{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DPTGO2QXB3DMUBCK2VPF26H7AY","short_pith_number":"pith:DPTGO2QX","canonical_record":{"source":{"id":"2412.17758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T18:14:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e084398be9480c04cc72f8011f7bbe628bd75567a7ca9d08ab9065b6c20031c0","abstract_canon_sha256":"66460349b7b8efee2afff897805cd2f40c4e2652dd51250dd5f2b07633ef9142"},"schema_version":"1.0"},"canonical_sha256":"1be6676a170ec6ca044ad55e5d78ff062ac777ef9acc13284dd924a8a064b2b7","source":{"kind":"arxiv","id":"2412.17758","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17758","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17758v1","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17758","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"DPTGO2QXB3DM","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"DPTGO2QXB3DMUBCK","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"DPTGO2QX","created_at":"2026-07-05T09:53:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DPTGO2QXB3DMUBCK2VPF26H7AY","target":"record","payload":{"canonical_record":{"source":{"id":"2412.17758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T18:14:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e084398be9480c04cc72f8011f7bbe628bd75567a7ca9d08ab9065b6c20031c0","abstract_canon_sha256":"66460349b7b8efee2afff897805cd2f40c4e2652dd51250dd5f2b07633ef9142"},"schema_version":"1.0"},"canonical_sha256":"1be6676a170ec6ca044ad55e5d78ff062ac777ef9acc13284dd924a8a064b2b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:26.977374Z","signature_b64":"sdTuL8knDWSpdF8FzxTQZmB15IZ7Ds7kZ61BtxqZqLYDiAZQNWKFBweNfR5KxrVyRy4q3FIuKGmtKjHIsb6dDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be6676a170ec6ca044ad55e5d78ff062ac777ef9acc13284dd924a8a064b2b7","last_reissued_at":"2026-07-05T09:53:26.977008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:26.977008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.17758","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":"2026-07-05T09:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xzpoj1C07NqG1Pn/7XvtQSwXYCLggLAwflhkCXrKJGrksMle4H5L2V1BoLwXjbbcREwuCoujYaKki+eweMyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:05:38.760623Z"},"content_sha256":"d509bc5ed297dca3209843e29bf4f1e6fc40a76621dba0417f48e5cf40fcea83","schema_version":"1.0","event_id":"sha256:d509bc5ed297dca3209843e29bf4f1e6fc40a76621dba0417f48e5cf40fcea83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DPTGO2QXB3DMUBCK2VPF26H7AY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In Case You Missed It: ARC 'Challenge' Is Not That Challenging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"{\\L}ukasz Borchmann","submitted_at":"2024-12-23T18:14:36Z","abstract_excerpt":"ARC Challenge appears more difficult than ARC Easy for modern LLMs primarily due to an evaluation setup that prevents direct comparison of answer choices rather than inherent complexity. Although some researchers have quietly shifted to a more appropriate scheme over the last year, the implications of this change have yet to be widely acknowledged. We highlight this overlooked shift, show how similar evaluation practices falsely imply reasoning deficits in other benchmarks, and demonstrate that fairer methods dramatically reduce performance gaps (e.g. on SIQA) and even yield superhuman results"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17758","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/2412.17758/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":"2026-07-05T09:53:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XM18DtbFx0r2Gt8/ZyKenLJnUNr1lIKSrgRG8r1xizsh7nBbxC3fP3lIkAYhLy0kLgr+t4O5t04SAd6jINJwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:05:38.761151Z"},"content_sha256":"173b109fd6984e126ce0e845c1a72caf94d77bc29a3f960cd2d4e9d76291dd5f","schema_version":"1.0","event_id":"sha256:173b109fd6984e126ce0e845c1a72caf94d77bc29a3f960cd2d4e9d76291dd5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPTGO2QXB3DMUBCK2VPF26H7AY/bundle.json","state_url":"https://pith.science/pith/DPTGO2QXB3DMUBCK2VPF26H7AY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPTGO2QXB3DMUBCK2VPF26H7AY/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":"2026-08-08T12:05:38Z","links":{"resolver":"https://pith.science/pith/DPTGO2QXB3DMUBCK2VPF26H7AY","bundle":"https://pith.science/pith/DPTGO2QXB3DMUBCK2VPF26H7AY/bundle.json","state":"https://pith.science/pith/DPTGO2QXB3DMUBCK2VPF26H7AY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPTGO2QXB3DMUBCK2VPF26H7AY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DPTGO2QXB3DMUBCK2VPF26H7AY","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":"66460349b7b8efee2afff897805cd2f40c4e2652dd51250dd5f2b07633ef9142","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T18:14:36Z","title_canon_sha256":"e084398be9480c04cc72f8011f7bbe628bd75567a7ca9d08ab9065b6c20031c0"},"schema_version":"1.0","source":{"id":"2412.17758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17758","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17758v1","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17758","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"DPTGO2QXB3DM","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"DPTGO2QXB3DMUBCK","created_at":"2026-07-05T09:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"DPTGO2QX","created_at":"2026-07-05T09:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:173b109fd6984e126ce0e845c1a72caf94d77bc29a3f960cd2d4e9d76291dd5f","target":"graph","created_at":"2026-07-05T09:53:26Z","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/2412.17758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ARC Challenge appears more difficult than ARC Easy for modern LLMs primarily due to an evaluation setup that prevents direct comparison of answer choices rather than inherent complexity. Although some researchers have quietly shifted to a more appropriate scheme over the last year, the implications of this change have yet to be widely acknowledged. We highlight this overlooked shift, show how similar evaluation practices falsely imply reasoning deficits in other benchmarks, and demonstrate that fairer methods dramatically reduce performance gaps (e.g. on SIQA) and even yield superhuman results","authors_text":"{\\L}ukasz Borchmann","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T18:14:36Z","title":"In Case You Missed It: ARC 'Challenge' Is Not That Challenging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17758","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:d509bc5ed297dca3209843e29bf4f1e6fc40a76621dba0417f48e5cf40fcea83","target":"record","created_at":"2026-07-05T09:53:26Z","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":"66460349b7b8efee2afff897805cd2f40c4e2652dd51250dd5f2b07633ef9142","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T18:14:36Z","title_canon_sha256":"e084398be9480c04cc72f8011f7bbe628bd75567a7ca9d08ab9065b6c20031c0"},"schema_version":"1.0","source":{"id":"2412.17758","kind":"arxiv","version":1}},"canonical_sha256":"1be6676a170ec6ca044ad55e5d78ff062ac777ef9acc13284dd924a8a064b2b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1be6676a170ec6ca044ad55e5d78ff062ac777ef9acc13284dd924a8a064b2b7","first_computed_at":"2026-07-05T09:53:26.977008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:26.977008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdTuL8knDWSpdF8FzxTQZmB15IZ7Ds7kZ61BtxqZqLYDiAZQNWKFBweNfR5KxrVyRy4q3FIuKGmtKjHIsb6dDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:26.977374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17758","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d509bc5ed297dca3209843e29bf4f1e6fc40a76621dba0417f48e5cf40fcea83","sha256:173b109fd6984e126ce0e845c1a72caf94d77bc29a3f960cd2d4e9d76291dd5f"],"state_sha256":"2f2efd1e057a95ffa827a4e35c5ae6598ec0a43f478c75ce0385fb7f15ee1110"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLezLCHGMB+IXSstmlmUQskEvQj2DuWuz/YsCyovWhcar3RpVLCvb8gLY+JANewnto+jhxYfMU6kMPgAHoh6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:05:38.765351Z","bundle_sha256":"f6a1864a9ce5751d11c9893713ce215de505be85e6e2806b63d9788f91798d5c"}}