{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KWFZ7LKCVDH2UJMDUDL7SIR6CL","short_pith_number":"pith:KWFZ7LKC","canonical_record":{"source":{"id":"2605.16865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T07:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"d91fa992df7169978a7e2800ca98bd851dbc95e62d7f4f7e1bb7ffd198ddadab","abstract_canon_sha256":"525996c2af35114b47f73523be53e16451c1d75fb47c025a9525adaa2e02f7bc"},"schema_version":"1.0"},"canonical_sha256":"558b9fad42a8cfaa2583a0d7f9223e12fd89bae3676dcccdca66ce398399cc8a","source":{"kind":"arxiv","id":"2605.16865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16865","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16865v1","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16865","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"KWFZ7LKCVDH2","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"KWFZ7LKCVDH2UJMD","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"KWFZ7LKC","created_at":"2026-05-20T00:03:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KWFZ7LKCVDH2UJMDUDL7SIR6CL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T07:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"d91fa992df7169978a7e2800ca98bd851dbc95e62d7f4f7e1bb7ffd198ddadab","abstract_canon_sha256":"525996c2af35114b47f73523be53e16451c1d75fb47c025a9525adaa2e02f7bc"},"schema_version":"1.0"},"canonical_sha256":"558b9fad42a8cfaa2583a0d7f9223e12fd89bae3676dcccdca66ce398399cc8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:27.144573Z","signature_b64":"6CrSWbWEjtGUt/EDt1POJyxGjTbwszPnjmGHZRD8TuEl+XDIgrbq+9cCVcpMekOeh10lTvYxErGhM1C3pcUsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"558b9fad42a8cfaa2583a0d7f9223e12fd89bae3676dcccdca66ce398399cc8a","last_reissued_at":"2026-05-20T00:03:27.143636Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:27.143636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16865","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":"2026-05-20T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cJaxBghTwJ7j9u1DI0Qbf5E092EIIjV4rtk8DuOIjp1IBPb9FfSjS6qd5wtXHO6HntR2vkdjcy6U61YeKyjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:48:02.184517Z"},"content_sha256":"aff0f0b7e708bd3b9e6f2afc94104eb00223b73df3c1be879807d25718cf0ddb","schema_version":"1.0","event_id":"sha256:aff0f0b7e708bd3b9e6f2afc94104eb00223b73df3c1be879807d25718cf0ddb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KWFZ7LKCVDH2UJMDUDL7SIR6CL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MixSD: Mixed Contextual Self-Distillation for Knowledge Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Aligning fine-tuning targets with a language model's own generation distribution prevents catastrophic forgetting of pretrained capabilities.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiarui Liu, Lechen Zhang, Mona Diab, Weihao Xuan, Yingheng Wang, Yinghui He, Yongjin Yang, Zhijing Jin","submitted_at":"2026-05-16T07:57:09Z","abstract_excerpt":"Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning targets from humans or external systems diverge from the model's autoregressive distribution, forcing the optimizer to imitate low-probability token sequences. To address this problem, we propose MixSD, a simple external-teacher-free method for distribution-aligned knowledge injection. Instead of training on fixed targets, MixSD constructs supervision dynamica"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"aligning supervision with the model's native generation distribution is a simple and effective principle for knowledge injection that mitigates catastrophic forgetting.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The mixed supervision sequences preserve the factual learning signal while remaining substantially closer to the base model's distribution, as constructed from the expert and naive conditionals.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MixSD achieves superior memorization-retention trade-off in knowledge injection by using mixed self-generated supervision from the base model's conditionals, retaining up to 100% held-out capability versus 1% for standard SFT.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Aligning fine-tuning targets with a language model's own generation distribution prevents catastrophic forgetting of pretrained capabilities.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cd18781c7d4e522cdbaf1f2cb97332840812d3a736c9e59bbe319121bc17694c"},"source":{"id":"2605.16865","kind":"arxiv","version":1},"verdict":{"id":"7a497101-b14e-42e1-aa3c-7520a45d5071","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:05:54.150137Z","strongest_claim":"aligning supervision with the model's native generation distribution is a simple and effective principle for knowledge injection that mitigates catastrophic forgetting.","one_line_summary":"MixSD achieves superior memorization-retention trade-off in knowledge injection by using mixed self-generated supervision from the base model's conditionals, retaining up to 100% held-out capability versus 1% for standard SFT.