{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NKFJJQR3XNORXBHAWAAH3TA7NL","short_pith_number":"pith:NKFJJQR3","canonical_record":{"source":{"id":"2605.16750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T02:07:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e5a0ed3bacc77a2a2e5101d5c928d18fbcd462c14c0521ab369d19d5a251215","abstract_canon_sha256":"672d31f0a103ac6a10f5af216dd7839b194e9816fbb00abd2c137bfec3b4002a"},"schema_version":"1.0"},"canonical_sha256":"6a8a94c23bbb5d1b84e0b0007dcc1f6ac727c98c219e533719ff15a6b747747d","source":{"kind":"arxiv","id":"2605.16750","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16750","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16750v1","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16750","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"NKFJJQR3XNOR","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"NKFJJQR3XNORXBHA","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"NKFJJQR3","created_at":"2026-05-20T00:03:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NKFJJQR3XNORXBHAWAAH3TA7NL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T02:07:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e5a0ed3bacc77a2a2e5101d5c928d18fbcd462c14c0521ab369d19d5a251215","abstract_canon_sha256":"672d31f0a103ac6a10f5af216dd7839b194e9816fbb00abd2c137bfec3b4002a"},"schema_version":"1.0"},"canonical_sha256":"6a8a94c23bbb5d1b84e0b0007dcc1f6ac727c98c219e533719ff15a6b747747d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:19.701731Z","signature_b64":"N6lOd8cw0uE1aNDeb0ZcqAJ+TrttuJJz+voFikDZPs2eOJVEASXNNEAlxkZnPy2qPFoxOejJzz+D/NvPfIPzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a8a94c23bbb5d1b84e0b0007dcc1f6ac727c98c219e533719ff15a6b747747d","last_reissued_at":"2026-05-20T00:03:19.699256Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:19.699256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16750","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":"2026-05-20T00:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qmja6mNrTOcHy/qhFJBntVRTbrrP+lvBWijgMMXiVFBLoTdUe033Jlg2IdsGW8Hd8kaRO2sCI6oAShcMKMMEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:30:11.416604Z"},"content_sha256":"a4e5f39e04e90ef92590f2368ae42dba1e42d73a8ba652ee9549b7068d0d7ca6","schema_version":"1.0","event_id":"sha256:a4e5f39e04e90ef92590f2368ae42dba1e42d73a8ba652ee9549b7068d0d7ca6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NKFJJQR3XNORXBHAWAAH3TA7NL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniER: A Unified Benchmark for Item-level and Path-level Exercise Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A unified benchmark shows path-level exercise recommendation consistently outperforms item-level methods across effectiveness, robustness, and sparse data conditions.","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Guiyong Zhuang, Jiapu Wang, Liangda Fang, Quanlong Guan, Shirui Pan, Xinghe Cheng, Yixin Liu, Yusheng Xie","submitted_at":"2026-05-16T02:07:58Z","abstract_excerpt":"Personalized exercise recommendation dynamically aligns pedagogical resources with individual knowledge mastery, which is crucial for satisfying students' dynamic learning needs in modern education. The field is currently driven by two dominant paradigms: Item-Level Exercise Recommendation (ILER) optimizes for immediate single-step state transitions, while Path-Level Exercise Recommendation (PLER) constructs coherent learning paths to maximize cumulative gains. Despite sharing the same ultimate objective, disparate evaluation setups have kept these two lines of research isolated, hindering uni"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through multi-dimensional analyses covering effectiveness, generalizability, robustness, and efficiency, our results reveal the systematic dominance of PLER and expose the pedagogical failure of ILER's fragmented recommendations under extreme sparsity and noise.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The four dataset generation methods produce data that faithfully reflects real student learning dynamics and that the Weighted Cognitive Gain metric correctly measures cumulative learning benefit across both single-step and multi-step recommendation paradigms.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UniER unifies ILER and PLER with the WCG metric across 9 datasets and 18 methods, showing systematic PLER superiority especially under sparsity and noise.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A unified benchmark shows path-level exercise recommendation consistently outperforms item-level methods across effectiveness, robustness, and sparse data conditions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8405e105304412a667db574d2f910e49135613c938d4563fba76ef8e493b882c"},"source":{"id":"2605.16750","kind":"arxiv","version":1},"verdict":{"id":"c9e9f1f2-0ee7-4b5c-9186-365b55faac20","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:57:20.827248Z","strongest_claim":"Through multi-dimensional analyses covering effectiveness, generalizability, robustness, and efficiency, our results reveal the systematic dominance of PLER and expose the pedagogical failure of ILER's fragmented recommendations under extreme sparsity and noise.","one_line_summary":"UniER unifies ILER and PLER with the WCG metric across 9 datasets and 18 methods, showing systematic PLER superiority especially under sparsity and noise.