{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3DFFD73LNAG5VH23IBXOK56MAA","short_pith_number":"pith:3DFFD73L","canonical_record":{"source":{"id":"2605.16860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T07:50:00Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"9835345f5184346d40708307bc34b41b06ff56aa377315e2671d80b5a09e3680","abstract_canon_sha256":"4406ead7226486b8f012d3ca519ec88cfd3330b9097162e6181607749c2b8b4f"},"schema_version":"1.0"},"canonical_sha256":"d8ca51ff6b680dda9f5b406ee577cc0031020393454ba3ebe94adf4a0f3f76e9","source":{"kind":"arxiv","id":"2605.16860","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16860","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16860v1","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16860","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"3DFFD73LNAG5","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"3DFFD73LNAG5VH23","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"3DFFD73L","created_at":"2026-05-20T00:03:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3DFFD73LNAG5VH23IBXOK56MAA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T07:50:00Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"9835345f5184346d40708307bc34b41b06ff56aa377315e2671d80b5a09e3680","abstract_canon_sha256":"4406ead7226486b8f012d3ca519ec88cfd3330b9097162e6181607749c2b8b4f"},"schema_version":"1.0"},"canonical_sha256":"d8ca51ff6b680dda9f5b406ee577cc0031020393454ba3ebe94adf4a0f3f76e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:26.769895Z","signature_b64":"K22278XJvtNGCVP+ZsxwU7pPrFH/wLOgEij788F9j7X/gSFLde3+QT+R2QTeuit5p1xTmuquFB42lZ/QY/RLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8ca51ff6b680dda9f5b406ee577cc0031020393454ba3ebe94adf4a0f3f76e9","last_reissued_at":"2026-05-20T00:03:26.769148Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:26.769148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16860","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":"2026-05-20T00:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jqYpzCitGCl2/S4Tku39wR+kv9erM/jYcVDIro1+Ex9rl77jCQDJ3LtKke3XyWyZ0ybDZcZx+Gz8R7tsUQLOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:56:57.581015Z"},"content_sha256":"88c3bb32bf3b4ba069c36b34dc54f39d1c0a7f75e69610ec0523634c0d2204fd","schema_version":"1.0","event_id":"sha256:88c3bb32bf3b4ba069c36b34dc54f39d1c0a7f75e69610ec0523634c0d2204fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3DFFD73LNAG5VH23IBXOK56MAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PhysioSeq2Seq: A Hybrid Physiological Digital Twin and Sequence-to-Sequence LSTM for Long-Horizon Glucose Forecasting in Type 1 Diabetes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PhysioSeq2Seq reduces long-horizon glucose forecast bias by injecting patient-matched physiological states into a sequence-to-sequence LSTM.","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Clara Mosquera-Lopez, Lizhong Chen, Neville Mehta, Peter G. Jacobs, Phat Tran, Robert H. Dodier","submitted_at":"2026-05-16T07:50:00Z","abstract_excerpt":"Accurate long-horizon glucose forecasting is critical for automated insulin delivery systems, which help people with type 1 diabetes (T1D) manage their glucose and avoid dangerous hypoglycemia. However, standard recursive long short-term memory (LSTM) networks suffer from systematic negative bias at longer horizons due to error compounding, while purely mechanistic ordinary differential equation (ODE) models fail to generalize across individuals when parameterized at the population level. We propose PhysioSeq2Seq, a hybrid architecture that combines patient-specific physiological modeling with"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"At the 240-minute horizon, PhysioSeq2Seq achieves a mean absolute error of 39.28 mg/dL and a mean error of -10.62 mg/dL, reducing bias by 13.89 mg/dL over the recursive LSTM and reducing mean absolute error by 28.62 mg/dL over the ODE-based digital twin.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That selecting one of 300 pre-parameterized digital twins solely from a 3-hour CGM segment supplies internal ODE states accurate enough to constrain the LSTM's long-horizon output without introducing new systematic errors or selection bias.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Hybrid digital-twin matching plus Seq2Seq LSTM reduces 240-minute glucose forecast bias by 13.89 mg/dL and MAE by 28.62 mg/dL versus baselines on held-out T1DEXI data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PhysioSeq2Seq reduces long-horizon glucose forecast bias by injecting patient-matched physiological states into a sequence-to-sequence LSTM.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"358c7797498d97b7cb6fb8072398bc314ed0821ae8cf2954079174248c658654"},"source":{"id":"2605.16860","kind":"arxiv","version":1},"verdict":{"id":"e770f7fd-b051-4d13-8bf8-36f2a03ea7dd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:39:37.238727Z","strongest_claim":"At the 240-minute horizon, PhysioSeq2Seq achieves a mean absolute error of 39.28 mg/dL and a mean error of -10.62 mg/dL, reducing bias by 13.89 mg/dL over the recursive LSTM and reducing mean absolute error by 28.62 mg/dL over the ODE-based digital twin.","one_line_summary":"Hybrid digital-twin matching plus Seq2Seq LSTM reduces 240-minute glucose forecast bias by 13.89 mg/dL and MAE by 28.62 mg/dL versus baselines on held-out T1DEXI data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That selecting one of 300 pre-parameterized digital twins solely from a 3-hour CGM segment supplies internal ODE states accurate enough to constrain the LSTM's long-horizon output without introducing new systematic errors or selection bias.","pith_extraction_headline":"PhysioSeq2Seq reduces long-horizon glucose forecast bias by injecting patient-matched physiological states into a sequence-to-sequence LSTM."