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The mixed supervision sequences preserve the factual learning signal while remaining substantially closer to the base model's distribution, as constructed from the expert and naive conditionals.","pith_extraction_headline":"Aligning fine-tuning targets with a language model's own generation distribution prevents catastrophic forgetting of pretrained capabilities."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16865/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.200037Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:11:42.647492Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.302458Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.378248Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4dd803e5858d86c45e1f57b7be76b455ed8c54b4ac246289803a1793f97a7779"},"references":{"count":57,"sample":[{"doi":"","year":null,"title":"Measuring short-form factuality in large language models","work_id":"f8e490ab-7057-43fb-8c6d-06fc603836c7","ref_index":1,"cited_arxiv_id":"2411.04368","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2502.20377 , year=","work_id":"253720f1-271f-4a18-b48e-080715a0305c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"American Invitational Mathematics Examination (AIME) 2024 , author=","work_id":"ba78ac5d-070c-4d17-be42-6859a493bb86","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","ref_index":4,"cited_arxiv_id":"2103.03874","is_internal_anchor":true},{"doi":"","year":null,"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","ref_index":5,"cited_arxiv_id":"2110.14168","is_internal_anchor":true}],"resolved_work":57,"snapshot_sha256":"d2292109ecc0ab2337125fad49a0ad4c5ebcf954b5859f9e9ef9ef74b6499a04","internal_anchors":9},"formal_canon":{"evidence_count":1,"snapshot_sha256":"dfda7bacdc5f124f8b0b270e5cc87636fe885dbe6c185e2df4a58636e523ef42"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"7a497101-b14e-42e1-aa3c-7520a45d5071"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yogumMxIJt/Tz1oliCjZsNf6wBVrt7nwyqzW1N3Gox4uL9/8KnHW9vdj+Zz7jL4iErUuCpqfQ0vO68pXm1nLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:48:02.185876Z"},"content_sha256":"56e7c1a581612e209946f50b6c13e2a93bbe6b9cb477599e98484c0d9a1ffb6e","schema_version":"1.0","event_id":"sha256:56e7c1a581612e209946f50b6c13e2a93bbe6b9cb477599e98484c0d9a1ffb6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL/bundle.json","state_url":"https://pith.science/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL/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":"2026-05-24T00:48:02Z","links":{"resolver":"https://pith.science/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL","bundle":"https://pith.science/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL/bundle.json","state":"https://pith.science/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KWFZ7LKCVDH2UJMDUDL7SIR6CL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KWFZ7LKCVDH2UJMDUDL7SIR6CL","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":"525996c2af35114b47f73523be53e16451c1d75fb47c025a9525adaa2e02f7bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T07:57:09Z","title_canon_sha256":"d91fa992df7169978a7e2800ca98bd851dbc95e62d7f4f7e1bb7ffd198ddadab"},"schema_version":"1.0","source":{"id":"2605.16865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16865","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16865v1","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16865","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"KWFZ7LKCVDH2","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"KWFZ7LKCVDH2UJMD","created_at":"2026-05-20T00:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"KWFZ7LKC","created_at":"2026-05-20T00:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:56e7c1a581612e209946f50b6c13e2a93bbe6b9cb477599e98484c0d9a1ffb6e","target":"graph","created_at":"2026-05-20T00:03:27Z","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":"aligning supervision with the model's native generation distribution is a simple and effective principle for knowledge injection that mitigates catastrophic forgetting."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The mixed supervision sequences preserve the factual learning signal while remaining substantially closer to the base model's distribution, as constructed from the expert and naive conditionals."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MixSD achieves superior memorization-retention trade-off in knowledge injection by using mixed self-generated supervision from the base model's conditionals, retaining up to 100% held-out capability versus 1% for standard SFT."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Aligning fine-tuning targets with a language model's own generation distribution prevents catastrophic forgetting of pretrained capabilities."