{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SPRZFPCVGD7CGFD2YDZTOSG6VP","short_pith_number":"pith:SPRZFPCV","canonical_record":{"source":{"id":"2104.08663","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-04-17T23:29:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eff90d01865de86a1111fe3b12bc151e9232bce96af744c034df9e46e1ae06cd","abstract_canon_sha256":"1fd562a991a8991536de793d8cf58f04b93e2e9f72c665030905a21657661fdb"},"schema_version":"1.0"},"canonical_sha256":"93e392bc5530fe23147ac0f33748deabf975c816f03c8931b8bfa0fdd46c18cd","source":{"kind":"arxiv","id":"2104.08663","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08663","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08663v4","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08663","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"SPRZFPCVGD7C","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"SPRZFPCVGD7CGFD2","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"SPRZFPCV","created_at":"2026-07-05T03:24:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SPRZFPCVGD7CGFD2YDZTOSG6VP","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08663","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-04-17T23:29:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eff90d01865de86a1111fe3b12bc151e9232bce96af744c034df9e46e1ae06cd","abstract_canon_sha256":"1fd562a991a8991536de793d8cf58f04b93e2e9f72c665030905a21657661fdb"},"schema_version":"1.0"},"canonical_sha256":"93e392bc5530fe23147ac0f33748deabf975c816f03c8931b8bfa0fdd46c18cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:29.177544Z","signature_b64":"rtD5h8DQrcYcTmLMMmjMw9I5HrCUPw6oOH6+XeZA5eBmgdX/DTA5rf9MH39ZbKv52wyZitQTUkH3vkGy703JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e392bc5530fe23147ac0f33748deabf975c816f03c8931b8bfa0fdd46c18cd","last_reissued_at":"2026-07-05T03:24:29.177026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:29.177026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08663","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMcOBgwuJRwUquNigdWa/Av2qadgOTor+CcO6Lr0QPhZlbHPdfg2kcJNVqeJixRP36vf6uh7VDvpwSsxuwCSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T22:01:39.252680Z"},"content_sha256":"2f3fbd846e9ba46814ee80aafdcbe14cbe614de198d8d044d4af00ec7621f1fe","schema_version":"1.0","event_id":"sha256:2f3fbd846e9ba46814ee80aafdcbe14cbe614de198d8d044d4af00ec7621f1fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SPRZFPCVGD7CGFD2YDZTOSG6VP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A benchmark with 18 diverse datasets shows BM25 as a robust zero-shot baseline while re-ranking models lead in performance at higher cost.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Abhishek Srivastava, Andreas R\\\"uckl\\'e, Iryna Gurevych, Nandan Thakur, Nils Reimers","submitted_at":"2021-04-17T23:29:55Z","abstract_excerpt":"Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of-distribution (OOD) generalization capabilities. To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval. We leverage a careful selection of 18 publicly available datasets from diverse text retrieval tasks and domains and evaluate 10 state-of-the-art retrieval systems includi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 18 selected datasets provide a sufficiently heterogeneous and representative sample of out-of-distribution scenarios to draw general conclusions about model generalization in information retrieval.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"BEIR is a heterogeneous zero-shot benchmark showing BM25 as a robust baseline while re-ranking and late-interaction models perform best on average at higher cost, with dense and sparse models lagging in generalization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A benchmark with 18 diverse datasets shows BM25 as a robust zero-shot baseline while re-ranking models lead in performance at higher cost.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c8c5486d65b59f6abd205fc193c2546ab52f251a8c9211c93e46e83dfb64620a"},"source":{"id":"2104.08663","kind":"arxiv","version":4},"verdict":{"id":"96c48c26-5450-4830-9dd1-725c1bcf2020","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T14:35:26.616158Z","strongest_claim":"Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches.","one_line_summary":"BEIR is a heterogeneous zero-shot benchmark showing BM25 as a robust baseline while re-ranking and late-interaction models perform best on average at higher cost, with dense and sparse models lagging in generalization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 18 selected datasets provide a sufficiently heterogeneous and representative sample of out-of-distribution scenarios to draw general conclusions about model generalization in information retrieval.","pith_extraction_headline":"A benchmark with 18 diverse datasets shows BM25 as a robust zero-shot baseline while re-ranking models lead in performance at higher cost."