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16860/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.231635Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:51:12.278927Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.306188Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.381489Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"77d1932b4517c19b5d51eccf18a12b8294fa5b8f6def29b89d04a3001e024d01"},"references":{"count":26,"sample":[{"doi":"10.1088/0967-3334/25/4/010","year":null,"title":"and Haueter, Ulrich and Massi-Benedetti, Massimo and Federici, Marco Orsini and Pieber, Thomas R","work_id":"b21bbc2b-9bf2-4327-b7e2-7bcfb8519f00","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Wang, Fei and Haynes, Aveni and Gregory, Gabriel A","work_id":"e34c9177-1fcd-4fe9-aca8-9b153d8f5ea3","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Diabetes , volume =","work_id":"a2b4ebaf-563c-45f0-b6ca-69eea311de34","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Breton and Sriram Sankaranarayanan , journal =","work_id":"67970ac8-4aa5-41b5-95e8-9b923afbcf5a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"2020 , volume =","work_id":"a1107c75-eda8-476e-899b-ccfa1cb1e806","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"447538af1809dea3af5f72072fc03145fba122d328e9c07cbd6de1294bf86d4c","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e5f7501b7d2c084e6b4bb98db0c71a87fa280c7e2247a6e5f9a160cd9d5ee56c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e770f7fd-b051-4d13-8bf8-36f2a03ea7dd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfoDoQyxYcbP1FyAz/kH3b88m6u1SWVXHM9PQEKDmW/icz3SyzcdqTj6VywV/Z381nCLhm1b5vjMwayA2PDpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:56:57.581803Z"},"content_sha256":"fb6b5fd9f34103bfc64ae63b79a0532013d6fae89ea49b9a8df320294b6ef7aa","schema_version":"1.0","event_id":"sha256:fb6b5fd9f34103bfc64ae63b79a0532013d6fae89ea49b9a8df320294b6ef7aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DFFD73LNAG5VH23IBXOK56MAA/bundle.json","state_url":"https://pith.science/pith/3DFFD73LNAG5VH23IBXOK56MAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DFFD73LNAG5VH23IBXOK56MAA/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":"2026-05-26T18:56:57Z","links":{"resolver":"https://pith.science/pith/3DFFD73LNAG5VH23IBXOK56MAA","bundle":"https://pith.science/pith/3DFFD73LNAG5VH23IBXOK56MAA/bundle.json","state":"https://pith.science/pith/3DFFD73LNAG5VH23IBXOK56MAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DFFD73LNAG5VH23IBXOK56MAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3DFFD73LNAG5VH23IBXOK56MAA","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":"4406ead7226486b8f012d3ca519ec88cfd3330b9097162e6181607749c2b8b4f","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T07:50:00Z","title_canon_sha256":"9835345f5184346d40708307bc34b41b06ff56aa377315e2671d80b5a09e3680"},"schema_version":"1.0","source":{"id":"2605.16860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16860","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16860v1","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16860","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"3DFFD73LNAG5","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"3DFFD73LNAG5VH23","created_at":"2026-05-20T00:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"3DFFD73L","created_at":"2026-05-20T00:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:fb6b5fd9f34103bfc64ae63b79a0532013d6fae89ea49b9a8df320294b6ef7aa","target":"graph","created_at":"2026-05-20T00:03:26Z","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":"At the 240-minute horizon, PhysioSeq2Seq achieves a mean absolute error of 39.28 mg/dL and a mean error of -10.62 mg/dL, reducing bias by 13.89 mg/dL over the recursive LSTM and reducing mean absolute error by 28.62 mg/dL over the ODE-based digital twin."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That selecting one of 300 pre-parameterized digital twins solely from a 3-hour CGM segment supplies internal ODE states accurate enough to constrain the LSTM's long-horizon output without introducing new systematic errors or selection bias."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Hybrid digital-twin matching plus Seq2Seq LSTM reduces 240-minute glucose forecast bias by 13.89 mg/dL and MAE by 28.62 mg/dL versus baselines on held-out T1DEXI data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PhysioSeq2Seq reduces long-horizon glucose forecast bias by injecting patient-matched physiological states into a sequence-to-sequence LSTM."