{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AVSXPDPELG2DEOQ5ZRYZK4GYM5","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":"fde84058c9b2b24a735db4eeb41da58ca8d5035c2127b3143a7cd9ead4fee101","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T13:23:44Z","title_canon_sha256":"819db0a3c74c80367326f15a7afc473b75ee1a70b25abc1b40072e3aca3981eb"},"schema_version":"1.0","source":{"id":"2505.13089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13089","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13089v2","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13089","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"AVSXPDPELG2D","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"AVSXPDPELG2DEOQ5","created_at":"2026-07-05T11:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"AVSXPDPE","created_at":"2026-07-05T11:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:3e3c59e4492129e469c988b17cca830a52e6894a1efdd7a8db733858663994ae","target":"graph","created_at":"2026-07-05T11:10:08Z","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/2505.13089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Systematic generalization remains challenging for current language models, which are known to be both sensitive to semantically similar permutations of the input and to struggle with known concepts presented in novel contexts. Although benchmarks exist for assessing compositional behavior, it is unclear how to measure the difficulty of a systematic generalization problem. In this work, we show how one aspect of systematic generalization can be described by the entropy of the distribution of component parts in the training data. We formalize a framework for measuring entropy in a sequence-to-se","authors_text":"\\'Etienne Simon, Lucas Georges Gabriel Charpentier, Sondre Wold","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T13:23:44Z","title":"Systematic Generalization in Language Models Scales with Information Entropy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13089","kind":"arxiv","version":2},"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":"sha256:73cb24f3c0663cb9eb237f7c0f1ba3cbc543c7612e3209a8a7f2e7f6f5b8ff7c","target":"record","created_at":"2026-07-05T11:10:08Z","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":"fde84058c9b2b24a735db4eeb41da58ca8d5035c2127b3143a7cd9ead4fee101","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T13:23:44Z","title_canon_sha256":"819db0a3c74c80367326f15a7afc473b75ee1a70b25abc1b40072e3aca3981eb"},"schema_version":"1.0","source":{"id":"2505.13089","kind":"arxiv","version":2}},"canonical_sha256":"0565778de459b4323a1dcc719570d867477312d99e1976fb81d83a6e610c692e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0565778de459b4323a1dcc719570d867477312d99e1976fb81d83a6e610c692e","first_computed_at":"2026-07-05T11:10:08.729658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:08.729658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YUmJ7kno/rPt5hXxqQGodWKSHgmapkORbSuwO8JfiSzFS30VTROxNQUwGJxGybv0mM7bC31qma5ZU3WSWOXNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:08.730146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73cb24f3c0663cb9eb237f7c0f1ba3cbc543c7612e3209a8a7f2e7f6f5b8ff7c","sha256:3e3c59e4492129e469c988b17cca830a52e6894a1efdd7a8db733858663994ae"],"state_sha256":"be4635c113af83cc41557226a0d8f22815651ef7e2d71e3bc5e236c83bc4d67e"}