{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:REMW4YGERUK3YZULDDSFX4ZAMX","short_pith_number":"pith:REMW4YGE","canonical_record":{"source":{"id":"2605.12763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:20:27Z","cross_cats_sorted":["math.DS","math.OC","q-bio.NC"],"title_canon_sha256":"14dcd61b0f8cfbed36538b49b155f469b3677862c6af4b6b1814269e8e651f26","abstract_canon_sha256":"c5e5841adfb5591d3edf44c79da67f9bc54f4e9b8d5a72426909a417a33a7a19"},"schema_version":"1.0"},"canonical_sha256":"89196e60c48d15bc668b18e45bf32065efdc83b9f3e2c984a22e3269b6ded12b","source":{"kind":"arxiv","id":"2605.12763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12763","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12763v1","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12763","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"REMW4YGERUK3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"REMW4YGERUK3YZUL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"REMW4YGE","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:REMW4YGERUK3YZULDDSFX4ZAMX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:20:27Z","cross_cats_sorted":["math.DS","math.OC","q-bio.NC"],"title_canon_sha256":"14dcd61b0f8cfbed36538b49b155f469b3677862c6af4b6b1814269e8e651f26","abstract_canon_sha256":"c5e5841adfb5591d3edf44c79da67f9bc54f4e9b8d5a72426909a417a33a7a19"},"schema_version":"1.0"},"canonical_sha256":"89196e60c48d15bc668b18e45bf32065efdc83b9f3e2c984a22e3269b6ded12b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:48.336440Z","signature_b64":"hBf4UyOcjQT+pt/3NEU2hpoGLhT1VjXgiRqjlLhs8Nu8qDo0h2AneP95Nw41sYJ+rBs0Ze2Hr2+ci5xVcLHjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89196e60c48d15bc668b18e45bf32065efdc83b9f3e2c984a22e3269b6ded12b","last_reissued_at":"2026-05-18T03:09:48.335490Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:48.335490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12763","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":"2026-05-18T03:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erhvB0P9S6iLykCZpSXXbX9QKrl2Fm5k1K8Dqeg8JtFGdGVIsniTlSnjlh4QBIZLk3okzmXf1oSqH5UjwAhZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:36:50.461236Z"},"content_sha256":"12e30b5455cdc45a78de097ee8d6245f84b4aa40fa346f6e4bdca9c75019ab83","schema_version":"1.0","event_id":"sha256:12e30b5455cdc45a78de097ee8d6245f84b4aa40fa346f6e4bdca9c75019ab83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:REMW4YGERUK3YZULDDSFX4ZAMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-Space NTK Collapse Near Bifurcations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Near bifurcations, the state-space NTK reduces to a rank-one operator matching the learning geometry of a classical normal form.","cross_cats":["math.DS","math.OC","q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Eric Shea-Brown, James Hazelden","submitted_at":"2026-05-12T21:20:27Z","abstract_excerpt":"Rich feature learning in tasks that unfold over time often requires the model to pass through bifurcations, constituting qualitative changes in the underlying model dynamics. We develop a local theory of gradient descent near these transitions through the empirical state-space neural tangent kernel (sNTK). Our central finding is that bifurcations both dominate and simplify learning dynamics: near bifurcations, we can reduce sNTK to a rank-one operator corresponding to learning in a classical normal form system, providing an analytically tractable description of the local learning geometry, eve"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"near bifurcations, we can reduce sNTK to a rank-one operator corresponding to learning in a classical normal form system, providing an analytically tractable description of the local learning geometry, even for high-dimensional recurrent systems.