{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:URSNDDDQZODJVNCAIOQO6TBQP7","short_pith_number":"pith:URSNDDDQ","canonical_record":{"source":{"id":"2605.12483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:57:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49c215ec67f8dcbf3197b08cf6dc71c97317ce38431a7d9b5787242c65a18466","abstract_canon_sha256":"25c163c0ee0c1fd8e36b6a83351eb068b56d1735f62dec0a11da2c45c2d631a0"},"schema_version":"1.0"},"canonical_sha256":"a464d18c70cb869ab44043a0ef4c307fdf6452fff054af0d6714aceff5b7685a","source":{"kind":"arxiv","id":"2605.12483","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12483","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12483v3","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12483","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"URSNDDDQZODJ","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"URSNDDDQZODJVNCA","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"URSNDDDQ","created_at":"2026-05-20T00:01:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:URSNDDDQZODJVNCAIOQO6TBQP7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:57:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49c215ec67f8dcbf3197b08cf6dc71c97317ce38431a7d9b5787242c65a18466","abstract_canon_sha256":"25c163c0ee0c1fd8e36b6a83351eb068b56d1735f62dec0a11da2c45c2d631a0"},"schema_version":"1.0"},"canonical_sha256":"a464d18c70cb869ab44043a0ef4c307fdf6452fff054af0d6714aceff5b7685a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:44.013802Z","signature_b64":"tUloLbsG4AguVoqu23Xxieu/KD4k7czvWr0YQwPqNZxxpt/T6v5o54NriuSVq3q3ghH+w/mA0rUOqmPL7LeXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a464d18c70cb869ab44043a0ef4c307fdf6452fff054af0d6714aceff5b7685a","last_reissued_at":"2026-05-20T00:01:44.012985Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:44.012985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12483","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rIXjb5dDZu1tBRVSwqzgdqbHSpGHKlHyjCXLAzGjDs1bfyK+mds8tddt4b1VbMFrKVRPfFNM3gZ8FhkG+XJMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T17:07:13.099116Z"},"content_sha256":"e476a68188000c16971194ef6d0a1470207d8120c4ad4ba0c0c9cd2c3aed1ef5","schema_version":"1.0","event_id":"sha256:e476a68188000c16971194ef6d0a1470207d8120c4ad4ba0c0c9cd2c3aed1ef5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:URSNDDDQZODJVNCAIOQO6TBQP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A four-stage workflow with sparse-reward RL on a teacher followed by on-policy distillation outperforms direct GRPO on LLM math reasoning.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alborz Geramifard, Hejian Sang, Ran He, Yuanda Xu, Zhengze Zhou, Zhipeng Wang","submitted_at":"2026-05-12T17:57:48Z","abstract_excerpt":"We present a four-stage post-training workflow for LLM reasoning that allocates scarce labeled training data more effectively than standard recipes. The stages are: (1) sparse-reward RL on a larger teacher; (2a) forward-KL warmup on teacher rollouts; (2b) on-policy distillation under student rollouts; (3) optional sparse-reward RL on the deployment student using any held-out labeled data. On verifiable math with a Qwen3-1.7B deployment student, the workflow reaches $79.3\\%$ MATH and $25.2\\%$ AIME~2024 (avg@16), versus $75.9\\%$ and $19.8\\%$ for direct GRPO on the same student. We justify the wo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On verifiable math with a Qwen3-1.7B deployment student, the workflow reaches 79.3% MATH and 25.2% AIME 2024 (avg@16), versus 75.9% and 19.8% for direct GRPO on the same student.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The teacher model must itself be reward-shaped (condition C1) and lie within a small KL divergence of the student (condition C2) for the on-policy distillation stage to provide informative dense implicit rewards.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A four-stage sparse-to-dense reward workflow for LLM post-training reaches 79.3% on MATH and 25.2% on AIME 2024 with a 1.7B student, outperforming direct GRPO by enforcing dense implicit rewards from a shaped teacher.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A four-stage workflow with sparse-reward RL on a teacher followed by on-policy distillation outperforms direct GRPO on LLM math reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5c9e23903cd85fb5cdb33a44308b26fe82c54b6e8c744ee0d27760639f76a73a"},"source":{"id":"2605.12483","kind":"arxiv","version":3},"verdict":{"id":"96d23965-f712-4d00-99d7-f499e253406f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:37:05.873569Z","strongest_claim":"On verifiable math with a Qwen3-1.7B deployment student, the workflow reaches 79.3% MATH and 25.2% AIME 2024 (avg@16), versus 75.9% and 19.8% for direct GRPO on the same student.","one_line_summary":"A four-stage sparse-to-dense reward workflow for LLM post-training reaches 79.3% on MATH and 25.2% on AIME 2024 with a 1.7B student, outperforming direct GRPO by enforcing dense implicit rewards from a shaped teacher.