{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UCH4LSACUREFSSCSMR2DHGN6ED","short_pith_number":"pith:UCH4LSAC","schema_version":"1.0","canonical_sha256":"a08fc5c802a44859485264743399be20f6b0c94dcd8a80b9e60d73c99f6ec29c","source":{"kind":"arxiv","id":"2505.11581","version":1},"attestation_state":"computed","paper":{"title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Akarsh Kumar, Jeff Clune, Joel Lehman, Kenneth O. Stanley","submitted_at":"2025-05-16T16:28:34Z","abstract_excerpt":"Much of the excitement in modern AI is driven by the observation that scaling up existing systems leads to better performance. But does better performance necessarily imply better internal representations? While the representational optimist assumes it must, this position paper challenges that view. We compare neural networks evolved through an open-ended search process to networks trained via conventional stochastic gradient descent (SGD) on the simple task of generating a single image. This minimal setup offers a unique advantage: each hidden neuron's full functional behavior can be easily v"},"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":"2505.11581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T16:28:34Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e20aba47ab9af4d8f18e58b1368f169b43ab54dfff7ecf9495e578eae32e120b","abstract_canon_sha256":"f092e9f5cdcc5474c3c5e456ced33b34ed25841dd83cd568af802ccea4cc1670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:23.987717Z","signature_b64":"YeRcfzNWc6ILbaPk5DL4JIE07pfrh1sfOd5xRlUqg5TA5TsrMlRxjf0hpP3kjr8Xg5LNp68lLB1HrTdn79KmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a08fc5c802a44859485264743399be20f6b0c94dcd8a80b9e60d73c99f6ec29c","last_reissued_at":"2026-07-05T11:04:23.987206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:23.987206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Akarsh Kumar, Jeff Clune, Joel Lehman, Kenneth O. Stanley","submitted_at":"2025-05-16T16:28:34Z","abstract_excerpt":"Much of the excitement in modern AI is driven by the observation that scaling up existing systems leads to better performance. But does better performance necessarily imply better internal representations? While the representational optimist assumes it must, this position paper challenges that view. We compare neural networks evolved through an open-ended search process to networks trained via conventional stochastic gradient descent (SGD) on the simple task of generating a single image. This minimal setup offers a unique advantage: each hidden neuron's full functional behavior can be easily v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11581","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/2505.11581/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":"2505.11581","created_at":"2026-07-05T11:04:23.987268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11581v1","created_at":"2026-07-05T11:04:23.987268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11581","created_at":"2026-07-05T11:04:23.987268+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCH4LSACUREF","created_at":"2026-07-05T11:04:23.987268+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCH4LSACUREFSSCS","created_at":"2026-07-05T11:04:23.987268+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCH4LSAC","created_at":"2026-07-05T11:04:23.987268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19941","citing_title":"Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01433","citing_title":"CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13675","citing_title":"Characterizing Universal Object Representations Across Vision Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18907","citing_title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18572","citing_title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED","json":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED.json","graph_json":"https://pith.science/api/pith-number/UCH4LSACUREFSSCSMR2DHGN6ED/graph.json","events_json":"https://pith.science/api/pith-number/UCH4LSACUREFSSCSMR2DHGN6ED/events.json","paper":"https://pith.science/paper/UCH4LSAC"},"agent_actions":{"view_html":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED","download_json":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED.json","view_paper":"https://pith.science/paper/UCH4LSAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11581&json=true","fetch_graph":"https://pith.science/api/pith-number/UCH4LSACUREFSSCSMR2DHGN6ED/graph.json","fetch_events":"https://pith.science/api/pith-number/UCH4LSACUREFSSCSMR2DHGN6ED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED/action/storage_attestation","attest_author":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED/action/author_attestation","sign_citation":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED/action/citation_signature","submit_replication":"https://pith.science/pith/UCH4LSACUREFSSCSMR2DHGN6ED/action/replication_record"}},"created_at":"2026-07-05T11:04:23.987268+00:00","updated_at":"2026-07-05T11:04:23.987268+00:00"}