{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BZKHMBUM2YXIK7FTZ4JLEP55SH","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":"7ae42a78985f5ae7b75ac9a2f35e4d7eb7e629c8124f4f14c04f27d22464e2b6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T23:24:14Z","title_canon_sha256":"215c65f58bc1a4f34da8b2d67ac4cbdc27df985efaf3d9106adcd270e669d890"},"schema_version":"1.0","source":{"id":"2305.18654","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18654","created_at":"2026-07-05T07:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18654v3","created_at":"2026-07-05T07:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18654","created_at":"2026-07-05T07:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"BZKHMBUM2YXI","created_at":"2026-07-05T07:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"BZKHMBUM2YXIK7FT","created_at":"2026-07-05T07:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"BZKHMBUM","created_at":"2026-07-05T07:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:04c6ff0ae5c348bc1ba73a5f73009d3efba3a54fd18fe0fa995649a5e848ce4c","target":"graph","created_at":"2026-07-05T07:07:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.18654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems. This begs the question: Are these errors incidental, or do they signal more substantial limitations? In an attempt to demystify transformer LLMs, we investigate the limits of these models across three representative compositional tasks -- multi-digit multiplication, logic grid puzzles, and a classic dynamic programming problem. These tasks require breaking problems","authors_text":"Allyson Ettinger, Bill Yuchen Lin, Chandra Bhagavatula, Jena D. Hwang, Liwei Jiang, Melanie Sclar, Nouha Dziri, Peter West, Ronan Le Bras, Sean Welleck, Soumya Sanyal, Xiang Lorraine Li, Xiang Ren, Ximing Lu, Yejin Choi, Zaid Harchaoui","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T23:24:14Z","title":"Faith and Fate: Limits of Transformers on Compositionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18654","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":"sha256:7f4968b7b3a2530126a77bb5d29dc44bb627c8cf106cc639cd580168ce30bde9","target":"record","created_at":"2026-07-05T07:07:11Z","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":"7ae42a78985f5ae7b75ac9a2f35e4d7eb7e629c8124f4f14c04f27d22464e2b6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T23:24:14Z","title_canon_sha256":"215c65f58bc1a4f34da8b2d67ac4cbdc27df985efaf3d9106adcd270e669d890"},"schema_version":"1.0","source":{"id":"2305.18654","kind":"arxiv","version":3}},"canonical_sha256":"0e5476068cd62e857cb3cf12b23fbd91cdc2548a7ada9bd683072e57dbce6bb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e5476068cd62e857cb3cf12b23fbd91cdc2548a7ada9bd683072e57dbce6bb5","first_computed_at":"2026-07-05T07:07:11.028756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:11.028756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6y2XBx7O4WPc23mYE6ApZicP6JQ7WMinH3wXKKpx+asIeiUTcrxLEcvMkBx+0pLMxJWgkVcIIjhGvxBROsy3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:11.029237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18654","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f4968b7b3a2530126a77bb5d29dc44bb627c8cf106cc639cd580168ce30bde9","sha256:04c6ff0ae5c348bc1ba73a5f73009d3efba3a54fd18fe0fa995649a5e848ce4c"],"state_sha256":"9fcb0015cd65daf4a1ec5c5d81d6b0dedf3f297ed4d2547a993aba060507a67b"}