{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PGSXDFNHJLRBSFBMWXHUJB62EB","short_pith_number":"pith:PGSXDFNH","canonical_record":{"source":{"id":"1902.04699","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T01:48:58Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"b611e99442f7e3a3cf3a994b99ff3af3c331a8795376ca9b456ffce4c819faf9","abstract_canon_sha256":"e3106e16f1e195024078ea6485bb240109508024c6bb5668dc9f0558ced64a6b"},"schema_version":"1.0"},"canonical_sha256":"79a57195a74ae219142cb5cf4487da20784605438d7c252d33b908e825565259","source":{"kind":"arxiv","id":"1902.04699","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04699","created_at":"2026-05-17T23:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04699v2","created_at":"2026-05-17T23:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04699","created_at":"2026-05-17T23:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"PGSXDFNHJLRB","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PGSXDFNHJLRBSFBM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PGSXDFNH","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PGSXDFNHJLRBSFBMWXHUJB62EB","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04699","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T01:48:58Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"b611e99442f7e3a3cf3a994b99ff3af3c331a8795376ca9b456ffce4c819faf9","abstract_canon_sha256":"e3106e16f1e195024078ea6485bb240109508024c6bb5668dc9f0558ced64a6b"},"schema_version":"1.0"},"canonical_sha256":"79a57195a74ae219142cb5cf4487da20784605438d7c252d33b908e825565259","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:25.811958Z","signature_b64":"YMgkiJbU4fZL/k+UjC7XxySXETMUjG3T4Gl+1657/MvmQmSKFtxGr6g/CGn7a9gXim2iX6EfXbYOqHovEPZxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a57195a74ae219142cb5cf4487da20784605438d7c252d33b908e825565259","last_reissued_at":"2026-05-17T23:45:25.811566Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:25.811566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04699","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kaVRLBGrXv/jgR5vWok0CiFb9pUINnYW+ZHYtU5Q/CMgaQdzVLhS3KdzMWPjXppDSPABRwVpj4Ti1i+rsMEhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:54:26.059194Z"},"content_sha256":"2103e343abaf7f412c55bf0155c3d97907fd25fe39025d5d2a35ff4952b566c0","schema_version":"1.0","event_id":"sha256:2103e343abaf7f412c55bf0155c3d97907fd25fe39025d5d2a35ff4952b566c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PGSXDFNHJLRBSFBMWXHUJB62EB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differential Description Length for Hyperparameter Selection in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Host-Madsen, June Zhang, Mojtaba Abolfazli","submitted_at":"2019-02-13T01:48:58Z","abstract_excerpt":"This paper introduces a new method for model selection and more generally hyperparameter selection in machine learning. Minimum description length (MDL) is an established method for model selection, which is however not directly aimed at minimizing generalization error, which is often the primary goal in machine learning. The paper demonstrates a relationship between generalization error and a difference of description lengths of the training data; we call this difference differential description length (DDL). This allows prediction of generalization error from the training data alone by perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04699","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCAWQ6uelH2hg82wbkyE6nwXkANtXVfMK+GMkDA1V2LmZpXZ6KEZqSmkDLEAJpveZ4Z7ORazxnKiUH6JqMVgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:54:26.059774Z"},"content_sha256":"23ca717ad1f7081de57c67be6f175dadb629ca83a0c7c31604bed55b52425fc4","schema_version":"1.0","event_id":"sha256:23ca717ad1f7081de57c67be6f175dadb629ca83a0c7c31604bed55b52425fc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PGSXDFNHJLRBSFBMWXHUJB62EB/bundle.json","state_url":"https://pith.science/pith/PGSXDFNHJLRBSFBMWXHUJB62EB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PGSXDFNHJLRBSFBMWXHUJB62EB/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":"2026-05-26T17:54:26Z","links":{"resolver":"https://pith.science/pith/PGSXDFNHJLRBSFBMWXHUJB62EB","bundle":"https://pith.science/pith/PGSXDFNHJLRBSFBMWXHUJB62EB/bundle.json","state":"https://pith.science/pith/PGSXDFNHJLRBSFBMWXHUJB62EB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PGSXDFNHJLRBSFBMWXHUJB62EB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PGSXDFNHJLRBSFBMWXHUJB62EB","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":"e3106e16f1e195024078ea6485bb240109508024c6bb5668dc9f0558ced64a6b","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T01:48:58Z","title_canon_sha256":"b611e99442f7e3a3cf3a994b99ff3af3c331a8795376ca9b456ffce4c819faf9"},"schema_version":"1.0","source":{"id":"1902.04699","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04699","created_at":"2026-05-17T23:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04699v2","created_at":"2026-05-17T23:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04699","created_at":"2026-05-17T23:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"PGSXDFNHJLRB","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PGSXDFNHJLRBSFBM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PGSXDFNH","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:23ca717ad1f7081de57c67be6f175dadb629ca83a0c7c31604bed55b52425fc4","target":"graph","created_at":"2026-05-17T23:45:25Z","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"},"paper":{"abstract_excerpt":"This paper introduces a new method for model selection and more generally hyperparameter selection in machine learning. Minimum description length (MDL) is an established method for model selection, which is however not directly aimed at minimizing generalization error, which is often the primary goal in machine learning. The paper demonstrates a relationship between generalization error and a difference of description lengths of the training data; we call this difference differential description length (DDL). This allows prediction of generalization error from the training data alone by perfo","authors_text":"Anders Host-Madsen, June Zhang, Mojtaba Abolfazli","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T01:48:58Z","title":"Differential Description Length for Hyperparameter Selection in Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04699","kind":"arxiv","version":2},"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":"sha256:2103e343abaf7f412c55bf0155c3d97907fd25fe39025d5d2a35ff4952b566c0","target":"record","created_at":"2026-05-17T23:45:25Z","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":"e3106e16f1e195024078ea6485bb240109508024c6bb5668dc9f0558ced64a6b","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T01:48:58Z","title_canon_sha256":"b611e99442f7e3a3cf3a994b99ff3af3c331a8795376ca9b456ffce4c819faf9"},"schema_version":"1.0","source":{"id":"1902.04699","kind":"arxiv","version":2}},"canonical_sha256":"79a57195a74ae219142cb5cf4487da20784605438d7c252d33b908e825565259","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79a57195a74ae219142cb5cf4487da20784605438d7c252d33b908e825565259","first_computed_at":"2026-05-17T23:45:25.811566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:25.811566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YMgkiJbU4fZL/k+UjC7XxySXETMUjG3T4Gl+1657/MvmQmSKFtxGr6g/CGn7a9gXim2iX6EfXbYOqHovEPZxDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:25.811958Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04699","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2103e343abaf7f412c55bf0155c3d97907fd25fe39025d5d2a35ff4952b566c0","sha256:23ca717ad1f7081de57c67be6f175dadb629ca83a0c7c31604bed55b52425fc4"],"state_sha256":"04d19b45c08efd5a1254c7f153765bf1b8af39c706ca18dd3241926e4f349794"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uE6Dq8CPOBL8ahJ88ajzLUX8m07RU7iTTEFRUJ9GRlvmwzc2cXPIZ5X0Q5XW+zpH5K/0oArl8NbzJp8jJH61DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:54:26.063062Z","bundle_sha256":"3a38863585ca1d5ea7e95288e0ff7d6844f7adb2603f1cca9bdec25eb7cb5afa"}}