}],"snapshot_sha256":"358c7797498d97b7cb6fb8072398bc314ed0821ae8cf2954079174248c658654"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e5f7501b7d2c084e6b4bb98db0c71a87fa280c7e2247a6e5f9a160cd9d5ee56c"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.231635Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T20:51:12.278927Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.306188Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.381489Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16860/integrity.json","findings":[],"snapshot_sha256":"77d1932b4517c19b5d51eccf18a12b8294fa5b8f6def29b89d04a3001e024d01","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate long-horizon glucose forecasting is critical for automated insulin delivery systems, which help people with type 1 diabetes (T1D) manage their glucose and avoid dangerous hypoglycemia. However, standard recursive long short-term memory (LSTM) networks suffer from systematic negative bias at longer horizons due to error compounding, while purely mechanistic ordinary differential equation (ODE) models fail to generalize across individuals when parameterized at the population level. We propose PhysioSeq2Seq, a hybrid architecture that combines patient-specific physiological modeling with","authors_text":"Clara Mosquera-Lopez, Lizhong Chen, Neville Mehta, Peter G. Jacobs, Phat Tran, Robert H. Dodier","cross_cats":["cs.AI","q-bio.QM"],"headline":"PhysioSeq2Seq reduces long-horizon glucose forecast bias by injecting patient-matched physiological states into a sequence-to-sequence LSTM.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T07:50:00Z","title":"PhysioSeq2Seq: A Hybrid Physiological Digital Twin and Sequence-to-Sequence LSTM for Long-Horizon Glucose Forecasting in Type 1 Diabetes"},"references":{"count":26,"internal_anchors":1,"resolved_work":26,"sample":[{"cited_arxiv_id":"","doi":"10.1088/0967-3334/25/4/010","is_internal_anchor":false,"ref_index":1,"title":"and Haueter, Ulrich and Massi-Benedetti, Massimo and Federici, Marco Orsini and Pieber, Thomas R","work_id":"b21bbc2b-9bf2-4327-b7e2-7bcfb8519f00","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"and Wang, Fei and Haynes, Aveni and Gregory, Gabriel A","work_id":"e34c9177-1fcd-4fe9-aca8-9b153d8f5ea3","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Diabetes , volume =","work_id":"a2b4ebaf-563c-45f0-b6ca-69eea311de34","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Breton and Sriram Sankaranarayanan , journal =","work_id":"67970ac8-4aa5-41b5-95e8-9b923afbcf5a","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"2020 , volume =","work_id":"a1107c75-eda8-476e-899b-ccfa1cb1e806","year":2020}],"snapshot_sha256":"447538af1809dea3af5f72072fc03145fba122d328e9c07cbd6de1294bf86d4c"},"source":{"id":"2605.16860","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T20:39:37.238727Z","id":"e770f7fd-b051-4d13-8bf8-36f2a03ea7dd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Hybrid digital-twin matching plus Seq2Seq LSTM reduces 240-minute glucose forecast bias by 13.89 mg/dL and MAE by 28.62 mg/dL versus baselines on held-out T1DEXI data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PhysioSeq2Seq reduces long-horizon glucose forecast bias by injecting patient-matched physiological states into a sequence-to-sequence LSTM.","strongest_claim":"At the 240-minute horizon, PhysioSeq2Seq achieves a mean absolute error of 39.28 mg/dL and a mean error of -10.62 mg/dL, reducing bias by 13.89 mg/dL over the recursive LSTM and reducing mean absolute error by 28.62 mg/dL over the ODE-based digital twin.","weakest_assumption":"That selecting one of 300 pre-parameterized digital twins solely from a 3-hour CGM segment supplies internal ODE states accurate enough to constrain the LSTM's long-horizon output without introducing new systematic errors or selection bias."}},"verdict_id":"e770f7fd-b051-4d13-8bf8-36f2a03ea7dd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:88c3bb32bf3b4ba069c36b34dc54f39d1c0a7f75e69610ec0523634c0d2204fd","target":"record","created_at":"2026-05-20T00:03:26Z","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":"4406ead7226486b8f012d3ca519ec88cfd3330b9097162e6181607749c2b8b4f","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T07:50:00Z","title_canon_sha256":"9835345f5184346d40708307bc34b41b06ff56aa377315e2671d80b5a09e3680"},"schema_version":"1.0","source":{"id":"2605.16860","kind":"arxiv","version":1}},"canonical_sha256":"d8ca51ff6b680dda9f5b406ee577cc0031020393454ba3ebe94adf4a0f3f76e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8ca51ff6b680dda9f5b406ee577cc0031020393454ba3ebe94adf4a0f3f76e9","first_computed_at":"2026-05-20T00:03:26.769148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:26.769148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K22278XJvtNGCVP+ZsxwU7pPrFH/wLOgEij788F9j7X/gSFLde3+QT+R2QTeuit5p1xTmuquFB42lZ/QY/RLAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:26.769895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88c3bb32bf3b4ba069c36b34dc54f39d1c0a7f75e69610ec0523634c0d2204fd","sha256:fb6b5fd9f34103bfc64ae63b79a0532013d6fae89ea49b9a8df320294b6ef7aa"],"state_sha256":"435a178b48e71eac4d9531f07b8e31d413f38c339f5ff04c25ec9792805d5829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdZwsPNfoXJpU5nb6SEhf9MFbvjz7C1E/DsHq9W8f5mKa/37sJyJwRinqD4tTHXtmJeqAwS3p0zLNfr/tt6aCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T18:56:57.585703Z","bundle_sha256":"c689b060e04d71ecf838a39042c9e1739e6032aa1c8e43806c4deff095a9887c"}}