{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V2HVCKOORCCJHIEJ6WTESR6M5Z","short_pith_number":"pith:V2HVCKOO","canonical_record":{"source":{"id":"2605.13473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:59:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8afc6aea63fda48a49767a60fbfc6e89d4c2a22468ae4b510ed73d342aa7b9e1","abstract_canon_sha256":"5093d0f0e9ba463cb4be5369fa3e04276e01fe1791c1dbd14e4898ace465fb14"},"schema_version":"1.0"},"canonical_sha256":"ae8f5129ce888493a089f5a64947ccee65eaccf648772ff79bf2e6f538521557","source":{"kind":"arxiv","id":"2605.13473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13473","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13473v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13473","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"V2HVCKOORCCJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"V2HVCKOORCCJHIEJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"V2HVCKOO","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V2HVCKOORCCJHIEJ6WTESR6M5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:59:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8afc6aea63fda48a49767a60fbfc6e89d4c2a22468ae4b510ed73d342aa7b9e1","abstract_canon_sha256":"5093d0f0e9ba463cb4be5369fa3e04276e01fe1791c1dbd14e4898ace465fb14"},"schema_version":"1.0"},"canonical_sha256":"ae8f5129ce888493a089f5a64947ccee65eaccf648772ff79bf2e6f538521557","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:41.520401Z","signature_b64":"P4FEgFnswv04kJkrGl1b7qIKg5uHnm5g6GiwggBU6mQgVMjF23cEG193S09JDePbHyAJAUP7hx26EdbmKp0gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8f5129ce888493a089f5a64947ccee65eaccf648772ff79bf2e6f538521557","last_reissued_at":"2026-05-18T02:44:41.519789Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:41.519789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13473","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":"2026-05-18T02:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3WLBHx7ClCcwfIPyLbpwC9mj6LtGmlJiiH3oRp/kU34MuJca1/5bAHLpl4AQs2xQ2y+rUGDkCJKEiqc3KkzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:54:12.834090Z"},"content_sha256":"f1544a85b9f3aad7a0e1849cd97b3abda1927a1d38152dd41e175fabbf638bf2","schema_version":"1.0","event_id":"sha256:f1544a85b9f3aad7a0e1849cd97b3abda1927a1d38152dd41e175fabbf638bf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V2HVCKOORCCJHIEJ6WTESR6M5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OSDN augments the Delta Rule with an online diagonal preconditioner equivalent to per-feature key scaling, delivering super-geometric convergence and 39% lower recall residual at 1.3B parameters.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenyu Zhou, Dongdong Ge, Hongpei Li, Jianghao Lin, Yinyu Ye, Yuerou Liu","submitted_at":"2026-05-13T12:59:26Z","abstract_excerpt":"Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall. The Delta Rule mitigates this by writing each token via one step of online gradient descent. However, its step size relies on a single scalar gate that ignores the feature-wise curvature of the inner objective. We propose Online Scaled DeltaNet (OSDN), which augments the scalar gate with a diagonal preconditioner updated online via hypergradient feedback. Crucially, this right-preconditioning is algebraically equivalent to a per-feature scaling"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By exploiting the exact-quadratic structure of the inner regression loss, we establish super-geometric convergence against a right-Newton comparator and prove an algorithm-aligned token-local residual contraction bound; at 1.3B parameters OSDN achieves a 39% reduction in the recall residual ratio.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The inner objective remains exactly quadratic and the online hypergradient update for the diagonal preconditioner can be maintained without breaking the chunkwise parallel pipeline or requiring high-dimensional state.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OSDN adds online diagonal preconditioning to the Delta Rule, preserving chunkwise parallelism while proving super-geometric convergence and delivering 32-39% recall gains at 340M-1.3B scales.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OSDN augments the Delta Rule with an online diagonal preconditioner equivalent to per-feature key scaling, delivering super-geometric convergence and 39% lower recall residual at 1.3B parameters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f76df0f9d6254453bc369ab5be0b1c7dfd479f2e502f474059bd423ac56db383"},"source":{"id":"2605.13473","kind":"arxiv","version":1},"verdict":{"id":"414a0e29-9c84-4451-8f0b-a5440e79128a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:04:37.167670Z","strongest_claim":"By exploiting the exact-quadratic structure of the inner regression loss, we establish super-geometric convergence against a right-Newton comparator and prove an algorithm-aligned token-local residual contraction bound; at 1.3B parameters OSDN achieves a 39% reduction in the recall residual ratio.","one_line_summary":"OSDN adds online diagonal preconditioning to the Delta Rule, preserving chunkwise parallelism while proving super-geometric convergence and delivering 32-39% recall gains at 340M-1.3B scales.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The inner objective remains exactly quadratic and the online hypergradient update for the diagonal preconditioner can be maintained without breaking the chunkwise parallel pipeline or requiring high-dimensional state.","pith_extraction_headline":"OSDN augments the Delta Rule with an online diagonal preconditioner equivalent to per-feature key scaling, delivering super-geometric convergence and 39% lower recall residual at 1.3B parameters."