{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YIMYYIHNGO2E6M5DMR7WQM4MGE","short_pith_number":"pith:YIMYYIHN","canonical_record":{"source":{"id":"2605.17444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-17T13:29:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"031c8c3e5ebdf735586083681faccc786e1f5f9e0cb815361fb6675aecba481f","abstract_canon_sha256":"413214767acc6b2cb2cadb7eb39810c70c73388f2b1a75ec748238d21fe713c3"},"schema_version":"1.0"},"canonical_sha256":"c2198c20ed33b44f33a3647f68338c312547f3d5467d07dd5eaa6c1bfa53b94a","source":{"kind":"arxiv","id":"2605.17444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17444","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17444v1","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17444","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"YIMYYIHNGO2E","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"YIMYYIHNGO2E6M5D","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"YIMYYIHN","created_at":"2026-05-20T00:04:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YIMYYIHNGO2E6M5DMR7WQM4MGE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-17T13:29:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"031c8c3e5ebdf735586083681faccc786e1f5f9e0cb815361fb6675aecba481f","abstract_canon_sha256":"413214767acc6b2cb2cadb7eb39810c70c73388f2b1a75ec748238d21fe713c3"},"schema_version":"1.0"},"canonical_sha256":"c2198c20ed33b44f33a3647f68338c312547f3d5467d07dd5eaa6c1bfa53b94a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:39.199339Z","signature_b64":"tXi1SplKXIIBuDz+v0Ul+Vwarjp80oqXs7W/wzOrInHZuFkKTB3TheccvQ+RQ+B/KbIorL62J3hctNuioHa5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2198c20ed33b44f33a3647f68338c312547f3d5467d07dd5eaa6c1bfa53b94a","last_reissued_at":"2026-05-20T00:04:39.198116Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:39.198116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17444","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":"2026-05-20T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TD/SpCh8LASPINxMHlXryHGkkhF4uScQZ/dZUzYhcoOE0qmwgYekDJnJt3StuY+8c91SQ6BcdgFgZvOeWoYFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:53:23.096541Z"},"content_sha256":"300c2bdc9e9c09641b79fb900ef8d864d907fec29bb886eeff9578572bf27c60","schema_version":"1.0","event_id":"sha256:300c2bdc9e9c09641b79fb900ef8d864d907fec29bb886eeff9578572bf27c60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YIMYYIHNGO2E6M5DMR7WQM4MGE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MemRepair equips LLM repair agents with three persistent memory layers so they can reuse past fixes, security patterns, and refinement paths when fixing vulnerabilities across large code repositories.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Fang Liu, Li Zhang, Simiao Liu, Xiaoli Lian, Yang Liu, Yinghao Zhu","submitted_at":"2026-05-17T13:29:46Z","abstract_excerpt":"Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM)-based agents have recently shown promise for automated vulnerability repair (AVR), most existing systems still treat repair as a single generation step over the currently visible code context. As a result, they lack a persistent mechanism for reusing prior fixes or learning from failed validation attempts, which limits their effectiveness on complex, multi-file repair tasks. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MemRepair achieves state-of-the-art resolution rates of 58.0%, 58.2%, and 30.58% on SEC-Bench, PatchEval (Python, Go, JavaScript), and the C++ subset of Multi-SWE-bench, outperforming OpenHands, SWE-agent, and InfCode-C++ while maintaining competitive repair cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The three memory layers can be retrieved and applied at runtime in a manner that produces net positive gains on complex multi-file repairs without introducing retrieval errors or excessive latency that would negate the benefit.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MemRepair equips LLM repair agents with three persistent memory layers so they can reuse past fixes, security patterns, and refinement paths when fixing vulnerabilities across large code repositories.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6f3530240e5a75d1faf61851f08920cf1b6a5841db6ec539af3a42098c6656f4"},"source":{"id":"2605.17444","kind":"arxiv","version":1},"verdict":{"id":"0fab6137-e439-40f5-a434-3ca7057dcb6f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T23:02:19.533275Z","strongest_claim":"MemRepair achieves state-of-the-art resolution rates of 58.0%, 58.2%, and 30.58% on SEC-Bench, PatchEval (Python, Go, JavaScript), and the C++ subset of Multi-SWE-bench, outperforming OpenHands, SWE-agent, and InfCode-C++ while maintaining competitive repair cost.","one_line_summary":"MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The three memory layers can be retrieved and applied at runtime in a manner that produces net positive gains on complex multi-file repairs without introducing retrieval errors or excessive latency that would negate the benefit.","pith_extraction_headline":"MemRepair equips LLM repair agents with three persistent memory layers so they can reuse past fixes, security patterns, and refinement paths when fixing vulnerabilities across large code repositories."