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the local linearization and decomposition into bifurcation-relevant and residual channels remain valid and dominant for the full nonlinear high-dimensional system and that the amplification of the rank-one channel is not an artifact of the specific student-teacher architecture or initialization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Bifurcations cause sNTK to reduce to a dominant rank-one channel matching normal forms, collapsing effective rank and funneling gradient descent into critical dynamical directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Near bifurcations, the state-space NTK reduces to a rank-one operator matching the learning geometry of a classical normal form.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"830635fb0e07b626dd72ee997bdc1794b85ea416911b49ea21addf7fa4be25aa"},"source":{"id":"2605.12763","kind":"arxiv","version":1},"verdict":{"id":"2d2b5b40-ca3a-411e-a1f3-df4b9c5b942e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:59:36.791495Z","strongest_claim":"near bifurcations, we can reduce sNTK to a rank-one operator corresponding to learning in a classical normal form system, providing an analytically tractable description of the local learning geometry, even for high-dimensional recurrent systems.","one_line_summary":"Bifurcations cause sNTK to reduce to a dominant rank-one channel matching normal forms, collapsing effective rank and funneling gradient descent into critical dynamical directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the local linearization and decomposition into bifurcation-relevant and residual channels remain valid and dominant for the full nonlinear high-dimensional system and that the amplification of the rank-one channel is not an artifact of the specific student-teacher architecture or initialization.","pith_extraction_headline":"Near bifurcations, the state-space NTK reduces to a rank-one operator matching the learning geometry of a classical normal form."},"references":{"count":137,"sample":[{"doi":"","year":null,"title":"arXiv preprint arXiv:2311.10869 , year=","work_id":"f22c5df9-65f5-49e8-a935-6d46c04b57bb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Deep Residual Learning for Image Recognition , author=. 2015 , eprint=","work_id":"948c9222-e716-4297-919b-917ed6f56d86","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"James Bradbury and Roy Frostig and Peter Hawkins and Matthew James Johnson and Chris Leary and Dougal Maclaurin and George Necula and Adam Paszke and Jake Vander","work_id":"f722cabc-fda6-4889-82c5-313113edc5fb","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and","work_id":"85fe8ea2-dfba-4883-bbba-2341408e0f7b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Papyan, Vardan and Han, X. Y. and Donoho, David L. , title =. Proceedings of the National Academy of Sciences , volume =. 2020 , doi =","work_id":"b8a58faa-8ff4-4caa-aec9-7f7975b434e2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":137,"snapshot_sha256":"9998b4c72bb7632a5f8f05c65cb65da2b1478ce41e74ba3564c51457f9232fe4","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":"2d2b5b40-ca3a-411e-a1f3-df4b9c5b942e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4U0pAHA3kuTu3hugL4DnjuxOkEtdFf4XqY+OFpLd1uqlm9xstOTgiECGOLSnFAuWjB4sge32eX8uffJ9SMSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:36:50.461801Z"},"content_sha256":"c8d73a1b7c70e62ae616eea6d4d258a8404e831e7b1f10ef4925f2e86a4e6a10","schema_version":"1.0","event_id":"sha256:c8d73a1b7c70e62ae616eea6d4d258a8404e831e7b1f10ef4925f2e86a4e6a10"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:REMW4YGERUK3YZULDDSFX4ZAMX","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1162/NECO\\_a\\_00409) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks , author=. Neural Computation , volume=. 2013 , publisher=. doi:10.1162/NECO\\_a\\_00409 , PMID=","arxiv_id":"2605.12763","detector":"doi_compliance","evidence":{"ref_index":47,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks , author=. Neural Computation , volume=. 