{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:753BPG5QMV6WSXELCZ2OFE7V6C","short_pith_number":"pith:753BPG5Q","canonical_record":{"source":{"id":"2407.07890","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T17:57:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9ef4ef72eba68fc147a2983407f6ae2f94eec644981e7e9eef82e06b950d0cfa","abstract_canon_sha256":"b2c14cfae54cb7bec3177bdc96407bf3ef46f57d089ac8705156d3d9780304ac"},"schema_version":"1.0"},"canonical_sha256":"ff76179bb0657d695c8b1674e293f5f09d9d3ea56c13bab2b092aa15ae433f58","source":{"kind":"arxiv","id":"2407.07890","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07890","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07890v3","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07890","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_12","alias_value":"753BPG5QMV6W","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_16","alias_value":"753BPG5QMV6WSXEL","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_8","alias_value":"753BPG5Q","created_at":"2026-07-05T10:51:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:753BPG5QMV6WSXELCZ2OFE7V6C","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07890","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T17:57:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9ef4ef72eba68fc147a2983407f6ae2f94eec644981e7e9eef82e06b950d0cfa","abstract_canon_sha256":"b2c14cfae54cb7bec3177bdc96407bf3ef46f57d089ac8705156d3d9780304ac"},"schema_version":"1.0"},"canonical_sha256":"ff76179bb0657d695c8b1674e293f5f09d9d3ea56c13bab2b092aa15ae433f58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:23.863861Z","signature_b64":"fg9EeGk/iQb6yzJ8QZWObelLWwBfQaG0vxkifUr7XZ1fXE1ZSLGowpFN6O1q7k0boEgEB5vaXykGTbJkTTniBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff76179bb0657d695c8b1674e293f5f09d9d3ea56c13bab2b092aa15ae433f58","last_reissued_at":"2026-07-05T10:51:23.863357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:23.863357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07890","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNPwoYT+sGqIcChOqIh1wjxOYmz2Aw5aYKlyxDPywtTbk4QUhRwH3fMRU82/sPUpe8yj7rMO85and+M9Oq87Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:13:07.973264Z"},"content_sha256":"4743ea0cdf7452302de7f2302b3ad7c2e5cb597a3cc557ba1d2e0d979c76d197","schema_version":"1.0","event_id":"sha256:4743ea0cdf7452302de7f2302b3ad7c2e5cb597a3cc557ba1d2e0d979c76d197"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:753BPG5QMV6WSXELCZ2OFE7V6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training on the Test Task Confounds Evaluation and Emergence","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Florian E. Dorner, Moritz Hardt, Ricardo Dominguez-Olmedo","submitted_at":"2024-07-10T17:57:58Z","abstract_excerpt":"We study a fundamental problem in the evaluation of large language models that we call training on the test task. Unlike wrongful practices like training on the test data, leakage, or data contamination, training on the test task is not a malpractice. Rather, the term describes a growing set of practices that utilize knowledge about evaluation tasks at training time. We demonstrate that training on the test task confounds both relative model evaluations and claims about emergent capabilities. We argue that the seeming superiority of one model family over another may be explained by a different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07890","kind":"arxiv","version":3},"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/2407.07890/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":"2026-07-05T10:51:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7iE9zQ/iPSVtS8H1wy0dDCvZ1ofqXSE5FcvGPBW2CBCpPKwLsxWNt+0juAuvD5YznlQIUvYBYuk+3iK+Y5z1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:13:07.973843Z"},"content_sha256":"77c268874ca0407169eaae397701ddc5040287319d3e9a0fdf0ef6e003c9d659","schema_version":"1.0","event_id":"sha256:77c268874ca0407169eaae397701ddc5040287319d3e9a0fdf0ef6e003c9d659"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/753BPG5QMV6WSXELCZ2OFE7V6C/bundle.json","state_url":"https://pith.science/pith/753BPG5QMV6WSXELCZ2OFE7