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The four dataset generation methods produce data that faithfully reflects real student learning dynamics and that the Weighted Cognitive Gain metric correctly measures cumulative learning benefit across both single-step and multi-step recommendation paradigms.","pith_extraction_headline":"A unified benchmark shows path-level exercise recommendation consistently outperforms item-level methods across effectiveness, robustness, and sparse data conditions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16750/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T21:11:46.072199Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.274942Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.327267Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.457895Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6cd5f9df7adc573dbf9fc15c8e26e3956d70edaf7fc8dd3bddae622fa6aebf3f"},"references":{"count":38,"sample":[{"doi":"","year":2025,"title":"NR4DER: Neural Re- ranking for Diversified Exercise Recommendation,","work_id":"f9e3676a-fe3d-4214-8257-6cdb8e6e7e97","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Exploiting Cognitive Structure for Adaptive Learning,","work_id":"2c2651c1-9ec5-40d7-808a-f43744cfe92f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Reassessing the Effectiveness of Reinforcement Learning based Recom- mender Systems for Sequential Recommendation,","work_id":"4d821193-6118-41ef-9cd9-3775a2042184","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"User-item fairness tradeoffs in recommendations,","work_id":"39c3e04f-1bd0-4242-989c-6cdbcb33f04e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation,","work_id":"371ddecd-2a6f-4f57-9aa4-0ddaede8f3f5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":38,"snapshot_sha256":"31827a2dd4b0e6f91c9d3c1ffbcc7d64b2a29e52bd9affbadda21a22f4c306b3","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"309590ba51caec6c003eb46482134ffafeb4f3335995d6d74dc6f25f8500fcbd"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c9e9f1f2-0ee7-4b5c-9186-365b55faac20"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eoJuBYXpcusUdMsdBFGR3paqvZxLsIlQJFALwjZnxEAkNHDeXEpOg1B7vmbwzCTJSqHK1t+oKdNKzSKxK63ADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:30:11.417507Z"},"content_sha256":"e81283aa2515f22f7a6950d7f30c7b5d4079f57c738610a4c6896cdd6d985b7b","schema_version":"1.0","event_id":"sha256:e81283aa2515f22f7a6950d7f30c7b5d4079f57c738610a4c6896cdd6d985b7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKFJJQR3XNORXBHAWAAH3TA7NL/bundle.json","state_url":"https://pith.science/pith/NKFJJQR3XNORXBHAWAAH3TA7NL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKFJJQR3XNORXBHAWAAH3TA7NL/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":"2026-05-27T18:30:11Z","links":{"resolver":"https://pith.science/pith/NKFJJQR3XNORXBHAWAAH3TA7NL","bundle":"https://pith.science/pith/NKFJJQR3XNORXBHAWAAH3TA7NL/bundle.json","state":"https://pith.science/pith/NKFJJQR3XNORXBHAWAAH3TA7NL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKFJJQR3XNORXBHAWAAH3TA7NL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NKFJJQR3XNORXBHAWAAH3TA7NL","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":"672d31f0a103ac6a10f5af216dd7839b194e9816fbb00abd2c137bfec3b4002a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T02:07:58Z","title_canon_sha256":"4e5a0ed3bacc77a2a2e5101d5c928d18fbcd462c14c0521ab369d19d5a251215"},"schema_version":"1.0","source":{"id":"2605.16750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16750","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16750v1","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16750","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"NKFJJQR3XNOR","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"NKFJJQR3XNORXBHA","created_at":"2026-05-20T00:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"NKFJJQR3","created_at":"2026-05-20T00:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:e81283aa2515f22f7a6950d7f30c7b5d4079f57c738610a4c6896cdd6d985b7b","target":"graph","created_at":"2026-05-20T00:03:19Z","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":"Through multi-dimensional analyses covering effectiveness, generalizability, robustness, and efficiency, our results reveal the systematic dominance of PLER and expose the pedagogical failure of ILER's fragmented recommendations under extreme sparsity and noise."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The four dataset generation methods produce data that faithfully reflects real student learning dynamics and that the Weighted Cognitive Gain metric correctly measures cumulative learning benefit across both single-step and multi-step recommendation paradigms."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"UniER unifies ILER and PLER with the WCG metric across 9 datasets and 18 methods, showing systematic PLER superiority especially under sparsity and noise."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A unified benchmark shows path-level exercise recommendation consistently outperforms item-level methods across effectiveness, robustness, and sparse data conditions."