{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LRYPOV6GKFZKCVQ7DLOLENAJXD","short_pith_number":"pith:LRYPOV6G","canonical_record":{"source":{"id":"2605.15156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:51:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cd6ce2f1a7fc1a5ed18488a41b28cb6182d5e90cffaf86c28e62050de8efb577","abstract_canon_sha256":"4511675e7d58b801544f6e7768af3f8c6f11125fead76befb43a5284f634ae01"},"schema_version":"1.0"},"canonical_sha256":"5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6","source":{"kind":"arxiv","id":"2605.15156","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15156","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15156v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"LRYPOV6GKFZK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LRYPOV6GKFZKCVQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LRYPOV6G","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LRYPOV6GKFZKCVQ7DLOLENAJXD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:51:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cd6ce2f1a7fc1a5ed18488a41b28cb6182d5e90cffaf86c28e62050de8efb577","abstract_canon_sha256":"4511675e7d58b801544f6e7768af3f8c6f11125fead76befb43a5284f634ae01"},"schema_version":"1.0"},"canonical_sha256":"5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6","last_reissued_at":"2026-05-17T21:57:18.760051Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.437468Z"},"source_kind":"arxiv","source_id":"2605.15156","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":"2026-05-17T21:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11qibNz/Kz25HBo5JrFN8yslLq9EJ8T2lHTDd1VCPo2GV6tJoasBPov/YBIIdVxegOlscfqcKOMmaDt6wRHoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:11:35.968677Z"},"content_sha256":"7595952c57b0cf3667d13e53fafbe24dd54185176626dd77e066e1923cace0aa","schema_version":"1.0","event_id":"sha256:7595952c57b0cf3667d13e53fafbe24dd54185176626dd77e066e1923cace0aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LRYPOV6GKFZKCVQ7DLOLENAJXD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MeMo: Memory as a Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alfred Wei Lun Leong, Alok Prakash, Armando Solar-Lezama, Arun Verma, Bryan Kian Hsiang Low, Daniela Rus, Nancy F. Chen, Ryan Wei Heng Quek, Sanghyuk Lee","submitted_at":"2026-05-14T17:51:34Z","abstract_excerpt":"Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the need for efficient mechanisms to incorporate new knowledge. In this paper, we introduce MeMo (Memory as a Model), a modular framework that encodes new knowledge into a dedicated memory model while keeping the LLM parameters unchanged. Compared to existing methods, MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is ro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is robust to retrieval noise, (c) it avoids catastrophic forgetting in the LLM, (d) it does not require access to the LLM's weights or output logits, enabling plug-and-play integration with both open and proprietary closed-source LLMs, and (e) its retrieval cost is independent of corpus size at inference time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that a dedicated memory model can reliably encode and retrieve complex cross-document knowledge without any access to the LLM's internal weights or logits, and that this separation delivers the claimed robustness and performance gains on the tested benchmarks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MeMo encodes new knowledge into a separate memory model for frozen LLMs, achieving strong performance on BrowseComp-Plus, NarrativeQA, and MuSiQue while capturing cross-document relationships and remaining robust to retrieval noise.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ab2859af8db3917a11ea161db29352d9eddbe8f29a28ea0c4a832d2f94339724"},"source":{"id":"2605.15156","kind":"arxiv","version":1},"verdict":{"id":"90e5bd7a-2250-48e7-be1f-0ccd347caa32","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:13:50.182875Z","strongest_claim":"MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is robust to retrieval noise, (c) it avoids catastrophic forgetting in the LLM, (d) it does not require access to the LLM's weights or output logits, enabling plug-and-play integration with both open and proprietary closed-source LLMs, and (e) its retrieval cost is independent of corpus size at inference time.","one_line_summary":"MeMo encodes new knowledge into a separate memory model for frozen LLMs, achieving strong performance on BrowseComp-Plus, NarrativeQA, and MuSiQue while capturing cross-document relationships and remaining robust to retrieval noise.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that a dedicated memory model can reliably encode and retrieve complex cross-document knowledge without any access to the LLM's internal weights or logits, and that this separation delivers the claimed robustness and performance gains on the tested benchmarks.","pith_extraction_headline":"A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining."