{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M5WLHRDP3GFADTXBMCQMJESRJV","short_pith_number":"pith:M5WLHRDP","canonical_record":{"source":{"id":"2605.16825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T06:02:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d46c42a553fbd03f14ece5762727663a84b0b96a3d84253fd847ef0ef9fc3438","abstract_canon_sha256":"5184a92f5d0609a10357796c50d4d871d39989d238f575b13e056458448765ec"},"schema_version":"1.0"},"canonical_sha256":"676cb3c46fd98a01cee160a0c492514d7660a873087c51de92f5e696d2dba7f4","source":{"kind":"arxiv","id":"2605.16825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16825","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16825v1","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16825","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"M5WLHRDP3GFA","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"M5WLHRDP3GFADTXB","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"M5WLHRDP","created_at":"2026-05-20T00:03:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M5WLHRDP3GFADTXBMCQMJESRJV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T06:02:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d46c42a553fbd03f14ece5762727663a84b0b96a3d84253fd847ef0ef9fc3438","abstract_canon_sha256":"5184a92f5d0609a10357796c50d4d871d39989d238f575b13e056458448765ec"},"schema_version":"1.0"},"canonical_sha256":"676cb3c46fd98a01cee160a0c492514d7660a873087c51de92f5e696d2dba7f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:24.628739Z","signature_b64":"XHWVbjRjv6lFCbKLH9lw/+WAuXmOxHYXsKQL/uWFAnIIGMx9CJChuCABlhv0uzJyP98SA05gR6Jp6rAdHzMhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"676cb3c46fd98a01cee160a0c492514d7660a873087c51de92f5e696d2dba7f4","last_reissued_at":"2026-05-20T00:03:24.627724Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:24.627724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16825","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":"2026-05-20T00:03:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HuPVTOCTHdE3n4YdrovgkHI1QP9RVxJZDufJxYtyl0xXsGzB7CsxDKLqdD9Tb6rXfrxUsrQbHDdQFwTx+EsMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:01:31.570880Z"},"content_sha256":"d2741b7f98339e41f390b67823c994698bf026900c51526e5dbfb49855910123","schema_version":"1.0","event_id":"sha256:d2741b7f98339e41f390b67823c994698bf026900c51526e5dbfb49855910123"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M5WLHRDP3GFADTXBMCQMJESRJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Generative recommenders develop severe popularity bias from token-level optimization flaws and uniform item tokenization, which Ghost corrects using asymmetric unlikelihood optimization and skeleton-founded tokenization.","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bangguo Zhu, Chengqi Zhang, Hao Chen, Jun Yin, Peng Huo, Ruochen Liu, Senzhang Wang, Shirui Pan","submitted_at":"2026-05-16T06:02:40Z","abstract_excerpt":"Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite their effectiveness, we recognize that GRs are still susceptible to the long-standing issue of popularity bias that has pervaded the recommendation community. Although a few studies have attempted to extend traditional debiasing methods to GRs, their effectiveness is marginal, and the fundamental reason why GRs suffer from popularity bias remains under-explored. To bridge this gap, this study focuses on two core aspe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The severe popularity bias emerges from the confluence of a token-level optimization flaw and the undifferentiated property of item tokenization. Ghost substantially alleviates popularity bias and promotes fairer recommendations, while incurring slight degradation to the overall recommendation utility.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The theoretical analyses correctly pinpoint the root causes of popularity bias in generative recommenders, and the proposed asymmetric unlikelihood optimization together with skeleton-founded tokenization effectively mitigate these causes without introducing new biases or requiring extensive post-hoc adjustments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ghost reduces popularity bias in generative recommenders through asymmetric unlikelihood optimization and skeleton-founded tokenization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Generative recommenders develop severe popularity bias from token-level optimization flaws and uniform item tokenization, which Ghost corrects using asymmetric unlikelihood optimization and skeleton-founded tokenization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"66956e986f9c986dd9ee3be94a944d113b9419a1da4cd5d3a51d881780f6559d"},"source":{"id":"2605.16825","kind":"arxiv","version":1},"verdict":{"id":"39f21910-0740-4853-9eb4-408e686847ef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:36:58.612047Z","strongest_claim":"The severe popularity bias emerges from the confluence of a token-level optimization flaw and the undifferentiated property of item tokenization. Ghost substantially alleviates popularity bias and promotes fairer recommendations, while incurring slight degradation to the overall recommendation utility.","one_line_summary":"Ghost reduces popularity bias in generative recommenders through asymmetric unlikelihood optimization and skeleton-founded tokenization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The theoretical analyses correctly pinpoint the root causes of popularity bias in generative recommenders, and the proposed asymmetric unlikelihood optimization together with skeleton-founded tokenization effectively mitigate these causes without introducing new biases or requiring extensive post-hoc adjustments.","pith_extraction_headline":"Generative recommenders develop severe popularity bias from token-level optimization flaws and uniform item tokenization, which Ghost corrects using asymmetric unlikelihood optimization and skeleton-founded tokenization."