},"references":{"count":73,"sample":[{"doi":"","year":2023,"title":"What learning algorithm is in-context learning? investigations with linear models","work_id":"79950075-a669-4e48-8bc9-28cc29e8d753","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Zoology: Measuring and improving recall in efficient language models","work_id":"a51e0ddf-22e2-4d3c-9759-7201f7d9a699","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Simple linear attention language models balance the recall-throughput tradeoff","work_id":"c542bc4f-de21-42d2-812b-b46f5fa9b434","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Just read twice: closing the recall gap for recurrent language models, 2024 b","work_id":"0700c833-caaf-47d2-b97c-2f4a50eed025","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Hinton, V olodymyr Mnih, Joel Z","work_id":"2acf842b-c183-4bfb-8391-2b456d531aa2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":73,"snapshot_sha256":"8fbc836eb1ff49d3919ad7ba3273ee946089009a486517d6162d19a767f6e859","internal_anchors":5},"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":"414a0e29-9c84-4451-8f0b-a5440e79128a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8EvDGPLQasVNniAmk5HPQPTg6t6pHCPUAaoI/EW2TPwYbQ5P03izTKoiR6tH41lJEKgO2759KbTzciMhqacDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:54:12.834637Z"},"content_sha256":"3c0f01559987decde80142df02980345771184b0f28122cf2c63cc7e2a0d38f2","schema_version":"1.0","event_id":"sha256:3c0f01559987decde80142df02980345771184b0f28122cf2c63cc7e2a0d38f2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:V2HVCKOORCCJHIEJ6WTESR6M5Z","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2022.emnlp-main.697.URLhttps://aclanthology.org/2022.emnlp-main.697/) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Huanru Henry Mao. Fine-tuning pre-trained transformers into decaying fast weights. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors,Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 102","arxiv_id":"2605.13473","detector":"doi_compliance","evidence":{"ref_index":33,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Huanru Henry Mao. Fine-tuning pre-trained transformers into decaying fast weights. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors,Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 102","reconstructed_doi":"10.18653/v1/2022.emnlp-main.697.URLhttps://aclanthology.org/2022.emnlp-main.697/"},"severity":"advisory","ref_index":33,"audited_at":"2026-05-19T06:31:15.834776Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2022.emnlp-main.697.URLhttps://aclanthology.org/2022.emnlp-main.697/","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"505095e256be2086218576dbf3fd132817a1dea71f7326586b4cc6412360f57f","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":158,"payload_sha256":"a640d7fc750ff15732b1f4f42e0bb28ec39d1ac5b0378a3724064095ced5ef93","signature_b64":"LtF6Uixoev4NyorVtKKgdARkI2+qtVE/psUJmiUrA/0pbvtwM3ZnY+Zj+DokxDZXuvRL0pHQ0O5479ZmpZiVAA==","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":"2026-05-19T06:31:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9ods7QCWAyux/BELROXPWYxHRhsTIKjSiU5XRomuxcBoz1+3ww8Z4RNhdy645OLnCW6wXpDgPjhST+aNi/2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:54:12.835541Z"},"content_sha256":"a5089a3c640f95ced82079ecc8f955d897a51872df2b9ef42a79b3f72af9f837","schema_version":"1.0","event_id":"sha256:a5089a3c640f95ced82079ecc8f955d897a51872df2b9ef42a79b3f72af9f837"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z/bundle.json","state_url":"https://pith.science/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z/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":"2026-05-19T21:54:12Z","links":{"resolver":"https://pith.science/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z","bundle":"https://pith.science/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z/bundle.json","state":"https://pith.science/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2HVCKOORCCJHIEJ6WTESR6M5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V2HVCKOORCCJHIEJ6WTESR6M5Z","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":"5093d0f0e9ba463cb4be5369fa3e04276e01fe1791c1dbd14e4898ace465fb14","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:59:26Z","title_canon_sha256":"8afc6aea63fda48a49767a60fbfc6e89d4c2a22468ae4b510ed73d342aa7b9e1"},"schema_version":"1.0","source":{"id":"2605.13473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13473","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13473v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13473","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"V2HVCKOORCCJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"V2HVCKOORCCJHIEJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"V2HVCKOO","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3c0f01559987decde80142df02980345771184b0f28122cf2c63cc7e2a0d38f2","target":"graph","created_at":"2026-05-18T02:44:41Z","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":"By exploiting the exact-quadratic structure of the inner regression loss, we establish super-geometric convergence against a right-Newton comparator and prove an algorithm-aligned token-local residual contraction bound; at 1.3B parameters OSDN achieves a 39% reduction in the recall residual ratio."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The inner objective remains exactly quadratic and the online hypergradient update for the diagonal preconditioner can be maintained without breaking the chunkwise parallel pipeline or requiring high-dimensional state."