},"references":{"count":85,"sample":[{"doi":"","year":2023,"title":"Large Language Models are Zero-Shot Reasoners","work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","ref_index":1,"cited_arxiv_id":"2205.11916","is_internal_anchor":true},{"doi":"","year":2023,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","ref_index":2,"cited_arxiv_id":"2303.18223","is_internal_anchor":true},{"doi":"","year":2026,"title":"A survey on large language models for code generation.ACM Transactions on Software Engineering and Method- ology, 2026","work_id":"9e752029-4f11-4a0f-a918-aedb44fc00da","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Knowledge conflicts for LLMs : A survey","work_id":"a30cb4d9-a131-445a-b97a-24ff0c3eec9a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Dated data: Tracing knowledge cutoffs in large language models","work_id":"42f5f09c-2a88-48ad-bf87-387d0cac0d06","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":85,"snapshot_sha256":"9b3c22349b0707e872c441c3bc9b2318e36d142051ac8515abad153dcbab3423","internal_anchors":17},"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":"90e5bd7a-2250-48e7-be1f-0ccd347caa32"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQKpYpQmXu94YOfRzhsmmC9rcVXcSFWWTiclZMLmCB1QWRk8K8iMqJKfX58pIvQJ8pWj38URKcoYOdprelRCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:11:35.969692Z"},"content_sha256":"cc2059461857d25f8cdac42ce61f2294ed4b22ddf69d7976a65419fa075d3608","schema_version":"1.0","event_id":"sha256:cc2059461857d25f8cdac42ce61f2294ed4b22ddf69d7976a65419fa075d3608"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:LRYPOV6GKFZKCVQ7DLOLENAJXD","target":"integrity","payload":{"note":"URL 'https://storage.googleapis.com/' returned status 400 (Bad Request) at last check.","snippet":null,"arxiv_id":"2605.15156","detector":"external_links","evidence":{"url":"https://storage.googleapis.com/","final_url":"https://storage.googleapis.com/","host_kind":"website","status_code":400,"status_text":"Bad Request","verdict_class":"incontrovertible","checked_at_unix":1779190415.1447818},"severity":"advisory","ref_index":null,"audited_at":"2026-05-19T11:33:35.688842Z","event_type":"pith.integrity.v1","detected_doi":null,"detector_url":"https://pith.science/pith-integrity-protocol#external_links","external_url":"https://storage.googleapis.com/","finding_type":"dead_url","evidence_hash":"6f4cd50299f716a35a2b0f6295f6109d011f62f8fae78af17b79fa55edb159d7","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1101,"payload_sha256":"5ff55985e737728cc5f1159a6bb6c9fae404256e14fa62cafa21ad10b1c25735","signature_b64":"egW+YNECiCSib35MLKrNCP20lPf7aEfTqBazhKcPUCAkVI8MJmN2J9OX/Ln6wNqiH8tLCUrweKopmW7HCfn/Dw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T11:37:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNuXWOkCdTWWNEL+igfmZOd/v+V9DrGGu8krgTNovA6RFjkuidQKaeMFSY4cSsWC3cK6Y1FkBx91THwHAX1yBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:11:35.970935Z"},"content_sha256":"96121a481b9786f1cbff991f86e0b68b4959c073c5b484df721ed11eec7ec53c","schema_version":"1.0","event_id":"sha256:96121a481b9786f1cbff991f86e0b68b4959c073c5b484df721ed11eec7ec53c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD/bundle.json","state_url":"https://pith.science/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD/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":"2026-05-21T14:11:35Z","links":{"resolver":"https://pith.science/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD","bundle":"https://pith.science/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD/bundle.json","state":"https://pith.science/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRYPOV6GKFZKCVQ7DLOLENAJXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LRYPOV6GKFZKCVQ7DLOLENAJXD","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4511675e7d58b801544f6e7768af3f8c6f11125fead76befb43a5284f634ae01","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:51:34Z","title_canon_sha256":"cd6ce2f1a7fc1a5ed18488a41b28cb6182d5e90cffaf86c28e62050de8efb577"},"schema_version":"1.0","source":{"id":"2605.15156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15156","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15156v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"LRYPOV6GKFZK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LRYPOV6GKFZKCVQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LRYPOV6G","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cc2059461857d25f8cdac42ce61f2294ed4b22ddf69d7976a65419fa075d3608","target":"graph","created_at":"2026-05-17T21:57:18Z","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":"MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is robust to retrieval noise, (c) it avoids catastrophic forgetting in the LLM, (d) it does not require access to the LLM's weights or output logits, enabling plug-and-play integration with both open and proprietary closed-source LLMs, and (e) its retrieval cost is independent of corpus size at inference time."