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17444/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:19.953820Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:12:25.591109Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.719657Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.670465Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fcd5e1ce8fbd65ae08b78f7b06783f076cabdb02ab635b25f93390e1e0102741"},"references":{"count":60,"sample":[{"doi":"","year":2026,"title":"Common Weakness Enumeration","work_id":"0a2de53a-f5e1-46ce-97e6-d3b761051f6f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"National Vulnerability Database (NVD)","work_id":"150306d9-2fd8-4b89-af98-19304828da3c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Aider. 2024. Introducing Aider. https://aider.chat/ Accessed: 2026-01-15","work_id":"072c399f-2f5a-4b18-8bad-83460c95338d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3390/make7040149","year":2025,"title":"Alfred Asare Amoah and Yan Liu. 2025. Explainable Recommendation of Soft- ware Vulnerability Repair Based on Metadata Retrieval and Multifaceted LLMs. Machine Learning and Knowledge Extraction7, 4 (20","work_id":"6306e8e0-11a6-48ad-86f8-9e997c237ddd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Guru Bhandari, Amara Naseer, and Leon Moonen. 2021. CVEfixes: automated collection of vulnerabilities and their fixes from open-source software. InProceed- ings of the 17th International Conference on","work_id":"086c9a03-3f63-40f3-8671-d581a89b9087","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"e37a6a5945851af7040c9bc02a68ea0df2010ad523ea64f7884476df647ddda8","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a01e10d50d4b9d159e219d3a1ead4f50b0e98fc7d548892ab8c6bf52e84b459e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0fab6137-e439-40f5-a434-3ca7057dcb6f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcTZyVQuiiJamBz2M7L6BQ1WQje7+ZmrExw/mAc1mRtid40OsJ4ShE6zybM6sWrG/Z7wjVu5b2m2tkKSg5wqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:53:23.097750Z"},"content_sha256":"2ead8a8acd64d9e1ecd7d08048dc70fbc720a62408b3977046ba19aab8007d71","schema_version":"1.0","event_id":"sha256:2ead8a8acd64d9e1ecd7d08048dc70fbc720a62408b3977046ba19aab8007d71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE/bundle.json","state_url":"https://pith.science/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE/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":"2026-05-20T22:53:23Z","links":{"resolver":"https://pith.science/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE","bundle":"https://pith.science/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE/bundle.json","state":"https://pith.science/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIMYYIHNGO2E6M5DMR7WQM4MGE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YIMYYIHNGO2E6M5DMR7WQM4MGE","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":"413214767acc6b2cb2cadb7eb39810c70c73388f2b1a75ec748238d21fe713c3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-17T13:29:46Z","title_canon_sha256":"031c8c3e5ebdf735586083681faccc786e1f5f9e0cb815361fb6675aecba481f"},"schema_version":"1.0","source":{"id":"2605.17444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17444","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17444v1","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17444","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"YIMYYIHNGO2E","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"YIMYYIHNGO2E6M5D","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"YIMYYIHN","created_at":"2026-05-20T00:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:2ead8a8acd64d9e1ecd7d08048dc70fbc720a62408b3977046ba19aab8007d71","target":"graph","created_at":"2026-05-20T00:04:39Z","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":"MemRepair achieves state-of-the-art resolution rates of 58.0%, 58.2%, and 30.58% on SEC-Bench, PatchEval (Python, Go, JavaScript), and the C++ subset of Multi-SWE-bench, outperforming OpenHands, SWE-agent, and InfCode-C++ while maintaining competitive repair cost."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The three memory layers can be retrieved and applied at runtime in a manner that produces net positive gains on complex multi-file repairs without introducing retrieval errors or excessive latency that would negate the benefit."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MemRepair equips LLM repair agents with three persistent memory layers so they can reuse past fixes, security patterns, and refinement paths when fixing vulnerabilities across large code repositories."