}],"snapshot_sha256":"cd18781c7d4e522cdbaf1f2cb97332840812d3a736c9e59bbe319121bc17694c"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"dfda7bacdc5f124f8b0b270e5cc87636fe885dbe6c185e2df4a58636e523ef42"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.200037Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:11:42.647492Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.302458Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.378248Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16865/integrity.json","findings":[],"snapshot_sha256":"4dd803e5858d86c45e1f57b7be76b455ed8c54b4ac246289803a1793f97a7779","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning targets from humans or external systems diverge from the model's autoregressive distribution, forcing the optimizer to imitate low-probability token sequences. To address this problem, we propose MixSD, a simple external-teacher-free method for distribution-aligned knowledge injection. Instead of training on fixed targets, MixSD constructs supervision dynamica","authors_text":"Jiarui Liu, Lechen Zhang, Mona Diab, Weihao Xuan, Yingheng Wang, Yinghui He, Yongjin Yang, Zhijing Jin","cross_cats":[],"headline":"Aligning fine-tuning targets with a language model's own generation distribution prevents catastrophic forgetting of pretrained capabilities.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T07:57:09Z","title":"MixSD: Mixed Contextual Self-Distillation for Knowledge Injection"},"references":{"count":57,"internal_anchors":9,"resolved_work":57,"sample":[{"cited_arxiv_id":"2411.04368","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Measuring short-form factuality in large language models","work_id":"f8e490ab-7057-43fb-8c6d-06fc603836c7","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2502.20377 , year=","work_id":"253720f1-271f-4a18-b48e-080715a0305c","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"American Invitational Mathematics Examination (AIME) 2024 , author=","work_id":"ba78ac5d-070c-4d17-be42-6859a493bb86","year":2024},{"cited_arxiv_id":"2103.03874","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","year":null},{"cited_arxiv_id":"2110.14168","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":null}],"snapshot_sha256":"d2292109ecc0ab2337125fad49a0ad4c5ebcf954b5859f9e9ef9ef74b6499a04"},"source":{"id":"2605.16865","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:05:54.150137Z","id":"7a497101-b14e-42e1-aa3c-7520a45d5071","model_set":{"reader":"grok-4.3"},"one_line_summary":"MixSD achieves superior memorization-retention trade-off in knowledge injection by using mixed self-generated supervision from the base model's conditionals, retaining up to 100% held-out capability versus 1% for standard SFT.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Aligning fine-tuning targets with a language model's own generation distribution prevents catastrophic forgetting of pretrained capabilities.","strongest_claim":"aligning supervision with the model's native generation distribution is a simple and effective principle for knowledge injection that mitigates catastrophic forgetting.","weakest_assumption":"The mixed supervision sequences preserve the factual learning signal while remaining substantially closer to the base model's distribution, as constructed from the expert and naive conditionals."}},"verdict_id":"7a497101-b14e-42e1-aa3c-7520a45d5071"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aff0f0b7e708bd3b9e6f2afc94104eb00223b73df3c1be879807d25718cf0ddb","target":"record","created_at":"2026-05-20T00:03:27Z","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":"525996c2af35114b47f73523be53e16451c1d75fb47c025a9525adaa2e02f7bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T07:57:09Z","title_canon_sha256":"d91fa992df7169978a7e2800ca98bd851dbc95e62d7f4f7e1bb7ffd198ddadab"},"schema_version":"1.0","source":{"id":"2605.16865","kind":"arxiv","version":1}},"canonical_sha256":"558b9fad42a8cfaa2583a0d7f9223e12fd89bae3676dcccdca66ce398399cc8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"558b9fad42a8cfaa2583a0d7f9223e12fd89bae3676dcccdca66ce398399cc8a","first_computed_at":"2026-05-20T00:03:27.143636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:27.143636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6CrSWbWEjtGUt/EDt1POJyxGjTbwszPnjmGHZRD8TuEl+XDIgrbq+9cCVcpMekOeh10lTvYxErGhM1C3pcUsAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:27.144573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aff0f0b7e708bd3b9e6f2afc94104eb00223b73df3c1be879807d25718cf0ddb","sha256:56e7c1a581612e209946f50b6c13e2a93bbe6b9cb477599e98484c0d9a1ffb6e"],"state_sha256":"e84607d9b3d93283a238a0d5850fa1213c59fff2847c329de1e9ebe23ec972cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FfGv1CfDSFGKBBhTJby72YxV+O9MCQlEziF20etOXynsQKvXL2XR4G8QR+83MCLVn6lDnIG6QEc4SnFJd6kACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T00:48:02.191339Z","bundle_sha256":"51ff879e10c73d42097ec0d4bbfd943632473ea2ed9d90e6cdacfc4028714f15"}}