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16825/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.263145Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:51:12.772002Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.264014Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.406900Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"30ac0aa8453119816cc18cb187c9450c2bebf1ea2e4564b98c5d3180fa438d48"},"references":{"count":48,"sample":[{"doi":"","year":2018,"title":"Deep interest network for click-through rate prediction,","work_id":"fff87a5a-8e67-4b88-9795-93e8ab885c85","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Deep neural networks for youtube recommendations,","work_id":"b6151051-3638-48e9-b0e7-d852e0354625","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Deepinf: Social influence prediction with deep learning,","work_id":"ef73f8e6-b611-4cbc-9201-45955f44c50d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Recommender systems with generative retrieval,","work_id":"5e716d32-7499-4ef1-9f7a-73dd32168954","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Adapt- ing large language models by integrating collaborative semantics for recommendation,","work_id":"e3ebcb6e-47f0-4c9c-9599-6bb481c16ada","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":48,"snapshot_sha256":"7075b540928e313d569e03c7127422089969394e16183963f3d154ce5e1c7504","internal_anchors":2},"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":"39f21910-0740-4853-9eb4-408e686847ef"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqxB2yVfYNzFZkpOY9pBZX8WdBE5jQoLZlhfno9e0cTI9k5nVN+khzTd2G/GhandSWbYxtpcz3ZVKDNSkyF5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T15:01:31.572016Z"},"content_sha256":"8b95c469a43ec5fa0ae8afbcc4c6193059ed0d74e51da37a303227f594ea2291","schema_version":"1.0","event_id":"sha256:8b95c469a43ec5fa0ae8afbcc4c6193059ed0d74e51da37a303227f594ea2291"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5WLHRDP3GFADTXBMCQMJESRJV/bundle.json","state_url":"https://pith.science/pith/M5WLHRDP3GFADTXBMCQMJESRJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5WLHRDP3GFADTXBMCQMJESRJV/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":"2026-05-26T15:01:31Z","links":{"resolver":"https://pith.science/pith/M5WLHRDP3GFADTXBMCQMJESRJV","bundle":"https://pith.science/pith/M5WLHRDP3GFADTXBMCQMJESRJV/bundle.json","state":"https://pith.science/pith/M5WLHRDP3GFADTXBMCQMJESRJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5WLHRDP3GFADTXBMCQMJESRJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M5WLHRDP3GFADTXBMCQMJESRJV","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":"5184a92f5d0609a10357796c50d4d871d39989d238f575b13e056458448765ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T06:02:40Z","title_canon_sha256":"d46c42a553fbd03f14ece5762727663a84b0b96a3d84253fd847ef0ef9fc3438"},"schema_version":"1.0","source":{"id":"2605.16825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16825","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16825v1","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16825","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"M5WLHRDP3GFA","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"M5WLHRDP3GFADTXB","created_at":"2026-05-20T00:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"M5WLHRDP","created_at":"2026-05-20T00:03:24Z"}],"graph_snapshots":[{"event_id":"sha256:8b95c469a43ec5fa0ae8afbcc4c6193059ed0d74e51da37a303227f594ea2291","target":"graph","created_at":"2026-05-20T00:03:24Z","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 severe popularity bias emerges from the confluence of a token-level optimization flaw and the undifferentiated property of item tokenization. Ghost substantially alleviates popularity bias and promotes fairer recommendations, while incurring slight degradation to the overall recommendation utility."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The theoretical analyses correctly pinpoint the root causes of popularity bias in generative recommenders, and the proposed asymmetric unlikelihood optimization together with skeleton-founded tokenization effectively mitigate these causes without introducing new biases or requiring extensive post-hoc adjustments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Ghost reduces popularity bias in generative recommenders through asymmetric unlikelihood optimization and skeleton-founded tokenization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Generative recommenders develop severe popularity bias from token-level optimization flaws and uniform item tokenization, which Ghost corrects using asymmetric unlikelihood optimization and skeleton-founded tokenization."