2013 , publisher=. doi:10.1162/NECO\\_a\\_00409 , PMID=","reconstructed_doi":"10.1162/NECO\\_a\\_00409"},"severity":"advisory","ref_index":47,"audited_at":"2026-05-19T07:09:33.454774Z","event_type":"pith.integrity.v1","detected_doi":"10.1162/NECO\\_a\\_00409","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"7c7f71e38caaacc304c8014f47d61a38af97f1743d1c317836b13469d27eeb8f","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":266,"payload_sha256":"98fb2a3bf86c22d040e1548d120b70fcab5113950da24de86c6b658ec492b674","signature_b64":"9oz6bpuVWuppgvKo9YlDWAJXnIF7PaP0wck3H7zHqGEM+TLcmtYPm0n+gJvFQILEl12jlY/oJcZQak3rAmJOBw==","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":"2026-05-19T07:11:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2U2zHLkzGJO4YY3sdLUwDVJy0siSPvTNT4/rsp3xFFE3xSjfh+caicvUUewHVC0CaS3bV9VZX9kQRq6qcVorAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T21:36:50.463332Z"},"content_sha256":"3acfc8e2957ed5aaca5a199018a06a44e1431896b740638c578984c625763b50","schema_version":"1.0","event_id":"sha256:3acfc8e2957ed5aaca5a199018a06a44e1431896b740638c578984c625763b50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REMW4YGERUK3YZULDDSFX4ZAMX/bundle.json","state_url":"https://pith.science/pith/REMW4YGERUK3YZULDDSFX4ZAMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REMW4YGERUK3YZULDDSFX4ZAMX/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":"2026-05-21T21:36:50Z","links":{"resolver":"https://pith.science/pith/REMW4YGERUK3YZULDDSFX4ZAMX","bundle":"https://pith.science/pith/REMW4YGERUK3YZULDDSFX4ZAMX/bundle.json","state":"https://pith.science/pith/REMW4YGERUK3YZULDDSFX4ZAMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REMW4YGERUK3YZULDDSFX4ZAMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:REMW4YGERUK3YZULDDSFX4ZAMX","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":"c5e5841adfb5591d3edf44c79da67f9bc54f4e9b8d5a72426909a417a33a7a19","cross_cats_sorted":["math.DS","math.OC","q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:20:27Z","title_canon_sha256":"14dcd61b0f8cfbed36538b49b155f469b3677862c6af4b6b1814269e8e651f26"},"schema_version":"1.0","source":{"id":"2605.12763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12763","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12763v1","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12763","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"REMW4YGERUK3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"REMW4YGERUK3YZUL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"REMW4YGE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c8d73a1b7c70e62ae616eea6d4d258a8404e831e7b1f10ef4925f2e86a4e6a10","target":"graph","created_at":"2026-05-18T03:09:48Z","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":"near bifurcations, we can reduce sNTK to a rank-one operator corresponding to learning in a classical normal form system, providing an analytically tractable description of the local learning geometry, even for high-dimensional recurrent systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the local linearization and decomposition into bifurcation-relevant and residual channels remain valid and dominant for the full nonlinear high-dimensional system and that the amplification of the rank-one channel is not an artifact of the specific student-teacher architecture or initialization."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Bifurcations cause sNTK to reduce to a dominant rank-one channel matching normal forms, collapsing effective rank and funneling gradient descent into critical dynamical directions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Near bifurcations, the state-space NTK reduces to a rank-one operator matching the learning geometry of a classical normal form."}],"snapshot_sha256":"830635fb0e07b626dd72ee997bdc1794b85ea416911b49ea21addf7fa4be25aa"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Rich feature learning in tasks that unfold over time often requires the model to pass through bifurcations, constituting qualitative changes in the underlying model dynamics. We develop a local theory of gradient descent near these transitions through the empirical state-space neural tangent kernel (sNTK). Our central finding is that bifurcations both dominate and simplify learning dynamics: near bifurcations, we can reduce sNTK to a rank-one operator corresponding to learning in a classical normal form system, providing an analytically tractable description of the local learning geometry, eve","authors_text":"Eric Shea-Brown, James Hazelden","cross_cats":["math.DS","math.OC","q-bio.NC"],"headline":"Near bifurcations, the state-space NTK reduces to a rank-one operator matching the learning geometry of a classical normal form.