designed prompt to the LLM constitute reliable, unbiased organic relevance scores that can be directly combined with bids without introducing new commercial misinterpretation or repetitive insertion problems."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LERA is a retrieve-then-generate auction system that refines ad candidate ranking with LLM logits and applies a threshold-aware critical-value payment rule to maintain truthfulness in chatbot ad insertion."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots."}],"snapshot_sha256":"74a48ea5d2d18a37b6aade6c2e04c9558ee9196d91c698805959acca467a9223"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bdc2644db1667f093e0973863331f648713f39daee49752da275381e4bf36a38"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.635838Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:12:41.363236Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:23.114895Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.046034Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16474/integrity.json","findings":[],"snapshot_sha256":"6894cf608585feb40842220e38cb0ef6e3b1e783ea76d7070ace36e13f1ba44e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of advertising auction mechanisms into large language model (LLM)-based chatbots presents a significant opportunity for commercialization, yet poses unique challenges in balancing relevance, efficiency, and user experience. Recently, Feizi et al.~\\citep{feizi2023online} and Hajiaghayi et al.~\\citep{hajiaghayi2024ad} outlined a retrieve-then-generate paradigm that decouples retrieval and generation, offering lightweight ad insertion and payment determination. However, current retrieval relies solely on text embedding similarity, which may lead to commercial misinterpretation and","authors_text":"Bo Zheng, Chuan Yu, Haoran Sun, Jian Xu, Xiaotie Deng, Xinrui Song, Xinyu Zhang, Xu Chu, Zhaohua Chen, Zhilin Zhang","cross_cats":["cs.AI"],"headline":"LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T15:39:30Z","title":"LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots"},"references":{"count":66,"internal_anchors":3,"resolved_work":66,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Position auctions in ai-generated content.arXiv preprint arXiv:2506.03309, 2025","work_id":"1f1dd137-a287-48ff-b2fd-315a3736c796","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Uncovering chatgpt’s capabilities in recommender systems","work_id":"3cbe0ad0-f18e-44b4-af95-808e87884753","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Deepseek-v3.2: Pushing the frontier of open large language models","work_id":"a8309cf7-193a-4534-bf54-fa1d763fecfb","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Auctions with llm summaries","work_id":"d097e048-c8a8-43e7-a645-2a1f8e58cefe","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Mechanism design for large language models","work_id":"cf0ee41a-ec23-4b62-93d5-9535dbdad391","year":2024}],"snapshot_sha256":"34a6da9c8db8e687cd33a7a24e319151e642fadc437f50218dc6603d1d048d91"},"source":{"id":"2605.16474","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:57:22.540052Z","id":"deebf04f-bf18-474a-8c47-067ca0d9fdd4","model_set":{"reader":"grok-4.3"},"one_line_summary":"LERA is a retrieve-then-generate auction system that refines ad candidate ranking with LLM logits and applies a threshold-aware critical-value payment rule to maintain truthfulness in chatbot ad insertion.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"LERA combines embedding filters with LLM logits for relevance and applies a critical-value payment to run truthful ad auctions inside generative chatbots.","strongest_claim":"The LERA framework ensures truthfulness for utility-maximizing advertisers by using a critical-value payment rule that accounts for both the coarse-filtering and fine-ranking thresholds.","weakest_assumption":"The assumption that logits produced by a carefully designed prompt to the LLM constitute reliable, unbiased organic relevance scores that can be directly combined with bids without introducing new commercial misinterpretation or repetitive insertion problems."}},"verdict_id":"deebf04f-bf18-474a-8c47-067ca0d9fdd4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:130142e5dab7b185ec695367a600c2735c1c3a441f270cb8c9a90870fb2324e5","target":"record","created_at":"2026-05-20T00:02:23Z","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":"c0e6899192d86eedfa53dc0864ba55582516ef68e5f80ff21c2a80b1e5502267","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T15:39:30Z","title_canon_sha256":"3a4bd550581a91b0cebd406dbfa7b4bd4e876dbc07bfc14eac9dc4b841ea2d55"},"schema_version":"1.0","source":{"id":"2605.16474","kind":"arxiv","version":1}},"canonical_sha256":"78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78f2866aa96c7472a9fd254aa95f12906811aa96630b984b5438f84ee01ff87d","first_computed_at":"2026-05-20T00:02:23.875842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:23.875842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LFBJMzFTw/1XJ0B/GR3X6FRtB/R+4yskKEg+/nceDINVoMAoAxDdG053tAYbOvdXkhNUgsbOAlemg2OkygQjCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:23.876541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16474","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:130142e5dab7b185ec695367a600c2735c1c3a441f270cb8c9a90870fb2324e5","sha256:57491fd3f6d2a04b56c39e15f327b8ec1da84273bf3e0e48c60a6cb732455336"],"state_sha256":"c49c7909c7e1b33ed87b3755ba0a581045f2963b8a1214f7989491807f0d5516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtQeoruV8L9nm65BGZdhLRkuP0HgyZ9apaYCySm2+75wqmjNyI3M6+Nlnd5rRbAfqGCksKIGeiA4n35JyQkKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:20:03.365271Z","bundle_sha256":"63b1ace30a3bda070230cd5829d1ab06fae5b1092558b55a1d1305888aa23e7e"}}