}],"snapshot_sha256":"66956e986f9c986dd9ee3be94a944d113b9419a1da4cd5d3a51d881780f6559d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.263145Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T20:51:12.772002Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.264014Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.406900Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16825/integrity.json","findings":[],"snapshot_sha256":"30ac0aa8453119816cc18cb187c9450c2bebf1ea2e4564b98c5d3180fa438d48","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the recommendation paradigm. Despite their effectiveness, we recognize that GRs are still susceptible to the long-standing issue of popularity bias that has pervaded the recommendation community. Although a few studies have attempted to extend traditional debiasing methods to GRs, their effectiveness is marginal, and the fundamental reason why GRs suffer from popularity bias remains under-explored. To bridge this gap, this study focuses on two core aspe","authors_text":"Bangguo Zhu, Chengqi Zhang, Hao Chen, Jun Yin, Peng Huo, Ruochen Liu, Senzhang Wang, Shirui Pan","cross_cats":["cs.AI"],"headline":"Generative recommenders develop severe popularity bias from token-level optimization flaws and uniform item tokenization, which Ghost corrects using asymmetric unlikelihood optimization and skeleton-founded tokenization.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T06:02:40Z","title":"Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders"},"references":{"count":48,"internal_anchors":2,"resolved_work":48,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Deep interest network for click-through rate prediction,","work_id":"fff87a5a-8e67-4b88-9795-93e8ab885c85","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Deep neural networks for youtube recommendations,","work_id":"b6151051-3638-48e9-b0e7-d852e0354625","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Deepinf: Social influence prediction with deep learning,","work_id":"ef73f8e6-b611-4cbc-9201-45955f44c50d","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Recommender systems with generative retrieval,","work_id":"5e716d32-7499-4ef1-9f7a-73dd32168954","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Adapt- ing large language models by integrating collaborative semantics for recommendation,","work_id":"e3ebcb6e-47f0-4c9c-9599-6bb481c16ada","year":2024}],"snapshot_sha256":"7075b540928e313d569e03c7127422089969394e16183963f3d154ce5e1c7504"},"source":{"id":"2605.16825","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T20:36:58.612047Z","id":"39f21910-0740-4853-9eb4-408e686847ef","model_set":{"reader":"grok-4.3"},"one_line_summary":"Ghost reduces popularity bias in generative recommenders through asymmetric unlikelihood optimization and skeleton-founded tokenization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Generative recommenders develop severe popularity bias from token-level optimization flaws and uniform item tokenization, which Ghost corrects using asymmetric unlikelihood optimization and skeleton-founded tokenization.","strongest_claim":"The severe popularity bias emerges from the confluence of a token-level optimization flaw and the undifferentiated property of item tokenization. Ghost substantially alleviates popularity bias and promotes fairer recommendations, while incurring slight degradation to the overall recommendation utility.","weakest_assumption":"The theoretical analyses correctly pinpoint the root causes of popularity bias in generative recommenders, and the proposed asymmetric unlikelihood optimization together with skeleton-founded tokenization effectively mitigate these causes without introducing new biases or requiring extensive post-hoc adjustments."}},"verdict_id":"39f21910-0740-4853-9eb4-408e686847ef"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2741b7f98339e41f390b67823c994698bf026900c51526e5dbfb49855910123","target":"record","created_at":"2026-05-20T00:03:24Z","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":"5184a92f5d0609a10357796c50d4d871d39989d238f575b13e056458448765ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T06:02:40Z","title_canon_sha256":"d46c42a553fbd03f14ece5762727663a84b0b96a3d84253fd847ef0ef9fc3438"},"schema_version":"1.0","source":{"id":"2605.16825","kind":"arxiv","version":1}},"canonical_sha256":"676cb3c46fd98a01cee160a0c492514d7660a873087c51de92f5e696d2dba7f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"676cb3c46fd98a01cee160a0c492514d7660a873087c51de92f5e696d2dba7f4","first_computed_at":"2026-05-20T00:03:24.627724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:24.627724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XHWVbjRjv6lFCbKLH9lw/+WAuXmOxHYXsKQL/uWFAnIIGMx9CJChuCABlhv0uzJyP98SA05gR6Jp6rAdHzMhBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:24.628739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2741b7f98339e41f390b67823c994698bf026900c51526e5dbfb49855910123","sha256:8b95c469a43ec5fa0ae8afbcc4c6193059ed0d74e51da37a303227f594ea2291"],"state_sha256":"45b486bae946f1aa9861731fc7719af0065c680941067a5a013e7d419f5e62c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efTxoWFQ+KhaQIna9jtKEwHzlZAnKBdVFVCsKWjXS1JWSiqdnjq7tEEes9Xjy+vV/2FGMRYfM0yD8kO8Ti4SCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T15:01:31.577745Z","bundle_sha256":"0800a0fff68e799e2af69ee6da7d4bb2098c22aabf1d5cba8c5fca53da12f14d"}}