{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","short_pith_number":"pith:NZSAZFVW","canonical_record":{"source":{"id":"2607.03145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:36:02Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"de4ace7343ed3294366a933a3effad06001695beed4c470239fc06d14bc79ccf","abstract_canon_sha256":"4d0b6415e137f938c39a1d8dffc62810fa983fe606e66b96bc92f91db9eca20d"},"schema_version":"1.0"},"canonical_sha256":"6e640c96b6b6cbdfafcbbd28113c2f5a0a4f444c0096c5d68ac4c66d799d7ac5","source":{"kind":"arxiv","id":"2607.03145","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03145","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03145v1","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03145","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"pith_short_12","alias_value":"NZSAZFVWW3F5","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"pith_short_16","alias_value":"NZSAZFVWW3F57L6L","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"pith_short_8","alias_value":"NZSAZFVW","created_at":"2026-07-07T01:16:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:36:02Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"de4ace7343ed3294366a933a3effad06001695beed4c470239fc06d14bc79ccf","abstract_canon_sha256":"4d0b6415e137f938c39a1d8dffc62810fa983fe606e66b96bc92f91db9eca20d"},"schema_version":"1.0"},"canonical_sha256":"6e640c96b6b6cbdfafcbbd28113c2f5a0a4f444c0096c5d68ac4c66d799d7ac5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:44.496958Z","signature_b64":"M7t1aeeTS+Qdx6SQsypy6H1wuVrDAwlFMAPh9GIsYbATS5fagU5WlFCC7/28OlTJrZbKNU2sy9QT0DCCjZcDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e640c96b6b6cbdfafcbbd28113c2f5a0a4f444c0096c5d68ac4c66d799d7ac5","last_reissued_at":"2026-07-07T01:16:44.496464Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:44.496464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03145","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":"2026-07-07T01:16:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"If2EOYxc2H1FuEmmbZx1x6xR+aaCcpT22TxOSTA4jGmsCAN0R0/amupHnRwv9qk5LySaB43Y/dfI8qnOUjmoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:33:38.304735Z"},"content_sha256":"130d418e00948c7be473c628a88ac12eb66bb356050a185e9b20e9fff10e0a9a","schema_version":"1.0","event_id":"sha256:130d418e00948c7be473c628a88ac12eb66bb356050a185e9b20e9fff10e0a9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre L. M. Levada","submitted_at":"2026-07-03T09:36:02Z","abstract_excerpt":"The informativeness of a training set is as consequential as its size, yet most sampling strategies remain agnostic to the intrinsic geometry of the data distribution. We introduce CuBAS (Curvature-Based Adaptive Sampling), an information-geometric framework for adaptive data selection in supervised classification, grounded in the q-state Potts Markov random field (MRF) model. The central insight is that a labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geomet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03145","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.03145/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T01:16:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhsQeB/wWOa3Upk2PMEd63tXcvI4DAlf2Wjltkmw76dgO+M9klsq45iFcT0qSJvkTecctmc9YADQ/6bx4hsYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:33:38.305276Z"},"content_sha256":"d0c66d430dcb86afa878c19e2a17c19c06b73cc99a27d927a62e880dc5868704","schema_version":"1.0","event_id":"sha256:d0c66d430dcb86afa878c19e2a17c19c06b73cc99a27d927a62e880dc5868704"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.patcog.2019.07.004.Dengyong) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"ISSN 0031-3203. doi: https://doi.org/10.1016/j. patcog.2019.07.004. Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, and Bernhard Schölkopf. Learning with local and global consistency. InProceedings of the 17th International","arxiv_id":"2607.03145","detector":"doi_compliance","evidence":{"ref_index":12,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"ISSN 0031-3203. doi: https://doi.org/10.1016/j. patcog.2019.07.004. Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, and Bernhard Schölkopf. Learning with local and global consistency. InProceedings of the 17th International","reconstructed_doi":"10.1016/j.patcog.2019.07.004.Dengyong"},"severity":"advisory","ref_index":12,"audited_at":"2026-07-12T04:42:18.968116Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.patcog.2019.07.004.Dengyong","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"8fea4ddc4d00aa45250914306cc1679f716a5ef22b0ec837e67678b0f949f340","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12490,"payload_sha256":"c8f588ebb9d6ac4ffa3f1b7f813514a66dc891f2817a4c3cff271710810190d9","signature_b64":"m3GvBIPn/Eh0n7KrQ7yQ8ldR+LifR+4itZqR58VeXUMVSSt7B0AOO0PC1VQIvHFf978jMLnLmyVJsj5+MP+RAA==","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":"2026-07-12T04:47:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcRRMX6dD0KtYCDwvkxyrEl6ShjqO9IAZrt//5heFy3cVBS6f4RnN3CvN3r5x5EtjnvVFPf/Q9QS0EpoDNG2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:33:38.309417Z"},"content_sha256":"bc62fb2d38bc53ab7075ee89a4944d984b35ad8933c7d5450cd1fe22382a4574","schema_version":"1.0","event_id":"sha256:bc62fb2d38bc53ab7075ee89a4944d984b35ad8933c7d5450cd1fe22382a4574"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1002/aaai.12210.Shun-ichi) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: https://doi.org/10.1002/aaai. 12210. Shun-ichi Amari.Information Geometry and Its Applications. Springer,","arxiv_id":"2607.03145","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: https://doi.org/10.1002/aaai. 12210. Shun-ichi Amari.Information Geometry and Its Applications. Springer,","reconstructed_doi":"10.1002/aaai.12210.Shun-ichi"},"severity":"advisory","ref_index":6,"audited_at":"2026-07-12T04:42:18.968116Z","event_type":"pith.integrity.v1","detected_doi":"10.1002/aaai.12210.Shun-ichi","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"9e2edc6a7f90a53be4be4e0e6cfc0f17d83e8e4526d8a9eb344dc2510fd7c4a7","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12489,"payload_sha256":"8a26f323d5693164edcd466a7bdc9f29524c4b6f5555e59cb57a9156bf53c880","signature_b64":"AJYROV0XC1OIfwLksZA0R5BY26EzXg0rTVSSib3P2WXAgVigAAW7aEEsBVXWrKrO4NffX5LnmYKORlRuUgQKCw==","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":"2026-07-12T04:47:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6HctEU3pUpnoI+3OSYN6jji6UVUG3ujbzNXp+O3v+/slpXaEJrG2164REqPKu9IsKSC7OE9JMu8RGEASbl4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:33:38.309871Z"},"content_sha256":"565ab7687d6293b5d7737d8f48f17ae748572caaedc74a92d0ed2329e117cb95","schema_version":"1.0","event_id":"sha256:565ab7687d6293b5d7737d8f48f17ae748572caaedc74a92d0ed2329e117cb95"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/MSP.2017.2693418.Mathilde) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.1109/MSP.2017. 2693418. Mathilde Papillon, Sophia Sanborn, Johan Mathe, Louisa Cornelis, Abby Bertics, Domas Buracas, Hansen J. Lillemark, Christian Shewmake, Fatih Dinc, Xavier Pennec, and Nina Miolane. Beyond Euclid: An illustrate","arxiv_id":"2607.03145","detector":"doi_compliance","evidence":{"ref_index":4,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.1109/MSP.2017. 2693418. Mathilde Papillon, Sophia Sanborn, Johan Mathe, Louisa Cornelis, Abby Bertics, Domas Buracas, Hansen J. Lillemark, Christian Shewmake, Fatih Dinc, Xavier Pennec, and Nina Miolane. Beyond Euclid: An illustrate","reconstructed_doi":"10.1109/MSP.2017.2693418.Mathilde"},"severity":"advisory","ref_index":4,"audited_at":"2026-07-12T04:42:18.968116Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/MSP.2017.2693418.Mathilde","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"a1e2b92a61f7cccabe97c4777937566d175be66d7c2ad47f506558a9aaf246eb","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12488,"payload_sha256":"d8050550814dd626c37820c21ef701b056affc3457563d1d53e64ff835e12b31","signature_b64":"8sZ8Rka9Zq2Xmu1GPl+or0hWcICHjVJ1H23Kqr6hd42DYpCCpxBcOXIq/x1zD2GhtpC+Ii4NCDwiCqGKGJxbCA==","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":"2026-07-12T04:47:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7D38AKsNj/IUWnkp6eoIX8gaZuhoRy4JqGlE0T5435eHUW4j+UzpFpnN9VaAYeg+EL1eDfEG/EAx/J5HuSYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:33:38.310250Z"},"content_sha256":"424307e4efd2fb59c299d17e2765f5cf43c907049d552684b523c17c8235294e","schema_version":"1.0","event_id":"sha256:424307e4efd2fb59c299d17e2765f5cf43c907049d552684b523c17c8235294e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZSAZFVWW3F57L6LXUUBCPBPLI/bundle.json","state_url":"https://pith.science/pith/NZSAZFVWW3F57L6LXUUBCPBPLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZSAZFVWW3F57L6LXUUBCPBPLI/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":"2026-08-09T21:33:38Z","links":{"resolver":"https://pith.science/pith/NZSAZFVWW3F57L6LXUUBCPBPLI","bundle":"https://pith.science/pith/NZSAZFVWW3F57L6LXUUBCPBPLI/bundle.json","state":"https://pith.science/pith/NZSAZFVWW3F57L6LXUUBCPBPLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZSAZFVWW3F57L6LXUUBCPBPLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NZSAZFVWW3F57L6LXUUBCPBPLI","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4d0b6415e137f938c39a1d8dffc62810fa983fe606e66b96bc92f91db9eca20d","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:36:02Z","title_canon_sha256":"de4ace7343ed3294366a933a3effad06001695beed4c470239fc06d14bc79ccf"},"schema_version":"1.0","source":{"id":"2607.03145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03145","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03145v1","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03145","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"pith_short_12","alias_value":"NZSAZFVWW3F5","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"pith_short_16","alias_value":"NZSAZFVWW3F57L6L","created_at":"2026-07-07T01:16:44Z"},{"alias_kind":"pith_short_8","alias_value":"NZSAZFVW","created_at":"2026-07-07T01:16:44Z"}],"graph_snapshots":[{"event_id":"sha256:d0c66d430dcb86afa878c19e2a17c19c06b73cc99a27d927a62e880dc5868704","target":"graph","created_at":"2026-07-07T01:16:44Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.03145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The informativeness of a training set is as consequential as its size, yet most sampling strategies remain agnostic to the intrinsic geometry of the data distribution. We introduce CuBAS (Curvature-Based Adaptive Sampling), an information-geometric framework for adaptive data selection in supervised classification, grounded in the q-state Potts Markov random field (MRF) model. The central insight is that a labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geomet","authors_text":"Alexandre L. M. Levada","cross_cats":["cs.AI","cs.CV","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:36:02Z","title":"CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03145","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:130d418e00948c7be473c628a88ac12eb66bb356050a185e9b20e9fff10e0a9a","target":"record","created_at":"2026-07-07T01:16:44Z","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":"4d0b6415e137f938c39a1d8dffc62810fa983fe606e66b96bc92f91db9eca20d","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:36:02Z","title_canon_sha256":"de4ace7343ed3294366a933a3effad06001695beed4c470239fc06d14bc79ccf"},"schema_version":"1.0","source":{"id":"2607.03145","kind":"arxiv","version":1}},"canonical_sha256":"6e640c96b6b6cbdfafcbbd28113c2f5a0a4f444c0096c5d68ac4c66d799d7ac5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e640c96b6b6cbdfafcbbd28113c2f5a0a4f444c0096c5d68ac4c66d799d7ac5","first_computed_at":"2026-07-07T01:16:44.496464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:44.496464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M7t1aeeTS+Qdx6SQsypy6H1wuVrDAwlFMAPh9GIsYbATS5fagU5WlFCC7/28OlTJrZbKNU2sy9QT0DCCjZcDDg==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:44.496958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03145","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:424307e4efd2fb59c299d17e2765f5cf43c907049d552684b523c17c8235294e","sha256:565ab7687d6293b5d7737d8f48f17ae748572caaedc74a92d0ed2329e117cb95","sha256:bc62fb2d38bc53ab7075ee89a4944d984b35ad8933c7d5450cd1fe22382a4574"]}],"invalid_events":[],"applied_event_ids":["sha256:130d418e00948c7be473c628a88ac12eb66bb356050a185e9b20e9fff10e0a9a","sha256:d0c66d430dcb86afa878c19e2a17c19c06b73cc99a27d927a62e880dc5868704"],"state_sha256":"fb052edbf1b0e70896beb59c4651ff8a3dd6912266113cd447c27713eeb03a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbn+h7aZlCOGW4l0SPHUygZ1aiAiQiCtQVN3HKQR3wkZoOdsBjIUPkwyx/hz5EM1Gl7Xir5dX0p0qbq9TcUlBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:33:38.313539Z","bundle_sha256":"946ae1a2aa3ff8455bd4959456b3e6064f19e86673149b7dad12c9990610e288"}}