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.08663/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":94,"sample":[{"doi":"","year":2019,"title":"Amin Ahmad, Noah Constant, Yinfei Yang, and Daniel Cer. 2019. ReQA: An Evaluation for End-to-End Answer Retrieval Models. InProceedings of the 2nd Workshop on Machine Reading for Question Answering, p","work_id":"5d0113a3-6e54-41bc-b4c0-6c8692485ea0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Akari Asai, Jungo Kasai, Jonathan Clark, Kenton Lee, Eunsol Choi, and Hannaneh Hajishirzi","work_id":"6da63d05-546b-4e55-b023-a4f551c20f18","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguis- tics: Human Language Technologies, pages 547–564, Online","work_id":"9df27e51-690e-449e-a906-b69d6e0b3dce","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Petr Baudiš and Jan Šediv `y. 2015. Modeling of the question answering task in the yodaqa system. In International Conference of the Cross-Language Evaluation Forum for European Languages, pages 222–2","work_id":"6d514303-9ae8-4f7f-81e7-1f9ba1b352d2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic Parsing on Freebase from Question-Answer Pairs. In Proceedings of the 2013 Conference on Empiri- cal Methods in Natural Langu","work_id":"a75402fc-378a-4306-95ce-99b8fe6087b9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":94,"snapshot_sha256":"b1341d9084d08791920925d03692a5cb3bcde1535bbacca8d41c47bdb9d36331","internal_anchors":2},"formal_canon":{"evidence_count":1,"snapshot_sha256":"9ebd7936b407744ce6e0bc8bbb449774aee4d74c233f913afa29e29a412518b8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"96c48c26-5450-4830-9dd1-725c1bcf2020"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gOk9GA9ITZtMNPagqTr5rPNozNhv2nbDPyPlUbsLRnM56rWMCmn0/BtmIaNiGFNo2wOCU3y4BEFf+p0qqT+sAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T22:01:39.253272Z"},"content_sha256":"7063d94a5ac7349c877b8f65f9eb6293fd2ce3be3ae9ba6a986ca24230428415","schema_version":"1.0","event_id":"sha256:7063d94a5ac7349c877b8f65f9eb6293fd2ce3be3ae9ba6a986ca24230428415"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP/bundle.json","state_url":"https://pith.science/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP/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":"2026-07-06T22:01:39Z","links":{"resolver":"https://pith.science/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP","bundle":"https://pith.science/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP/bundle.json","state":"https://pith.science/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SPRZFPCVGD7CGFD2YDZTOSG6VP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SPRZFPCVGD7CGFD2YDZTOSG6VP","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":"1fd562a991a8991536de793d8cf58f04b93e2e9f72c665030905a21657661fdb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-04-17T23:29:55Z","title_canon_sha256":"eff90d01865de86a1111fe3b12bc151e9232bce96af744c034df9e46e1ae06cd"},"schema_version":"1.0","source":{"id":"2104.08663","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08663","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08663v4","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08663","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"SPRZFPCVGD7C","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"SPRZFPCVGD7CGFD2","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"SPRZFPCV","created_at":"2026-07-05T03:24:29Z"}],"graph_snapshots":[{"event_id":"sha256:7063d94a5ac7349c877b8f65f9eb6293fd2ce3be3ae9ba6a986ca24230428415","target":"graph","created_at":"2026-07-05T03:24:29Z","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":"Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 18 selected datasets provide a sufficiently heterogeneous and representative sample of out-of-distribution scenarios to draw general conclusions about model generalization in information retrieval."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"BEIR is a heterogeneous zero-shot benchmark showing BM25 as a robust baseline while re-ranking and late-interaction models perform best on average at higher cost, with dense and sparse models lagging in generalization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A benchmark with 18 diverse datasets shows BM25 as a robust zero-shot baseline while re-ranking models lead in performance at higher cost."