{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GKKKN2GZP23IE5UKWRYL3NCGX4","short_pith_number":"pith:GKKKN2GZ","canonical_record":{"source":{"id":"1803.09578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-26T13:35:14Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"8435b2f05420017354153bb3288e159ae301ca6905844d1f40c8ec86cd5c9890","abstract_canon_sha256":"bdcf8d2805e54c091688f472bdc07ccc32f3a278ff39ffa8bb7e66fc27d4e4f1"},"schema_version":"1.0"},"canonical_sha256":"3294a6e8d97eb682768ab470bdb446bf11f61b3f40d0b91cf91f80582f536fa8","source":{"kind":"arxiv","id":"1803.09578","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09578","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09578v1","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09578","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"GKKKN2GZP23I","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GKKKN2GZP23IE5UK","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GKKKN2GZ","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GKKKN2GZP23IE5UKWRYL3NCGX4","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-26T13:35:14Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"8435b2f05420017354153bb3288e159ae301ca6905844d1f40c8ec86cd5c9890","abstract_canon_sha256":"bdcf8d2805e54c091688f472bdc07ccc32f3a278ff39ffa8bb7e66fc27d4e4f1"},"schema_version":"1.0"},"canonical_sha256":"3294a6e8d97eb682768ab470bdb446bf11f61b3f40d0b91cf91f80582f536fa8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:11.057130Z","signature_b64":"fpwKTcWRDnhs+QpiTYdWuqyx1KfHJHKa74Zg/5uPecB2A/akuS+MYfXzALHreBTuIvCZi/0PxmEmPBkB4LYSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3294a6e8d97eb682768ab470bdb446bf11f61b3f40d0b91cf91f80582f536fa8","last_reissued_at":"2026-05-18T00:20:11.056433Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:11.056433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09578","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":"2026-05-18T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ft3GjKZ2jj7gig1hq/GispsqlZhsBn4+RLuNqHtwujSRZvFArv3tNTlJEk92E4mhXcFHY6uVngQP69/lsbwEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:39:52.263286Z"},"content_sha256":"ccb14fe779f89c886e929ffcaaa9684882288fbb2e186504dc02b700d238627c","schema_version":"1.0","event_id":"sha256:ccb14fe779f89c886e929ffcaaa9684882288fbb2e186504dc02b700d238627c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GKKKN2GZP23IE5UKWRYL3NCGX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Iryna Gurevych, Nils Reimers","submitted_at":"2018-03-26T13:35:14Z","abstract_excerpt":"Developing state-of-the-art approaches for specific tasks is a major driving force in our research community. Depending on the prestige of the task, publishing it can come along with a lot of visibility. The question arises how reliable are our evaluation methodologies to compare approaches?\n  One common methodology to identify the state-of-the-art is to partition data into a train, a development and a test set. Researchers can train and tune their approach on some part of the dataset and then select the model that worked best on the development set for a final evaluation on unseen test data. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09578","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":""},"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":"2026-05-18T00:20:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"to4IXzN2TUiSmpRyUN5wwa+zfwDhl/Nqr/JkWvvOpcGcNRqj9j1Z42OdTSm8mvQs89yIOwJ3QGFIm+gRwDGUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:39:52.263644Z"},"content_sha256":"8d142f045dbb3270667129d4dac5c394f540b592bb8d81d4080217acc90ea6ad","schema_version":"1.0","event_id":"sha256:8d142f045dbb3270667129d4dac5c394f540b592bb8d81d4080217acc90ea6ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKKKN2GZP23IE5UKWRYL3NCGX4/bundle.json","state_url":"https://pith.science/pith/GKKKN2GZP23IE5UKWRYL3NCGX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKKKN2GZP23IE5UKWRYL3NCGX4/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":"2026-06-02T17:39:52Z","links":{"resolver":"https://pith.science/pith/GKKKN2GZP23IE5UKWRYL3NCGX4","bundle":"https://pith.science/pith/GKKKN2GZP23IE5UKWRYL3NCGX4/bundle.json","state":"https://pith.science/pith/GKKKN2GZP23IE5UKWRYL3NCGX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKKKN2GZP23IE5UKWRYL3NCGX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GKKKN2GZP23IE5UKWRYL3NCGX4","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":"bdcf8d2805e54c091688f472bdc07ccc32f3a278ff39ffa8bb7e66fc27d4e4f1","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-26T13:35:14Z","title_canon_sha256":"8435b2f05420017354153bb3288e159ae301ca6905844d1f40c8ec86cd5c9890"},"schema_version":"1.0","source":{"id":"1803.09578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09578","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09578v1","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09578","created_at":"2026-05-18T00:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"GKKKN2GZP23I","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GKKKN2GZP23IE5UK","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GKKKN2GZ","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:8d142f045dbb3270667129d4dac5c394f540b592bb8d81d4080217acc90ea6ad","target":"graph","created_at":"2026-05-18T00:20:11Z","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":"Developing state-of-the-art approaches for specific tasks is a major driving force in our research community. Depending on the prestige of the task, publishing it can come along with a lot of visibility. The question arises how reliable are our evaluation methodologies to compare approaches?\n  One common methodology to identify the state-of-the-art is to partition data into a train, a development and a test set. Researchers can train and tune their approach on some part of the dataset and then select the model that worked best on the development set for a final evaluation on unseen test data. ","authors_text":"Iryna Gurevych, Nils Reimers","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-26T13:35:14Z","title":"Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09578","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:ccb14fe779f89c886e929ffcaaa9684882288fbb2e186504dc02b700d238627c","target":"record","created_at":"2026-05-18T00:20:11Z","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":"bdcf8d2805e54c091688f472bdc07ccc32f3a278ff39ffa8bb7e66fc27d4e4f1","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-03-26T13:35:14Z","title_canon_sha256":"8435b2f05420017354153bb3288e159ae301ca6905844d1f40c8ec86cd5c9890"},"schema_version":"1.0","source":{"id":"1803.09578","kind":"arxiv","version":1}},"canonical_sha256":"3294a6e8d97eb682768ab470bdb446bf11f61b3f40d0b91cf91f80582f536fa8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3294a6e8d97eb682768ab470bdb446bf11f61b3f40d0b91cf91f80582f536fa8","first_computed_at":"2026-05-18T00:20:11.056433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:11.056433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fpwKTcWRDnhs+QpiTYdWuqyx1KfHJHKa74Zg/5uPecB2A/akuS+MYfXzALHreBTuIvCZi/0PxmEmPBkB4LYSBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:11.057130Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccb14fe779f89c886e929ffcaaa9684882288fbb2e186504dc02b700d238627c","sha256:8d142f045dbb3270667129d4dac5c394f540b592bb8d81d4080217acc90ea6ad"],"state_sha256":"6edf01758174a52926f5d45bb932d3c44a2d6fb80b7cc8bae722a1c289400749"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DM6nunU2FVc1YklIxYA32AhFPIqgbqO51maDVilQPJ5GDSJNlbYMs9LA6bo6683f2761Q5nFg1cI7KwRSlReAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T17:39:52.265523Z","bundle_sha256":"4f5f3d947ae31870e4f75692602e89fddbcf0a7c7194d67e09acbb74fcc96a79"}}