{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJR6LZ4O7I5FY4PMOG37V2G2CW","short_pith_number":"pith:PJR6LZ4O","schema_version":"1.0","canonical_sha256":"7a63e5e78efa3a5c71ec71b7fae8da15891ae8273a87cde398e825fdb39d6300","source":{"kind":"arxiv","id":"2408.12578","version":2},"attestation_state":"computed","paper":{"title":"A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ekdeep Singh Lubana, Hidenori Tanaka, Kyogo Kawaguchi, Robert P. Dick","submitted_at":"2024-08-22T17:44:22Z","abstract_excerpt":"Increase in data, size, or compute can lead to sudden learning of specific capabilities by a neural network -- a phenomenon often called \"emergence''. Beyond scientific understanding, establishing the causal factors underlying such emergent capabilities is crucial to enable risk regulation frameworks for AI. In this work, we seek inspiration from study of emergent properties in other fields and propose a phenomenological definition for the concept in the context of neural networks. Our definition implicates the acquisition of general structures underlying the data-generating process as a cause"},"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":"2408.12578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T17:44:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0d9197eb0e3f02efa671802898ec3672590724cd7311dc0a7efd6e36fe0b5ed","abstract_canon_sha256":"a90433f26dd9eabe5107a912977f2fb889432764dc9d756a17bc14a36a9023a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:39.311831Z","signature_b64":"NY95dAQj/VtsyJQv174NNGgpWdE6MqmA3Rx5UHcNXGJBu8L8OnWutGonDnhcvErnjNpX0TJ9gH2dmiPoevE+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a63e5e78efa3a5c71ec71b7fae8da15891ae8273a87cde398e825fdb39d6300","last_reissued_at":"2026-07-05T09:04:39.311360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:39.311360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ekdeep Singh Lubana, Hidenori Tanaka, Kyogo Kawaguchi, Robert P. Dick","submitted_at":"2024-08-22T17:44:22Z","abstract_excerpt":"Increase in data, size, or compute can lead to sudden learning of specific capabilities by a neural network -- a phenomenon often called \"emergence''. Beyond scientific understanding, establishing the causal factors underlying such emergent capabilities is crucial to enable risk regulation frameworks for AI. In this work, we seek inspiration from study of emergent properties in other fields and propose a phenomenological definition for the concept in the context of neural networks. Our definition implicates the acquisition of general structures underlying the data-generating process as a cause"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12578","kind":"arxiv","version":2},"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/2408.12578/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":"2408.12578","created_at":"2026-07-05T09:04:39.311419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12578v2","created_at":"2026-07-05T09:04:39.311419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12578","created_at":"2026-07-05T09:04:39.311419+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJR6LZ4O7I5F","created_at":"2026-07-05T09:04:39.311419+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJR6LZ4O7I5FY4PM","created_at":"2026-07-05T09:04:39.311419+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJR6LZ4O","created_at":"2026-07-05T09:04:39.311419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20347","citing_title":"Critical Percolation as a Synthetic Data Model for Interpretability","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2501.02378","citing_title":"A ghost mechanism: An analytical model of abrupt learning in recurrent networks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20299","citing_title":"Mechanisms of Misgeneralization in Physical Sequence Modeling","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW","json":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW.json","graph_json":"https://pith.science/api/pith-number/PJR6LZ4O7I5FY4PMOG37V2G2CW/graph.json","events_json":"https://pith.science/api/pith-number/PJR6LZ4O7I5FY4PMOG37V2G2CW/events.json","paper":"https://pith.science/paper/PJR6LZ4O"},"agent_actions":{"view_html":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW","download_json":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW.json","view_paper":"https://pith.science/paper/PJR6LZ4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12578&json=true","fetch_graph":"https://pith.science/api/pith-number/PJR6LZ4O7I5FY4PMOG37V2G2CW/graph.json","fetch_events":"https://pith.science/api/pith-number/PJR6LZ4O7I5FY4PMOG37V2G2CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW/action/storage_attestation","attest_author":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW/action/author_attestation","sign_citation":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW/action/citation_signature","submit_replication":"https://pith.science/pith/PJR6LZ4O7I5FY4PMOG37V2G2CW/action/replication_record"}},"created_at":"2026-07-05T09:04:39.311419+00:00","updated_at":"2026-07-05T09:04:39.311419+00:00"}