}],"snapshot_sha256":"6f3530240e5a75d1faf61851f08920cf1b6a5841db6ec539af3a42098c6656f4"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a01e10d50d4b9d159e219d3a1ead4f50b0e98fc7d548892ab8c6bf52e84b459e"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:19.953820Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:12:25.591109Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.719657Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.670465Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17444/integrity.json","findings":[],"snapshot_sha256":"fcd5e1ce8fbd65ae08b78f7b06783f076cabdb02ab635b25f93390e1e0102741","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM)-based agents have recently shown promise for automated vulnerability repair (AVR), most existing systems still treat repair as a single generation step over the currently visible code context. As a result, they lack a persistent mechanism for reusing prior fixes or learning from failed validation attempts, which limits their effectiveness on complex, multi-file repair tasks. ","authors_text":"Fang Liu, Li Zhang, Simiao Liu, Xiaoli Lian, Yang Liu, Yinghao Zhu","cross_cats":["cs.AI","cs.CL"],"headline":"MemRepair equips LLM repair agents with three persistent memory layers so they can reuse past fixes, security patterns, and refinement paths when fixing vulnerabilities across large code repositories.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-17T13:29:46Z","title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair"},"references":{"count":60,"internal_anchors":7,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Common Weakness Enumeration","work_id":"0a2de53a-f5e1-46ce-97e6-d3b761051f6f","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"National Vulnerability Database (NVD)","work_id":"150306d9-2fd8-4b89-af98-19304828da3c","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Aider. 2024. Introducing Aider. https://aider.chat/ Accessed: 2026-01-15","work_id":"072c399f-2f5a-4b18-8bad-83460c95338d","year":2024},{"cited_arxiv_id":"","doi":"10.3390/make7040149","is_internal_anchor":false,"ref_index":4,"title":"Alfred Asare Amoah and Yan Liu. 2025. Explainable Recommendation of Soft- ware Vulnerability Repair Based on Metadata Retrieval and Multifaceted LLMs. Machine Learning and Knowledge Extraction7, 4 (20","work_id":"6306e8e0-11a6-48ad-86f8-9e997c237ddd","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Guru Bhandari, Amara Naseer, and Leon Moonen. 2021. CVEfixes: automated collection of vulnerabilities and their fixes from open-source software. InProceed- ings of the 17th International Conference on","work_id":"086c9a03-3f63-40f3-8671-d581a89b9087","year":2021}],"snapshot_sha256":"e37a6a5945851af7040c9bc02a68ea0df2010ad523ea64f7884476df647ddda8"},"source":{"id":"2605.17444","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:02:19.533275Z","id":"0fab6137-e439-40f5-a434-3ca7057dcb6f","model_set":{"reader":"grok-4.3"},"one_line_summary":"MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MemRepair equips LLM repair agents with three persistent memory layers so they can reuse past fixes, security patterns, and refinement paths when fixing vulnerabilities across large code repositories.","strongest_claim":"MemRepair achieves state-of-the-art resolution rates of 58.0%, 58.2%, and 30.58% on SEC-Bench, PatchEval (Python, Go, JavaScript), and the C++ subset of Multi-SWE-bench, outperforming OpenHands, SWE-agent, and InfCode-C++ while maintaining competitive repair cost.","weakest_assumption":"The three memory layers can be retrieved and applied at runtime in a manner that produces net positive gains on complex multi-file repairs without introducing retrieval errors or excessive latency that would negate the benefit."}},"verdict_id":"0fab6137-e439-40f5-a434-3ca7057dcb6f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:300c2bdc9e9c09641b79fb900ef8d864d907fec29bb886eeff9578572bf27c60","target":"record","created_at":"2026-05-20T00:04:39Z","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":"413214767acc6b2cb2cadb7eb39810c70c73388f2b1a75ec748238d21fe713c3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-17T13:29:46Z","title_canon_sha256":"031c8c3e5ebdf735586083681faccc786e1f5f9e0cb815361fb6675aecba481f"},"schema_version":"1.0","source":{"id":"2605.17444","kind":"arxiv","version":1}},"canonical_sha256":"c2198c20ed33b44f33a3647f68338c312547f3d5467d07dd5eaa6c1bfa53b94a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2198c20ed33b44f33a3647f68338c312547f3d5467d07dd5eaa6c1bfa53b94a","first_computed_at":"2026-05-20T00:04:39.198116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:39.198116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tXi1SplKXIIBuDz+v0Ul+Vwarjp80oqXs7W/wzOrInHZuFkKTB3TheccvQ+RQ+B/KbIorL62J3hctNuioHa5Bw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:39.199339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:300c2bdc9e9c09641b79fb900ef8d864d907fec29bb886eeff9578572bf27c60","sha256:2ead8a8acd64d9e1ecd7d08048dc70fbc720a62408b3977046ba19aab8007d71"],"state_sha256":"6f0c327c76ed1490b31d990428813c5baea7b4f6c8194c1915095c43ee82db2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxS37S139d+s/1WNgSKWqpnQMRcuJrlR3zPRN7Pc6yG+zpXYIq9z6gABhBtOwf57U15TSEHIzhsMa9psUYOHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T22:53:23.103260Z","bundle_sha256":"cf619f23da74d96f3d6312cd74fd4ab4e5b8bef2fecdf6aa68b7dfd8d95de707"}}