{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FN2M4KOETKE6BZ4EEI74BYLTR7","short_pith_number":"pith:FN2M4KOE","canonical_record":{"source":{"id":"2304.07687","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-16T03:49:50Z","cross_cats_sorted":["cs.CL","cs.FL"],"title_canon_sha256":"04a799962be895636eae94f668d8749eb7b9a5abb9f189a9c79fa4dc143a78c4","abstract_canon_sha256":"89823f52290c56c2054f8ea05cf0bcb837bccf096921ced0f889b19d1a59c9bc"},"schema_version":"1.0"},"canonical_sha256":"2b74ce29c49a89e0e784223fc0e1738fe3d0b4cddfbab8adb95a29fdf1a1da22","source":{"kind":"arxiv","id":"2304.07687","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07687","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07687v4","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07687","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"FN2M4KOETKE6","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"pith_short_16","alias_value":"FN2M4KOETKE6BZ4E","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"pith_short_8","alias_value":"FN2M4KOE","created_at":"2026-07-05T09:01:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FN2M4KOETKE6BZ4EEI74BYLTR7","target":"record","payload":{"canonical_record":{"source":{"id":"2304.07687","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-16T03:49:50Z","cross_cats_sorted":["cs.CL","cs.FL"],"title_canon_sha256":"04a799962be895636eae94f668d8749eb7b9a5abb9f189a9c79fa4dc143a78c4","abstract_canon_sha256":"89823f52290c56c2054f8ea05cf0bcb837bccf096921ced0f889b19d1a59c9bc"},"schema_version":"1.0"},"canonical_sha256":"2b74ce29c49a89e0e784223fc0e1738fe3d0b4cddfbab8adb95a29fdf1a1da22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:24.024377Z","signature_b64":"2aPewEHF1nVSv6f6n2zp73ZN4Ib2zi6hN7TmWJZ+IUXQO2w428krTJ8ypkkDEmtdkomhugaa9oN7eny8hZu2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b74ce29c49a89e0e784223fc0e1738fe3d0b4cddfbab8adb95a29fdf1a1da22","last_reissued_at":"2026-07-05T09:01:24.023896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:24.023896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.07687","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5/QXYLPmC9G9l33KHYtKsOH02dCO/vbkxajUagGP7RzmF6bcPr8zeFVqwU9sEUVhXcwfAAPlPeHAYbaGvaOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:34:32.037573Z"},"content_sha256":"b34dff74a0c00300996b512b02b4143519484ae7f837dd28eebbd24bbbed1860","schema_version":"1.0","event_id":"sha256:b34dff74a0c00300996b512b02b4143519484ae7f837dd28eebbd24bbbed1860"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FN2M4KOETKE6BZ4EEI74BYLTR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLRegTest: A Benchmark for the Machine Learning of Regular Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.FL"],"primary_cat":"cs.LG","authors_text":"Chihiro Shibata, Cody St. Clair, Dakotah Lambert, Derek Andersen, Emily Peterson, Jeffrey Heinz, Joanne Chau, Kalina Kostyszyn, Paul Fodor, Rahul Verma, Sam van der Poel, Tiantian Gao","submitted_at":"2023-04-16T03:49:50Z","abstract_excerpt":"Synthetic datasets constructed from formal languages allow fine-grained examination of the learning and generalization capabilities of machine learning systems for sequence classification. This article presents a new benchmark for machine learning systems on sequence classification called MLRegTest, which contains training, development, and test sets from 1,800 regular languages. Different kinds of formal languages represent different kinds of long-distance dependencies, and correctly identifying long-distance dependencies in sequences is a known challenge for ML systems to generalize successf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07687","kind":"arxiv","version":4},"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/2304.07687/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":"2026-07-05T09:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bcps4zBBaACHWeeiewjv3K32rRdf943+TkS5jFULxOjRxhtFWMkNvrWFjYo/ITUhxgjN5P1Psm243mYQLUYcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:34:32.037977Z"},"content_sha256":"3109f6508fdd8bbbd755bca8e21112206d60e4ae866703fe1776028df85e2af6","schema_version":"1.0","event_id":"sha256:3109f6508fdd8bbbd755bca8e21112206d60e4ae866703fe1776028df85e2af6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FN2M4KOETKE6BZ4EEI74BYLTR7/bundle.json","state_url":"https://pith.science/pith/FN2M4KOETKE6BZ4EEI74BYLTR