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:20:27Z","title":"State-Space NTK Collapse Near Bifurcations"},"references":{"count":137,"internal_anchors":5,"resolved_work":137,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"arXiv preprint arXiv:2311.10869 , year=","work_id":"f22c5df9-65f5-49e8-a935-6d46c04b57bb","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Deep Residual Learning for Image Recognition , author=. 2015 , eprint=","work_id":"948c9222-e716-4297-919b-917ed6f56d86","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"James Bradbury and Roy Frostig and Peter Hawkins and Matthew James Johnson and Chris Leary and Dougal Maclaurin and George Necula and Adam Paszke and Jake Vander","work_id":"f722cabc-fda6-4889-82c5-313113edc5fb","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and","work_id":"85fe8ea2-dfba-4883-bbba-2341408e0f7b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Papyan, Vardan and Han, X. Y. and Donoho, David L. , title =. Proceedings of the National Academy of Sciences , volume =. 2020 , doi =","work_id":"b8a58faa-8ff4-4caa-aec9-7f7975b434e2","year":2020}],"snapshot_sha256":"9998b4c72bb7632a5f8f05c65cb65da2b1478ce41e74ba3564c51457f9232fe4"},"source":{"id":"2605.12763","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:59:36.791495Z","id":"2d2b5b40-ca3a-411e-a1f3-df4b9c5b942e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Bifurcations cause sNTK to reduce to a dominant rank-one channel matching normal forms, collapsing effective rank and funneling gradient descent into critical dynamical directions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Near bifurcations, the state-space NTK reduces to a rank-one operator matching the learning geometry of a classical normal form.","strongest_claim":"near bifurcations, we can reduce sNTK to a rank-one operator corresponding to learning in a classical normal form system, providing an analytically tractable description of the local learning geometry, even for high-dimensional recurrent systems.","weakest_assumption":"That the local linearization and decomposition into bifurcation-relevant and residual channels remain valid and dominant for the full nonlinear high-dimensional system and that the amplification of the rank-one channel is not an artifact of the specific student-teacher architecture or initialization."}},"verdict_id":"2d2b5b40-ca3a-411e-a1f3-df4b9c5b942e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:12e30b5455cdc45a78de097ee8d6245f84b4aa40fa346f6e4bdca9c75019ab83","target":"record","created_at":"2026-05-18T03:09:48Z","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":"c5e5841adfb5591d3edf44c79da67f9bc54f4e9b8d5a72426909a417a33a7a19","cross_cats_sorted":["math.DS","math.OC","q-bio.NC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:20:27Z","title_canon_sha256":"14dcd61b0f8cfbed36538b49b155f469b3677862c6af4b6b1814269e8e651f26"},"schema_version":"1.0","source":{"id":"2605.12763","kind":"arxiv","version":1}},"canonical_sha256":"89196e60c48d15bc668b18e45bf32065efdc83b9f3e2c984a22e3269b6ded12b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89196e60c48d15bc668b18e45bf32065efdc83b9f3e2c984a22e3269b6ded12b","first_computed_at":"2026-05-18T03:09:48.335490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:48.335490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hBf4UyOcjQT+pt/3NEU2hpoGLhT1VjXgiRqjlLhs8Nu8qDo0h2AneP95Nw41sYJ+rBs0Ze2Hr2+ci5xVcLHjBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:48.336440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12e30b5455cdc45a78de097ee8d6245f84b4aa40fa346f6e4bdca9c75019ab83","sha256:c8d73a1b7c70e62ae616eea6d4d258a8404e831e7b1f10ef4925f2e86a4e6a10","sha256:3acfc8e2957ed5aaca5a199018a06a44e1431896b740638c578984c625763b50"],"state_sha256":"38b875bc1fb5191214a934ee3363fe722f705bc3d375f073e76ad7d4c85c051f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8YLlUNAuHX/bT8dMDqHUrKF8eOORzqzbAoOVVx9rKRiODGHzxRdtbdAjw/PvAM/C2a2sWaIbx2pqV+IWNlVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T21:36:50.466902Z","bundle_sha256":"b9818f38b08fbb77abc9e9d3ae3c89a8e11a7704d8593e9b1bd03e2ab3deba81"}}