{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MOXBLMUEZ5R2ZM3IXAOC7AJT2G","short_pith_number":"pith:MOXBLMUE","schema_version":"1.0","canonical_sha256":"63ae15b284cf63acb368b81c2f8133d1a242b5c52840b46338aa82104e013e6e","source":{"kind":"arxiv","id":"2210.06350","version":1},"attestation_state":"computed","paper":{"title":"CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Schmidhuber, Kazuki Irie, R\\'obert Csord\\'as","submitted_at":"2022-10-12T16:01:57Z","abstract_excerpt":"Well-designed diagnostic tasks have played a key role in studying the failure of neural nets (NNs) to generalize systematically. Famous examples include SCAN and Compositional Table Lookup (CTL). Here we introduce CTL++, a new diagnostic dataset based on compositions of unary symbolic functions. While the original CTL is used to test length generalization or productivity, CTL++ is designed to test systematicity of NNs, that is, their capability to generalize to unseen compositions of known functions. CTL++ splits functions into groups and tests performance on group elements composed in a way n"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.06350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T16:01:57Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a93c77728b6197bb96a83e46fa6e9cd97bebae456438e5010e092003f9687d4f","abstract_canon_sha256":"44c707b3ab020765074d3978fc88cc03c9320ca735920cfa7f94acc658fc817b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:59.426927Z","signature_b64":"B12m0NG1rZOh99PDjMuKNMPTcLbBZKTbIJuiYgjBfO0ZfMxDd2TMdTsUCEs+SWHp9Pmy4e7gvnQTJnw7bMXvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63ae15b284cf63acb368b81c2f8133d1a242b5c52840b46338aa82104e013e6e","last_reissued_at":"2026-07-05T05:05:59.426517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:59.426517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Schmidhuber, Kazuki Irie, R\\'obert Csord\\'as","submitted_at":"2022-10-12T16:01:57Z","abstract_excerpt":"Well-designed diagnostic tasks have played a key role in studying the failure of neural nets (NNs) to generalize systematically. Famous examples include SCAN and Compositional Table Lookup (CTL). Here we introduce CTL++, a new diagnostic dataset based on compositions of unary symbolic functions. While the original CTL is used to test length generalization or productivity, CTL++ is designed to test systematicity of NNs, that is, their capability to generalize to unseen compositions of known functions. CTL++ splits functions into groups and tests performance on group elements composed in a way n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06350","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/2210.06350/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.06350","created_at":"2026-07-05T05:05:59.426577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06350v1","created_at":"2026-07-05T05:05:59.426577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06350","created_at":"2026-07-05T05:05:59.426577+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOXBLMUEZ5R2","created_at":"2026-07-05T05:05:59.426577+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOXBLMUEZ5R2ZM3I","created_at":"2026-07-05T05:05:59.426577+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOXBLMUE","created_at":"2026-07-05T05:05:59.426577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15306","citing_title":"Generalization in LLM Problem Solving: The Case of the Shortest Path","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G","json":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G.json","graph_json":"https://pith.science/api/pith-number/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/graph.json","events_json":"https://pith.science/api/pith-number/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/events.json","paper":"https://pith.science/paper/MOXBLMUE"},"agent_actions":{"view_html":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G","download_json":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G.json","view_paper":"https://pith.science/paper/MOXBLMUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06350&json=true","fetch_graph":"https://pith.science/api/pith-number/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/graph.json","fetch_events":"https://pith.science/api/pith-number/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/action/storage_attestation","attest_author":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/action/author_attestation","sign_citation":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/action/citation_signature","submit_replication":"https://pith.science/pith/MOXBLMUEZ5R2ZM3IXAOC7AJT2G/action/replication_record"}},"created_at":"2026-07-05T05:05:59.426577+00:00","updated_at":"2026-07-05T05:05:59.426577+00:00"}