{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EDVAROFNGNN2XTAR2B632QQTXM","short_pith_number":"pith:EDVAROFN","canonical_record":{"source":{"id":"2502.05085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T17:01:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f37992a8dbee52a5848a85daaf8d29f770257a610dacb7699f54e74bbbdba39","abstract_canon_sha256":"0251e8dbfdf1406d936b969aa2f7dc4808dc4d5374524e2de9feb09f53186557"},"schema_version":"1.0"},"canonical_sha256":"20ea08b8ad335babcc11d07dbd4213bb0b7e4d1006fb4e10296d48c39a07bb0b","source":{"kind":"arxiv","id":"2502.05085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05085","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05085v1","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05085","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"EDVAROFNGNN2","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"EDVAROFNGNN2XTAR","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"EDVAROFN","created_at":"2026-07-05T10:11:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EDVAROFNGNN2XTAR2B632QQTXM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.05085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T17:01:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f37992a8dbee52a5848a85daaf8d29f770257a610dacb7699f54e74bbbdba39","abstract_canon_sha256":"0251e8dbfdf1406d936b969aa2f7dc4808dc4d5374524e2de9feb09f53186557"},"schema_version":"1.0"},"canonical_sha256":"20ea08b8ad335babcc11d07dbd4213bb0b7e4d1006fb4e10296d48c39a07bb0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:03.013555Z","signature_b64":"dIWr7BEBhA+ZSCVABBh9xKbrDh8p5kcq64k8YV/B6Bb76S9OoyFnrldG8rffVklISlePxKd78OK4milHSOPhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20ea08b8ad335babcc11d07dbd4213bb0b7e4d1006fb4e10296d48c39a07bb0b","last_reissued_at":"2026-07-05T10:11:03.012999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:03.012999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.05085","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":"2026-07-05T10:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iU4pU5dNELtPBcQjqvabkQ+VaHrUZjMETGwnwwfX7zjrRijRg2HRHIw6r12hTpi5+Sl2KflUqpWyJnhSIqjeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T23:17:48.145512Z"},"content_sha256":"ee42d89abc3d9f4e4a65f2efa3afae7717a1d9e6cd656b60866fc4950d1e0f34","schema_version":"1.0","event_id":"sha256:ee42d89abc3d9f4e4a65f2efa3afae7717a1d9e6cd656b60866fc4950d1e0f34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EDVAROFNGNN2XTAR2B632QQTXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causality can systematically address the monsters under the bench(marks)","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Felix Leeb, Zhijing Jin","submitted_at":"2025-02-07T17:01:37Z","abstract_excerpt":"Effective and reliable evaluation is essential for advancing empirical machine learning. However, the increasing accessibility of generalist models and the progress towards ever more complex, high-level tasks make systematic evaluation more challenging. Benchmarks are plagued by various biases, artifacts, or leakage, while models may behave unreliably due to poorly explored failure modes. Haphazard treatments and inconsistent formulations of such \"monsters\" can contribute to a duplication of efforts, a lack of trust in results, and unsupported inferences. In this position paper, we argue causa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05085","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/2502.05085/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":"2026-07-05T10:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUu/ZogL0Q3wgvCHFjTUwEuj/rYevvN9SuZyv1nPTQaRezw4jsnSnGz6XMDinANmr7Hy6paleIeb/xxdIdKJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T23:17:48.145896Z"},"content_sha256":"2f044a16095948f1c39a9b8d769a4e667634971561f18fc77eb1c6616980d75e","schema_version":"1.0","event_id":"sha256:2f044a16095948f1c39a9b8d769a4e667634971561f18fc77eb1c6616980d75e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDVAROFNGNN2XTAR2B632QQTXM/bundle.json","state_url":"https://pith.science/pith/EDVAROFNGNN2XTAR2B632QQTXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDVAROFNGNN2XTAR2B632QQTXM/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":"2026-08-03T23:17:48Z","links":{"resolver":"https://pith.science/pith/EDVAROFNGNN2XTAR2B632QQTXM","bundle":"https://pith.science/pith/EDVAROFNGNN2XTAR2B632QQTXM/bundle.json","state":"https://pith.science/pith/EDVAROFNGNN2XTAR2B632QQTXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDVAROFNGNN2XTAR2B632QQTXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EDVAROFNGNN2XTAR2B632QQTXM","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":"0251e8dbfdf1406d936b969aa2f7dc4808dc4d5374524e2de9feb09f53186557","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T17:01:37Z","title_canon_sha256":"8f37992a8dbee52a5848a85daaf8d29f770257a610dacb7699f54e74bbbdba39"},"schema_version":"1.0","source":{"id":"2502.05085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05085","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05085v1","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05085","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"EDVAROFNGNN2","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"EDVAROFNGNN2XTAR","created_at":"2026-07-05T10:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"EDVAROFN","created_at":"2026-07-05T10:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:2f044a16095948f1c39a9b8d769a4e667634971561f18fc77eb1c6616980d75e","target":"graph","created_at":"2026-07-05T10:11:03Z","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/2502.05085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective and reliable evaluation is essential for advancing empirical machine learning. However, the increasing accessibility of generalist models and the progress towards ever more complex, high-level tasks make systematic evaluation more challenging. Benchmarks are plagued by various biases, artifacts, or leakage, while models may behave unreliably due to poorly explored failure modes. Haphazard treatments and inconsistent formulations of such \"monsters\" can contribute to a duplication of efforts, a lack of trust in results, and unsupported inferences. In this position paper, we argue causa","authors_text":"Bernhard Sch\\\"olkopf, Felix Leeb, Zhijing Jin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T17:01:37Z","title":"Causality can systematically address the monsters under the bench(marks)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05085","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:ee42d89abc3d9f4e4a65f2efa3afae7717a1d9e6cd656b60866fc4950d1e0f34","target":"record","created_at":"2026-07-05T10:11:03Z","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":"0251e8dbfdf1406d936b969aa2f7dc4808dc4d5374524e2de9feb09f53186557","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-07T17:01:37Z","title_canon_sha256":"8f37992a8dbee52a5848a85daaf8d29f770257a610dacb7699f54e74bbbdba39"},"schema_version":"1.0","source":{"id":"2502.05085","kind":"arxiv","version":1}},"canonical_sha256":"20ea08b8ad335babcc11d07dbd4213bb0b7e4d1006fb4e10296d48c39a07bb0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20ea08b8ad335babcc11d07dbd4213bb0b7e4d1006fb4e10296d48c39a07bb0b","first_computed_at":"2026-07-05T10:11:03.012999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:03.012999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dIWr7BEBhA+ZSCVABBh9xKbrDh8p5kcq64k8YV/B6Bb76S9OoyFnrldG8rffVklISlePxKd78OK4milHSOPhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:03.013555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee42d89abc3d9f4e4a65f2efa3afae7717a1d9e6cd656b60866fc4950d1e0f34","sha256:2f044a16095948f1c39a9b8d769a4e667634971561f18fc77eb1c6616980d75e"],"state_sha256":"1df1122cec343ebbb1073300366ae6f7b656c686e97aba4f316eb4d433bccfa5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"53WWTfw0PBwq/8m42MwBz+EhjD+s0xuBI7UCx7fQ9pbDJ3VwvoLoHApBRU7jdqZEXHhkjKT+voC8FjEtGEHHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T23:17:48.148659Z","bundle_sha256":"16e3201c90be81ff2c88603fba8aec7948a20431fb0ee29339337aad0a9a7a8f"}}