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OSDN adds online diagonal preconditioning to the Delta Rule, preserving chunkwise parallelism while proving super-geometric convergence and delivering 32-39% recall gains at 340M-1.3B scales."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"OSDN augments the Delta Rule with an online diagonal preconditioner equivalent to per-feature key scaling, delivering super-geometric convergence and 39% lower recall residual at 1.3B parameters."}],"snapshot_sha256":"f76df0f9d6254453bc369ab5be0b1c7dfd479f2e502f474059bd423ac56db383"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall. The Delta Rule mitigates this by writing each token via one step of online gradient descent. However, its step size relies on a single scalar gate that ignores the feature-wise curvature of the inner objective. We propose Online Scaled DeltaNet (OSDN), which augments the scalar gate with a diagonal preconditioner updated online via hypergradient feedback. Crucially, this right-preconditioning is algebraically equivalent to a per-feature scaling","authors_text":"Chenyu Zhou, Dongdong Ge, Hongpei Li, Jianghao Lin, Yinyu Ye, Yuerou Liu","cross_cats":["cs.CL"],"headline":"OSDN augments the Delta Rule with an online diagonal preconditioner equivalent to per-feature key scaling, delivering super-geometric convergence and 39% lower recall residual at 1.3B parameters.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:59:26Z","title":"OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention"},"references":{"count":73,"internal_anchors":5,"resolved_work":73,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"What learning algorithm is in-context learning? investigations with linear models","work_id":"79950075-a669-4e48-8bc9-28cc29e8d753","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Zoology: Measuring and improving recall in efficient language models","work_id":"a51e0ddf-22e2-4d3c-9759-7201f7d9a699","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Simple linear attention language models balance the recall-throughput tradeoff","work_id":"c542bc4f-de21-42d2-812b-b46f5fa9b434","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Just read twice: closing the recall gap for recurrent language models, 2024 b","work_id":"0700c833-caaf-47d2-b97c-2f4a50eed025","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Hinton, V olodymyr Mnih, Joel Z","work_id":"2acf842b-c183-4bfb-8391-2b456d531aa2","year":2016}],"snapshot_sha256":"8fbc836eb1ff49d3919ad7ba3273ee946089009a486517d6162d19a767f6e859"},"source":{"id":"2605.13473","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:04:37.167670Z","id":"414a0e29-9c84-4451-8f0b-a5440e79128a","model_set":{"reader":"grok-4.3"},"one_line_summary":"OSDN adds online diagonal preconditioning to the Delta Rule, preserving chunkwise parallelism while proving super-geometric convergence and delivering 32-39% recall gains at 340M-1.3B scales.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"OSDN augments the Delta Rule with an online diagonal preconditioner equivalent to per-feature key scaling, delivering super-geometric convergence and 39% lower recall residual at 1.3B parameters.","strongest_claim":"By exploiting the exact-quadratic structure of the inner regression loss, we establish super-geometric convergence against a right-Newton comparator and prove an algorithm-aligned token-local residual contraction bound; at 1.3B parameters OSDN achieves a 39% reduction in the recall residual ratio.","weakest_assumption":"The inner objective remains exactly quadratic and the online hypergradient update for the diagonal preconditioner can be maintained without breaking the chunkwise parallel pipeline or requiring high-dimensional state."}},"verdict_id":"414a0e29-9c84-4451-8f0b-a5440e79128a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f1544a85b9f3aad7a0e1849cd97b3abda1927a1d38152dd41e175fabbf638bf2","target":"record","created_at":"2026-05-18T02:44:41Z","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":"5093d0f0e9ba463cb4be5369fa3e04276e01fe1791c1dbd14e4898ace465fb14","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:59:26Z","title_canon_sha256":"8afc6aea63fda48a49767a60fbfc6e89d4c2a22468ae4b510ed73d342aa7b9e1"},"schema_version":"1.0","source":{"id":"2605.13473","kind":"arxiv","version":1}},"canonical_sha256":"ae8f5129ce888493a089f5a64947ccee65eaccf648772ff79bf2e6f538521557","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae8f5129ce888493a089f5a64947ccee65eaccf648772ff79bf2e6f538521557","first_computed_at":"2026-05-18T02:44:41.519789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:41.519789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P4FEgFnswv04kJkrGl1b7qIKg5uHnm5g6GiwggBU6mQgVMjF23cEG193S09JDePbHyAJAUP7hx26EdbmKp0gAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:41.520401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1544a85b9f3aad7a0e1849cd97b3abda1927a1d38152dd41e175fabbf638bf2","sha256:3c0f01559987decde80142df02980345771184b0f28122cf2c63cc7e2a0d38f2","sha256:a5089a3c640f95ced82079ecc8f955d897a51872df2b9ef42a79b3f72af9f837"],"state_sha256":"2dfa24d13ecc4e8de887a71e582541e4816d922cf367378e2d670ed1d7af6eb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MmLwzjE2ES7vA0lvHbgRG3XBBjXMSm8kLd0jRC1u4uuZyvLzgvcf8GNcYZWQwq/2dJZy70Ml4p0xWEmjtJIeCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T21:54:12.837872Z","bundle_sha256":"ceec5f4c9fee019085c86dc15fe5988fe5c2ff1e1e0e3d1c81edfe182e6d5045"}}