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FN2M4KOETKE6BZ4EEI74BYLTR7/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":"2026-07-06T07:34:32Z","links":{"resolver":"https://pith.science/pith/FN2M4KOETKE6BZ4EEI74BYLTR7","bundle":"https://pith.science/pith/FN2M4KOETKE6BZ4EEI74BYLTR7/bundle.json","state":"https://pith.science/pith/FN2M4KOETKE6BZ4EEI74BYLTR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FN2M4KOETKE6BZ4EEI74BYLTR7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FN2M4KOETKE6BZ4EEI74BYLTR7","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":"89823f52290c56c2054f8ea05cf0bcb837bccf096921ced0f889b19d1a59c9bc","cross_cats_sorted":["cs.CL","cs.FL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-16T03:49:50Z","title_canon_sha256":"04a799962be895636eae94f668d8749eb7b9a5abb9f189a9c79fa4dc143a78c4"},"schema_version":"1.0","source":{"id":"2304.07687","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.07687","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"2304.07687v4","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07687","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"FN2M4KOETKE6","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"pith_short_16","alias_value":"FN2M4KOETKE6BZ4E","created_at":"2026-07-05T09:01:24Z"},{"alias_kind":"pith_short_8","alias_value":"FN2M4KOE","created_at":"2026-07-05T09:01:24Z"}],"graph_snapshots":[{"event_id":"sha256:3109f6508fdd8bbbd755bca8e21112206d60e4ae866703fe1776028df85e2af6","target":"graph","created_at":"2026-07-05T09:01:24Z","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/2304.07687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic datasets constructed from formal languages allow fine-grained examination of the learning and generalization capabilities of machine learning systems for sequence classification. This article presents a new benchmark for machine learning systems on sequence classification called MLRegTest, which contains training, development, and test sets from 1,800 regular languages. Different kinds of formal languages represent different kinds of long-distance dependencies, and correctly identifying long-distance dependencies in sequences is a known challenge for ML systems to generalize successf","authors_text":"Chihiro Shibata, Cody St. Clair, Dakotah Lambert, Derek Andersen, Emily Peterson, Jeffrey Heinz, Joanne Chau, Kalina Kostyszyn, Paul Fodor, Rahul Verma, Sam van der Poel, Tiantian Gao","cross_cats":["cs.CL","cs.FL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-16T03:49:50Z","title":"MLRegTest: A Benchmark for the Machine Learning of Regular Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07687","kind":"arxiv","version":4},"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:b34dff74a0c00300996b512b02b4143519484ae7f837dd28eebbd24bbbed1860","target":"record","created_at":"2026-07-05T09:01:24Z","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":"89823f52290c56c2054f8ea05cf0bcb837bccf096921ced0f889b19d1a59c9bc","cross_cats_sorted":["cs.CL","cs.FL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-16T03:49:50Z","title_canon_sha256":"04a799962be895636eae94f668d8749eb7b9a5abb9f189a9c79fa4dc143a78c4"},"schema_version":"1.0","source":{"id":"2304.07687","kind":"arxiv","version":4}},"canonical_sha256":"2b74ce29c49a89e0e784223fc0e1738fe3d0b4cddfbab8adb95a29fdf1a1da22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b74ce29c49a89e0e784223fc0e1738fe3d0b4cddfbab8adb95a29fdf1a1da22","first_computed_at":"2026-07-05T09:01:24.023896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:24.023896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2aPewEHF1nVSv6f6n2zp73ZN4Ib2zi6hN7TmWJZ+IUXQO2w428krTJ8ypkkDEmtdkomhugaa9oN7eny8hZu2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:24.024377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.07687","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b34dff74a0c00300996b512b02b4143519484ae7f837dd28eebbd24bbbed1860","sha256:3109f6508fdd8bbbd755bca8e21112206d60e4ae866703fe1776028df85e2af6"],"state_sha256":"364f86d132f802981371f0d5364c7550414982f2f369fa5682a7cf0ce5e314a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTztpygWTtJplZgJpIIwD7dgN3MLnDm5erejsqeYHLd14ptSqHf9/ofk+BAgJR5wW1nlp4AFYGIw/knzXSifBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T07:34:32.040118Z","bundle_sha256":"b7ab41ce93cbbd308a4468db4478dc140f6c3a35f8b9b5f4db3bfcebfba5c1ae"}}