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The teacher model must itself be reward-shaped (condition C1) and lie within a small KL divergence of the student (condition C2) for the on-policy distillation stage to provide informative dense implicit rewards.","pith_extraction_headline":"A four-stage workflow with sparse-reward RL on a teacher followed by on-policy distillation outperforms direct GRPO on LLM math reasoning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12483/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.804122Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T10:34:39.758162Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T08:01:17.948604Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T07:26:27.872311Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7bc778090ef335bac4b8ccec696206fbfce4ab2ef7583ecddbcb592ac287f49d"},"references":{"count":30,"sample":[{"doi":"","year":null,"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","ref_index":1,"cited_arxiv_id":"2204.05862","is_internal_anchor":true},{"doi":"","year":null,"title":"Rubric-based On-policy Distillation","work_id":"c10aafd2-e520-4829-b1a8-b460c24ea267","ref_index":2,"cited_arxiv_id":"2605.07396","is_internal_anchor":true},{"doi":"","year":null,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","ref_index":3,"cited_arxiv_id":"2407.21783","is_internal_anchor":true},{"doi":"","year":null,"title":"Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision","work_id":"075fcc48-23c0-4231-bf6e-c629eb2a169b","ref_index":4,"cited_arxiv_id":"2604.12002","is_internal_anchor":true},{"doi":"","year":null,"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","ref_index":5,"cited_arxiv_id":"1503.02531","is_internal_anchor":true}],"resolved_work":30,"snapshot_sha256":"c65db4e06548ee0df5284946a6b3aa75679bca4e3fe0d006b623aa1b466f122f","internal_anchors":21},"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":"96d23965-f712-4d00-99d7-f499e253406f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qftuagGB09yCTbYV5B9Lzlfpxh3uFg5ieWQE/K0TC+Y2dud6SBuhScEm2zsSO70QrzzuA4U2HJRoCpAZwRP5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T17:07:13.099735Z"},"content_sha256":"2c999d9e117106436436c6d4c189dd27d53809bc925a499c83e909b56f56eada","schema_version":"1.0","event_id":"sha256:2c999d9e117106436436c6d4c189dd27d53809bc925a499c83e909b56f56eada"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URSNDDDQZODJVNCAIOQO6TBQP7/bundle.json","state_url":"https://pith.science/pith/URSNDDDQZODJVNCAIOQO6TBQP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URSNDDDQZODJVNCAIOQO6TBQP7/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":"2026-07-01T17:07:13Z","links":{"resolver":"https://pith.science/pith/URSNDDDQZODJVNCAIOQO6TBQP7","bundle":"https://pith.science/pith/URSNDDDQZODJVNCAIOQO6TBQP7/bundle.json","state":"https://pith.science/pith/URSNDDDQZODJVNCAIOQO6TBQP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URSNDDDQZODJVNCAIOQO6TBQP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:URSNDDDQZODJVNCAIOQO6TBQP7","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":"25c163c0ee0c1fd8e36b6a83351eb068b56d1735f62dec0a11da2c45c2d631a0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:57:48Z","title_canon_sha256":"49c215ec67f8dcbf3197b08cf6dc71c97317ce38431a7d9b5787242c65a18466"},"schema_version":"1.0","source":{"id":"2605.12483","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12483","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12483v3","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12483","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"URSNDDDQZODJ","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"URSNDDDQZODJVNCA","created_at":"2026-05-20T00:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"URSNDDDQ","created_at":"2026-05-20T00:01:44Z"}],"graph_snapshots":[{"event_id":"sha256:2c999d9e117106436436c6d4c189dd27d53809bc925a499c83e909b56f56eada","target":"graph","created_at":"2026-05-20T00:01:44Z","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":"On verifiable math with a Qwen3-1.7B deployment student, the workflow reaches 79.3% MATH and 25.2% AIME 2024 (avg@16), versus 75.9% and 19.8% for direct GRPO on the same student."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The teacher model must itself be reward-shaped (condition C1) and lie within a small KL divergence of the student (condition C2) for the on-policy distillation stage to provide informative dense implicit rewards."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A four-stage sparse-to-dense reward workflow for LLM post-training reaches 79.3% on MATH and 25.2% on AIME 2024 with a 1.7B student, outperforming direct GRPO by enforcing dense implicit rewards from a shaped teacher."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A four-stage workflow with sparse-reward RL on a teacher followed by on-policy distillation outperforms direct GRPO on LLM math reasoning."