}],"snapshot_sha256":"c8c5486d65b59f6abd205fc193c2546ab52f251a8c9211c93e46e83dfb64620a"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"9ebd7936b407744ce6e0bc8bbb449774aee4d74c233f913afa29e29a412518b8"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.08663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing neural information retrieval (IR) models have often been studied in homogeneous and narrow settings, which has considerably limited insights into their out-of-distribution (OOD) generalization capabilities. To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval. We leverage a careful selection of 18 publicly available datasets from diverse text retrieval tasks and domains and evaluate 10 state-of-the-art retrieval systems includi","authors_text":"Abhishek Srivastava, Andreas R\\\"uckl\\'e, Iryna Gurevych, Nandan Thakur, Nils Reimers","cross_cats":["cs.AI","cs.CL"],"headline":"A benchmark with 18 diverse datasets shows BM25 as a robust zero-shot baseline while re-ranking models lead in performance at higher cost.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-04-17T23:29:55Z","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models"},"references":{"count":94,"internal_anchors":2,"resolved_work":94,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Amin Ahmad, Noah Constant, Yinfei Yang, and Daniel Cer. 2019. ReQA: An Evaluation for End-to-End Answer Retrieval Models. InProceedings of the 2nd Workshop on Machine Reading for Question Answering, p","work_id":"5d0113a3-6e54-41bc-b4c0-6c8692485ea0","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Akari Asai, Jungo Kasai, Jonathan Clark, Kenton Lee, Eunsol Choi, and Hannaneh Hajishirzi","work_id":"6da63d05-546b-4e55-b023-a4f551c20f18","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguis- tics: Human Language Technologies, pages 547–564, Online","work_id":"9df27e51-690e-449e-a906-b69d6e0b3dce","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Petr Baudiš and Jan Šediv `y. 2015. Modeling of the question answering task in the yodaqa system. In International Conference of the Cross-Language Evaluation Forum for European Languages, pages 222–2","work_id":"6d514303-9ae8-4f7f-81e7-1f9ba1b352d2","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic Parsing on Freebase from Question-Answer Pairs. In Proceedings of the 2013 Conference on Empiri- cal Methods in Natural Langu","work_id":"a75402fc-378a-4306-95ce-99b8fe6087b9","year":2013}],"snapshot_sha256":"b1341d9084d08791920925d03692a5cb3bcde1535bbacca8d41c47bdb9d36331"},"source":{"id":"2104.08663","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-12T14:35:26.616158Z","id":"96c48c26-5450-4830-9dd1-725c1bcf2020","model_set":{"reader":"grok-4.3"},"one_line_summary":"BEIR is a heterogeneous zero-shot benchmark showing BM25 as a robust baseline while re-ranking and late-interaction models perform best on average at higher cost, with dense and sparse models lagging in generalization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A benchmark with 18 diverse datasets shows BM25 as a robust zero-shot baseline while re-ranking models lead in performance at higher cost.","strongest_claim":"Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs. In contrast, dense and sparse-retrieval models are computationally more efficient but often underperform other approaches.","weakest_assumption":"The 18 selected datasets provide a sufficiently heterogeneous and representative sample of out-of-distribution scenarios to draw general conclusions about model generalization in information retrieval."}},"verdict_id":"96c48c26-5450-4830-9dd1-725c1bcf2020"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f3fbd846e9ba46814ee80aafdcbe14cbe614de198d8d044d4af00ec7621f1fe","target":"record","created_at":"2026-07-05T03:24:29Z","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":"1fd562a991a8991536de793d8cf58f04b93e2e9f72c665030905a21657661fdb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-04-17T23:29:55Z","title_canon_sha256":"eff90d01865de86a1111fe3b12bc151e9232bce96af744c034df9e46e1ae06cd"},"schema_version":"1.0","source":{"id":"2104.08663","kind":"arxiv","version":4}},"canonical_sha256":"93e392bc5530fe23147ac0f33748deabf975c816f03c8931b8bfa0fdd46c18cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93e392bc5530fe23147ac0f33748deabf975c816f03c8931b8bfa0fdd46c18cd","first_computed_at":"2026-07-05T03:24:29.177026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:29.177026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtD5h8DQrcYcTmLMMmjMw9I5HrCUPw6oOH6+XeZA5eBmgdX/DTA5rf9MH39ZbKv52wyZitQTUkH3vkGy703JAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:29.177544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08663","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f3fbd846e9ba46814ee80aafdcbe14cbe614de198d8d044d4af00ec7621f1fe","sha256:7063d94a5ac7349c877b8f65f9eb6293fd2ce3be3ae9ba6a986ca24230428415"],"state_sha256":"9c1c4aeefa8de65b762454cafc1412d355abc43f69eb0d299b01dba6a4b25a2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6o5lHxHsEJHYquqakVYYSuHsCFiRbrGdvvjHchMx7+rekCevWNXZm8K8tW6bpI6pA8FRyM9zVe2E7ceB7e5JBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T22:01:39.255746Z","bundle_sha256":"6a63d5d931244c97639d5746a0841b05d56bb2ef1d92c0f3c31eb6dcd977a34b"}}