{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NISCMCUPQKZEHU3KJDT4FRXWOS","short_pith_number":"pith:NISCMCUP","canonical_record":{"source":{"id":"2212.10769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:02:08Z","cross_cats_sorted":[],"title_canon_sha256":"13e4a23a1d46c16c5279177ba5fa2d5d4bdee54e25362413069871633b62bed0","abstract_canon_sha256":"0c5336f9d6b0c28d64064ddfdd1c62b9ac4729d7ca5340580275dd5850b9c43d"},"schema_version":"1.0"},"canonical_sha256":"6a24260a8f82b243d36a48e7c2c6f67485020c4505bd9495b74efb2b12e15f00","source":{"kind":"arxiv","id":"2212.10769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10769","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10769v1","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10769","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"NISCMCUPQKZE","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"NISCMCUPQKZEHU3K","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"NISCMCUP","created_at":"2026-07-05T05:27:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NISCMCUPQKZEHU3KJDT4FRXWOS","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:02:08Z","cross_cats_sorted":[],"title_canon_sha256":"13e4a23a1d46c16c5279177ba5fa2d5d4bdee54e25362413069871633b62bed0","abstract_canon_sha256":"0c5336f9d6b0c28d64064ddfdd1c62b9ac4729d7ca5340580275dd5850b9c43d"},"schema_version":"1.0"},"canonical_sha256":"6a24260a8f82b243d36a48e7c2c6f67485020c4505bd9495b74efb2b12e15f00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:22.681031Z","signature_b64":"HztyMCPRnnVrQtaTmiiScuF8wT6bNvBdczsomoGkjA8ZEnsAP03N8/QYJE0hmpTVKqBLqdy67J+3EY8UodO+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a24260a8f82b243d36a48e7c2c6f67485020c4505bd9495b74efb2b12e15f00","last_reissued_at":"2026-07-05T05:27:22.680600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:22.680600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10769","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":"2026-07-05T05:27:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yP4WFJl36A9r3NiP+uo0eEeynORiZ6W3q56Dc6UjYjBf0uh9DtcOt6fW6/VQl0G723tTsqPzDzfaO2DVdppXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:24:17.097433Z"},"content_sha256":"3accc226f9c2d41d3b99849d7a5082389ee7615432d4ec2eef50a098ced7000d","schema_version":"1.0","event_id":"sha256:3accc226f9c2d41d3b99849d7a5082389ee7615432d4ec2eef50a098ced7000d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NISCMCUPQKZEHU3KJDT4FRXWOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Najoung Kim, Paul Smolensky, Tal Linzen","submitted_at":"2022-12-21T05:02:08Z","abstract_excerpt":"Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by composing known parts. Several benchmarks exploit distributional control across training and test to gauge compositional generalization, where certain lexical items only occur in limited contexts during training. While recent work using these benchmarks suggests that pretrained models achieve impressive generalization performance, we argue that exposure to pretraining data may break the aforementioned distributional con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10769","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/2212.10769/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":"2026-07-05T05:27:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P8v3+TE0KRhFsZHbCTiPN3xEFMMjlMr/rzyQtLLg776bzzHedE+RLmSjE4QSOQCf9XGmuq6/uEFSbQOSMqaEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:24:17.098103Z"},"content_sha256":"381d8cf085bf65942a955e8c3f09a3d07f4b4f5b0edf6aba56be5090baaf69d5","schema_version":"1.0","event_id":"sha256:381d8cf085bf65942a955e8c3f09a3d07f4b4f5b0edf6aba56be5090baaf69d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NISCMCUPQKZEHU3KJDT4FRXWOS/bundle.json","state_url":"https://pith.science/pith/NISCMCUPQKZEHU3KJDT4FRXWOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NISCMCUPQKZEHU3KJDT4FRXWOS/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":"2026-08-08T15:24:17Z","links":{"resolver":"https://pith.science/pith/NISCMCUPQKZEHU3KJDT4FRXWOS","bundle":"https://pith.science/pith/NISCMCUPQKZEHU3KJDT4FRXWOS/bundle.json","state":"https://pith.science/pith/NISCMCUPQKZEHU3KJDT4FRXWOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NISCMCUPQKZEHU3KJDT4FRXWOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NISCMCUPQKZEHU3KJDT4FRXWOS","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":"0c5336f9d6b0c28d64064ddfdd1c62b9ac4729d7ca5340580275dd5850b9c43d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:02:08Z","title_canon_sha256":"13e4a23a1d46c16c5279177ba5fa2d5d4bdee54e25362413069871633b62bed0"},"schema_version":"1.0","source":{"id":"2212.10769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10769","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10769v1","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10769","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"NISCMCUPQKZE","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"NISCMCUPQKZEHU3K","created_at":"2026-07-05T05:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"NISCMCUP","created_at":"2026-07-05T05:27:22Z"}],"graph_snapshots":[{"event_id":"sha256:381d8cf085bf65942a955e8c3f09a3d07f4b4f5b0edf6aba56be5090baaf69d5","target":"graph","created_at":"2026-07-05T05:27:22Z","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/2212.10769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by composing known parts. Several benchmarks exploit distributional control across training and test to gauge compositional generalization, where certain lexical items only occur in limited contexts during training. While recent work using these benchmarks suggests that pretrained models achieve impressive generalization performance, we argue that exposure to pretraining data may break the aforementioned distributional con","authors_text":"Najoung Kim, Paul Smolensky, Tal Linzen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:02:08Z","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10769","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":"sha256:3accc226f9c2d41d3b99849d7a5082389ee7615432d4ec2eef50a098ced7000d","target":"record","created_at":"2026-07-05T05:27:22Z","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":"0c5336f9d6b0c28d64064ddfdd1c62b9ac4729d7ca5340580275dd5850b9c43d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:02:08Z","title_canon_sha256":"13e4a23a1d46c16c5279177ba5fa2d5d4bdee54e25362413069871633b62bed0"},"schema_version":"1.0","source":{"id":"2212.10769","kind":"arxiv","version":1}},"canonical_sha256":"6a24260a8f82b243d36a48e7c2c6f67485020c4505bd9495b74efb2b12e15f00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a24260a8f82b243d36a48e7c2c6f67485020c4505bd9495b74efb2b12e15f00","first_computed_at":"2026-07-05T05:27:22.680600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:22.680600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HztyMCPRnnVrQtaTmiiScuF8wT6bNvBdczsomoGkjA8ZEnsAP03N8/QYJE0hmpTVKqBLqdy67J+3EY8UodO+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:22.681031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3accc226f9c2d41d3b99849d7a5082389ee7615432d4ec2eef50a098ced7000d","sha256:381d8cf085bf65942a955e8c3f09a3d07f4b4f5b0edf6aba56be5090baaf69d5"],"state_sha256":"48284eb9d711cf9eac45ba4801557580d06fc848040957dc927b24c9cb5056d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMPExGyJ0rC+JwqHnLtXTo8d3vwJ+F8Y3WvH1rOsp4hJbD5VQQ1AY4hC7PLVXSCAc9qHe+XkheQ/bYPE+A1BCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:24:17.103878Z","bundle_sha256":"4d9009f5ae8c8a74a956851e0da9bf08d6706a0b69e040f2b07b5f6f8417a041"}}