}],"snapshot_sha256":"5c9e23903cd85fb5cdb33a44308b26fe82c54b6e8c744ee0d27760639f76a73a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.804122Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T10:34:39.758162Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T08:01:17.948604Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T07:26:27.872311Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.12483/integrity.json","findings":[],"snapshot_sha256":"7bc778090ef335bac4b8ccec696206fbfce4ab2ef7583ecddbcb592ac287f49d","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a four-stage post-training workflow for LLM reasoning that allocates scarce labeled training data more effectively than standard recipes. The stages are: (1) sparse-reward RL on a larger teacher; (2a) forward-KL warmup on teacher rollouts; (2b) on-policy distillation under student rollouts; (3) optional sparse-reward RL on the deployment student using any held-out labeled data. On verifiable math with a Qwen3-1.7B deployment student, the workflow reaches $79.3\\%$ MATH and $25.2\\%$ AIME~2024 (avg@16), versus $75.9\\%$ and $19.8\\%$ for direct GRPO on the same student. We justify the wo","authors_text":"Alborz Geramifard, Hejian Sang, Ran He, Yuanda Xu, Zhengze Zhou, Zhipeng Wang","cross_cats":["cs.AI"],"headline":"A four-stage workflow with sparse-reward RL on a teacher followed by on-policy distillation outperforms direct GRPO on LLM math reasoning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:57:48Z","title":"Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training"},"references":{"count":30,"internal_anchors":21,"resolved_work":30,"sample":[{"cited_arxiv_id":"2204.05862","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","work_id":"a1f2574b-a899-4713-be60-c87ba332656c","year":null},{"cited_arxiv_id":"2605.07396","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Rubric-based On-policy Distillation","work_id":"c10aafd2-e520-4829-b1a8-b460c24ea267","year":null},{"cited_arxiv_id":"2407.21783","doi":"","is_internal_anchor":true,"ref_index":3,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","year":null},{"cited_arxiv_id":"2604.12002","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision","work_id":"075fcc48-23c0-4231-bf6e-c629eb2a169b","year":null},{"cited_arxiv_id":"1503.02531","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","year":null}],"snapshot_sha256":"c65db4e06548ee0df5284946a6b3aa75679bca4e3fe0d006b623aa1b466f122f"},"source":{"id":"2605.12483","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-19T16:37:05.873569Z","id":"96d23965-f712-4d00-99d7-f499e253406f","model_set":{"reader":"grok-4.3"},"one_line_summary":"A four-stage sparse-to-dense reward workflow for LLM post-training reaches 79.3% on MATH and 25.2% on AIME 2024 with a 1.7B student, outperforming direct GRPO by enforcing dense implicit rewards from a shaped teacher.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A four-stage workflow with sparse-reward RL on a teacher followed by on-policy distillation outperforms direct GRPO on LLM math reasoning.","strongest_claim":"On verifiable math with a Qwen3-1.7B deployment student, the workflow reaches 79.3% MATH and 25.2% AIME 2024 (avg@16), versus 75.9% and 19.8% for direct GRPO on the same student.","weakest_assumption":"The teacher model must itself be reward-shaped (condition C1) and lie within a small KL divergence of the student (condition C2) for the on-policy distillation stage to provide informative dense implicit rewards."}},"verdict_id":"96d23965-f712-4d00-99d7-f499e253406f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e476a68188000c16971194ef6d0a1470207d8120c4ad4ba0c0c9cd2c3aed1ef5","target":"record","created_at":"2026-05-20T00:01:44Z","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":"25c163c0ee0c1fd8e36b6a83351eb068b56d1735f62dec0a11da2c45c2d631a0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:57:48Z","title_canon_sha256":"49c215ec67f8dcbf3197b08cf6dc71c97317ce38431a7d9b5787242c65a18466"},"schema_version":"1.0","source":{"id":"2605.12483","kind":"arxiv","version":3}},"canonical_sha256":"a464d18c70cb869ab44043a0ef4c307fdf6452fff054af0d6714aceff5b7685a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a464d18c70cb869ab44043a0ef4c307fdf6452fff054af0d6714aceff5b7685a","first_computed_at":"2026-05-20T00:01:44.012985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:44.012985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tUloLbsG4AguVoqu23Xxieu/KD4k7czvWr0YQwPqNZxxpt/T6v5o54NriuSVq3q3ghH+w/mA0rUOqmPL7LeXDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:44.013802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12483","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e476a68188000c16971194ef6d0a1470207d8120c4ad4ba0c0c9cd2c3aed1ef5","sha256:2c999d9e117106436436c6d4c189dd27d53809bc925a499c83e909b56f56eada"],"state_sha256":"aa5bf6debf1337ecb81c7a3adfd4686bae7c1d0b14b8c39a550c501160a70ddd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cn84O9QNHbKR/I0Uuo3YHwsl6Qg5dTt+EBXvkTdOU3SR69tBQGUuJ8+S1VTK+cEbEoXnyFm447T+upcSr5QYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T17:07:13.102389Z","bundle_sha256":"2aa5d3ca51ae40a225a480b192ddf3bcf89a890e72bae6efa6eb50fb88519c75"}}