{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EJJS6CTR4AOXB4G3T4M5VKNK7S","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":"6e3d90ce3194c307ad889d5f02e53e69bdd002e2bd1210ff488131045481c8d5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T12:10:38Z","title_canon_sha256":"4ddcbd344a14cfed28fc8f88200d81866424f0ab2dfb65ff06a5fdad91869ca1"},"schema_version":"1.0","source":{"id":"2412.12841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12841","created_at":"2026-07-05T09:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12841v1","created_at":"2026-07-05T09:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12841","created_at":"2026-07-05T09:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"EJJS6CTR4AOX","created_at":"2026-07-05T09:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"EJJS6CTR4AOXB4G3","created_at":"2026-07-05T09:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"EJJS6CTR","created_at":"2026-07-05T09:50:21Z"}],"graph_snapshots":[{"event_id":"sha256:12c8463214fc59c0f593dfbba1ed279ec7cb66160de336cc298541e1e44abc2d","target":"graph","created_at":"2026-07-05T09:50:21Z","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/2412.12841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional relational reasoning (CRR) is a hallmark of human intelligence, but we lack a clear understanding of whether and how existing transformer large language models (LLMs) can solve CRR tasks. To enable systematic exploration of the CRR capability of LLMs, we first propose a new synthetic benchmark called Generalized Associative Recall (GAR) by integrating and generalizing the essence of several tasks in mechanistic interpretability (MI) study in a unified framework. Evaluation shows that GAR is challenging enough for existing LLMs, revealing their fundamental deficiency in CRR. Meanw","authors_text":"Da Xiao, Hongliang Liang, Qingye Meng, Ruikang Ni, Shihui Zheng, Xiangyu Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T12:10:38Z","title":"Benchmarking and Understanding Compositional Relational Reasoning of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12841","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":"sha256:579cc52fc2c8f4184c0662013e66dc6059b08e8db1c9130c60503abeb54c1aea","target":"record","created_at":"2026-07-05T09:50:21Z","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":"6e3d90ce3194c307ad889d5f02e53e69bdd002e2bd1210ff488131045481c8d5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T12:10:38Z","title_canon_sha256":"4ddcbd344a14cfed28fc8f88200d81866424f0ab2dfb65ff06a5fdad91869ca1"},"schema_version":"1.0","source":{"id":"2412.12841","kind":"arxiv","version":1}},"canonical_sha256":"22532f0a71e01d70f0db9f19daa9aafc9c528e9f8af6d7a9a1b92381e62b479b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22532f0a71e01d70f0db9f19daa9aafc9c528e9f8af6d7a9a1b92381e62b479b","first_computed_at":"2026-07-05T09:50:21.379335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:21.379335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Emuq9nEuQEf2IKHsFtxK6cPwjAN67BFzhjo2/rh4WbMHQjTVOTq+eDAX9pJgLldJgySy5IoNj1rMcRVvpnPHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:21.379758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:579cc52fc2c8f4184c0662013e66dc6059b08e8db1c9130c60503abeb54c1aea","sha256:12c8463214fc59c0f593dfbba1ed279ec7cb66160de336cc298541e1e44abc2d"],"state_sha256":"816ff80e55136412afc514dffa41fe2bf1e72657fcf57bd6aa08fb42fbcf706b"}