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that a dedicated memory model can reliably encode and retrieve complex cross-document knowledge without any access to the LLM's internal weights or logits, and that this separation delivers the claimed robustness and performance gains on the tested benchmarks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MeMo encodes new knowledge into a separate memory model for frozen LLMs, achieving strong performance on BrowseComp-Plus, NarrativeQA, and MuSiQue while capturing cross-document relationships and remaining robust to retrieval noise."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining."}],"snapshot_sha256":"ab2859af8db3917a11ea161db29352d9eddbe8f29a28ea0c4a832d2f94339724"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the need for efficient mechanisms to incorporate new knowledge. In this paper, we introduce MeMo (Memory as a Model), a modular framework that encodes new knowledge into a dedicated memory model while keeping the LLM parameters unchanged. Compared to existing methods, MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is ro","authors_text":"Alfred Wei Lun Leong, Alok Prakash, Armando Solar-Lezama, Arun Verma, Bryan Kian Hsiang Low, Daniela Rus, Nancy F. Chen, Ryan Wei Heng Quek, Sanghyuk Lee","cross_cats":["cs.AI","cs.LG"],"headline":"A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:51:34Z","title":"MeMo: Memory as a Model"},"references":{"count":85,"internal_anchors":17,"resolved_work":85,"sample":[{"cited_arxiv_id":"2205.11916","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Large Language Models are Zero-Shot Reasoners","work_id":"d9b7eb1a-7165-46ff-9f06-d2f0b9d6f95d","year":2023},{"cited_arxiv_id":"2303.18223","doi":"","is_internal_anchor":true,"ref_index":2,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A survey on large language models for code generation.ACM Transactions on Software Engineering and Method- ology, 2026","work_id":"9e752029-4f11-4a0f-a918-aedb44fc00da","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Knowledge conflicts for LLMs : A survey","work_id":"a30cb4d9-a131-445a-b97a-24ff0c3eec9a","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Dated data: Tracing knowledge cutoffs in large language models","work_id":"42f5f09c-2a88-48ad-bf87-387d0cac0d06","year":2024}],"snapshot_sha256":"9b3c22349b0707e872c441c3bc9b2318e36d142051ac8515abad153dcbab3423"},"source":{"id":"2605.15156","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:13:50.182875Z","id":"90e5bd7a-2250-48e7-be1f-0ccd347caa32","model_set":{"reader":"grok-4.3"},"one_line_summary":"MeMo encodes new knowledge into a separate memory model for frozen LLMs, achieving strong performance on BrowseComp-Plus, NarrativeQA, and MuSiQue while capturing cross-document relationships and remaining robust to retrieval noise.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A dedicated memory model encodes new knowledge so LLMs can use it without changing parameters or retraining.","strongest_claim":"MeMo offers several advantages: (a) it captures complex cross-document relationships, (b) it is robust to retrieval noise, (c) it avoids catastrophic forgetting in the LLM, (d) it does not require access to the LLM's weights or output logits, enabling plug-and-play integration with both open and proprietary closed-source LLMs, and (e) its retrieval cost is independent of corpus size at inference time.","weakest_assumption":"The assumption that a dedicated memory model can reliably encode and retrieve complex cross-document knowledge without any access to the LLM's internal weights or logits, and that this separation delivers the claimed robustness and performance gains on the tested benchmarks."}},"verdict_id":"90e5bd7a-2250-48e7-be1f-0ccd347caa32"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7595952c57b0cf3667d13e53fafbe24dd54185176626dd77e066e1923cace0aa","target":"record","created_at":"2026-05-17T21:18:33Z","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":"4511675e7d58b801544f6e7768af3f8c6f11125fead76befb43a5284f634ae01","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:51:34Z","title_canon_sha256":"cd6ce2f1a7fc1a5ed18488a41b28cb6182d5e90cffaf86c28e62050de8efb577"},"schema_version":"1.0","source":{"id":"2605.15156","kind":"arxiv","version":1}},"canonical_sha256":"5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c70f757c65172a1561f1adcb23409b8de092099ac8dfe652bfde395b50341e6","first_computed_at":"2026-05-17T21:40:25.437468Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:18.760051Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7595952c57b0cf3667d13e53fafbe24dd54185176626dd77e066e1923cace0aa","sha256:cc2059461857d25f8cdac42ce61f2294ed4b22ddf69d7976a65419fa075d3608","sha256:96121a481b9786f1cbff991f86e0b68b4959c073c5b484df721ed11eec7ec53c"],"state_sha256":"4f522a1c78d938de1c610498cfbc4b892c0cc51d9971fc077c85896f990a2054"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6/UxMdAblnVWO0diNTlGzDxDwe8oVKVW/+gUkkLs0XqCHV+l7PTvAf04nqsJxCY5ysF0Q1tB0UIJJ5ZBmhnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T14:11:35.974858Z","bundle_sha256":"fd8fe894ae6cab1d84db7bdf251fb320b4025b76386bf53002cd9189d826bf3a"}}