}],"snapshot_sha256":"8405e105304412a667db574d2f910e49135613c938d4563fba76ef8e493b882c"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"309590ba51caec6c003eb46482134ffafeb4f3335995d6d74dc6f25f8500fcbd"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:11:46.072199Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.274942Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.327267Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.457895Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16750/integrity.json","findings":[],"snapshot_sha256":"6cd5f9df7adc573dbf9fc15c8e26e3956d70edaf7fc8dd3bddae622fa6aebf3f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalized exercise recommendation dynamically aligns pedagogical resources with individual knowledge mastery, which is crucial for satisfying students' dynamic learning needs in modern education. The field is currently driven by two dominant paradigms: Item-Level Exercise Recommendation (ILER) optimizes for immediate single-step state transitions, while Path-Level Exercise Recommendation (PLER) constructs coherent learning paths to maximize cumulative gains. Despite sharing the same ultimate objective, disparate evaluation setups have kept these two lines of research isolated, hindering uni","authors_text":"Guiyong Zhuang, Jiapu Wang, Liangda Fang, Quanlong Guan, Shirui Pan, Xinghe Cheng, Yixin Liu, Yusheng Xie","cross_cats":["cs.AI"],"headline":"A unified benchmark shows path-level exercise recommendation consistently outperforms item-level methods across effectiveness, robustness, and sparse data conditions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T02:07:58Z","title":"UniER: A Unified Benchmark for Item-level and Path-level Exercise Recommendation"},"references":{"count":38,"internal_anchors":0,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"NR4DER: Neural Re- ranking for Diversified Exercise Recommendation,","work_id":"f9e3676a-fe3d-4214-8257-6cdb8e6e7e97","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Exploiting Cognitive Structure for Adaptive Learning,","work_id":"2c2651c1-9ec5-40d7-808a-f43744cfe92f","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Reassessing the Effectiveness of Reinforcement Learning based Recom- mender Systems for Sequential Recommendation,","work_id":"4d821193-6118-41ef-9cd9-3775a2042184","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"User-item fairness tradeoffs in recommendations,","work_id":"39c3e04f-1bd0-4242-989c-6cdbcb33f04e","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation,","work_id":"371ddecd-2a6f-4f57-9aa4-0ddaede8f3f5","year":2024}],"snapshot_sha256":"31827a2dd4b0e6f91c9d3c1ffbcc7d64b2a29e52bd9affbadda21a22f4c306b3"},"source":{"id":"2605.16750","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T20:57:20.827248Z","id":"c9e9f1f2-0ee7-4b5c-9186-365b55faac20","model_set":{"reader":"grok-4.3"},"one_line_summary":"UniER unifies ILER and PLER with the WCG metric across 9 datasets and 18 methods, showing systematic PLER superiority especially under sparsity and noise.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A unified benchmark shows path-level exercise recommendation consistently outperforms item-level methods across effectiveness, robustness, and sparse data conditions.","strongest_claim":"Through multi-dimensional analyses covering effectiveness, generalizability, robustness, and efficiency, our results reveal the systematic dominance of PLER and expose the pedagogical failure of ILER's fragmented recommendations under extreme sparsity and noise.","weakest_assumption":"The four dataset generation methods produce data that faithfully reflects real student learning dynamics and that the Weighted Cognitive Gain metric correctly measures cumulative learning benefit across both single-step and multi-step recommendation paradigms."}},"verdict_id":"c9e9f1f2-0ee7-4b5c-9186-365b55faac20"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a4e5f39e04e90ef92590f2368ae42dba1e42d73a8ba652ee9549b7068d0d7ca6","target":"record","created_at":"2026-05-20T00:03:19Z","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":"672d31f0a103ac6a10f5af216dd7839b194e9816fbb00abd2c137bfec3b4002a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-05-16T02:07:58Z","title_canon_sha256":"4e5a0ed3bacc77a2a2e5101d5c928d18fbcd462c14c0521ab369d19d5a251215"},"schema_version":"1.0","source":{"id":"2605.16750","kind":"arxiv","version":1}},"canonical_sha256":"6a8a94c23bbb5d1b84e0b0007dcc1f6ac727c98c219e533719ff15a6b747747d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a8a94c23bbb5d1b84e0b0007dcc1f6ac727c98c219e533719ff15a6b747747d","first_computed_at":"2026-05-20T00:03:19.699256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:19.699256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N6lOd8cw0uE1aNDeb0ZcqAJ+TrttuJJz+voFikDZPs2eOJVEASXNNEAlxkZnPy2qPFoxOejJzz+D/NvPfIPzBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:19.701731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4e5f39e04e90ef92590f2368ae42dba1e42d73a8ba652ee9549b7068d0d7ca6","sha256:e81283aa2515f22f7a6950d7f30c7b5d4079f57c738610a4c6896cdd6d985b7b"],"state_sha256":"5c35ae9a957e33e945eb90172b10e0a3c202998f517e19d88806a2cc3ffccdb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UY90/MbG7ciSsNRL971v0J2J3l0KpVeMIzITd+3fbXn4pdXKzC0UdH1I1JtQBSYYtbxbDzBHYuE46mrJQsCjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:30:11.422420Z","bundle_sha256":"de3ff90c4a1e1907f42b7fe631b048e85e6a7aefa5bf68083e75d6353cd6dd41"}}