V6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/753BPG5QMV6WSXELCZ2OFE7V6C/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":"2026-08-08T23:13:07Z","links":{"resolver":"https://pith.science/pith/753BPG5QMV6WSXELCZ2OFE7V6C","bundle":"https://pith.science/pith/753BPG5QMV6WSXELCZ2OFE7V6C/bundle.json","state":"https://pith.science/pith/753BPG5QMV6WSXELCZ2OFE7V6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/753BPG5QMV6WSXELCZ2OFE7V6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:753BPG5QMV6WSXELCZ2OFE7V6C","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":"b2c14cfae54cb7bec3177bdc96407bf3ef46f57d089ac8705156d3d9780304ac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T17:57:58Z","title_canon_sha256":"9ef4ef72eba68fc147a2983407f6ae2f94eec644981e7e9eef82e06b950d0cfa"},"schema_version":"1.0","source":{"id":"2407.07890","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07890","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07890v3","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07890","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_12","alias_value":"753BPG5QMV6W","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_16","alias_value":"753BPG5QMV6WSXEL","created_at":"2026-07-05T10:51:23Z"},{"alias_kind":"pith_short_8","alias_value":"753BPG5Q","created_at":"2026-07-05T10:51:23Z"}],"graph_snapshots":[{"event_id":"sha256:77c268874ca0407169eaae397701ddc5040287319d3e9a0fdf0ef6e003c9d659","target":"graph","created_at":"2026-07-05T10:51:23Z","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/2407.07890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a fundamental problem in the evaluation of large language models that we call training on the test task. Unlike wrongful practices like training on the test data, leakage, or data contamination, training on the test task is not a malpractice. Rather, the term describes a growing set of practices that utilize knowledge about evaluation tasks at training time. We demonstrate that training on the test task confounds both relative model evaluations and claims about emergent capabilities. We argue that the seeming superiority of one model family over another may be explained by a different","authors_text":"Florian E. Dorner, Moritz Hardt, Ricardo Dominguez-Olmedo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T17:57:58Z","title":"Training on the Test Task Confounds Evaluation and Emergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07890","kind":"arxiv","version":3},"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":"sha256:4743ea0cdf7452302de7f2302b3ad7c2e5cb597a3cc557ba1d2e0d979c76d197","target":"record","created_at":"2026-07-05T10:51:23Z","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":"b2c14cfae54cb7bec3177bdc96407bf3ef46f57d089ac8705156d3d9780304ac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T17:57:58Z","title_canon_sha256":"9ef4ef72eba68fc147a2983407f6ae2f94eec644981e7e9eef82e06b950d0cfa"},"schema_version":"1.0","source":{"id":"2407.07890","kind":"arxiv","version":3}},"canonical_sha256":"ff76179bb0657d695c8b1674e293f5f09d9d3ea56c13bab2b092aa15ae433f58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff76179bb0657d695c8b1674e293f5f09d9d3ea56c13bab2b092aa15ae433f58","first_computed_at":"2026-07-05T10:51:23.863357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:23.863357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fg9EeGk/iQb6yzJ8QZWObelLWwBfQaG0vxkifUr7XZ1fXE1ZSLGowpFN6O1q7k0boEgEB5vaXykGTbJkTTniBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:23.863861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07890","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4743ea0cdf7452302de7f2302b3ad7c2e5cb597a3cc557ba1d2e0d979c76d197","sha256:77c268874ca0407169eaae397701ddc5040287319d3e9a0fdf0ef6e003c9d659"],"state_sha256":"ad0a0336f740a03b6f311416d5023c18e88fa92f16559a2fe89023b3771c4580"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ivg1XTK6bNTRFyPQfzSZU1dawNN9bvF+SmBQ4V4T6QIDKZPZOWhMIjpmJYa20IU5VDIa+pvouu1zEMAOj+pODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:13:07.977933Z","bundle_sha256":"12fbf8724da96cf5f29c3be4455084698ce40067a096953bf175d4f496dc4235"}}