{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2THACNB5B44VXSZSJCZCL32JMS","short_pith_number":"pith:2THACNB5","schema_version":"1.0","canonical_sha256":"d4ce01343d0f395bcb3248b225ef4964bf5f6e0f8795d46f1984c358de404bde","source":{"kind":"arxiv","id":"2412.16247","version":3},"attestation_state":"computed","paper":{"title":"Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Ravuri, Cian Eastwood, Gemma Elyse Moran, Jason Hartford, Kian Kenyon-Dean, Konstantin Donhauser, Kristina Ulicna","submitted_at":"2024-12-20T00:01:16Z","abstract_excerpt":"Sparse dictionary learning (DL) has emerged as a powerful approach to extract semantically meaningful concepts from the internals of large language models (LLMs) trained mainly in the text domain. In this work, we explore whether DL can extract meaningful concepts from less human-interpretable scientific data, such as vision foundation models trained on cell microscopy images, where limited prior knowledge exists about which high-level concepts should arise. We propose a novel combination of a sparse DL algorithm, Iterative Codebook Feature Learning (ICFL), with a PCA whitening pre-processing "},"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":"2412.16247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T00:01:16Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"cddd61fedf3ceaefd6137bcc6930a1d4e54dc51048afe0420ad53b645a982a08","abstract_canon_sha256":"406952e44583bc939b79ceaec4c031f5afe7931aabfde8ec16231e1f38a2f096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:06.005864Z","signature_b64":"7WTzbhA4MeNyeJuDQLONYlbAuKUI6y7RGDFJworLbzdmU/PJ9tAuzhGOLN+i3+Q02I2AfemXKuEdu4fPU4rKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4ce01343d0f395bcb3248b225ef4964bf5f6e0f8795d46f1984c358de404bde","last_reissued_at":"2026-07-05T11:39:06.005340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:06.005340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Ravuri, Cian Eastwood, Gemma Elyse Moran, Jason Hartford, Kian Kenyon-Dean, Konstantin Donhauser, Kristina Ulicna","submitted_at":"2024-12-20T00:01:16Z","abstract_excerpt":"Sparse dictionary learning (DL) has emerged as a powerful approach to extract semantically meaningful concepts from the internals of large language models (LLMs) trained mainly in the text domain. In this work, we explore whether DL can extract meaningful concepts from less human-interpretable scientific data, such as vision foundation models trained on cell microscopy images, where limited prior knowledge exists about which high-level concepts should arise. We propose a novel combination of a sparse DL algorithm, Iterative Codebook Feature Learning (ICFL), with a PCA whitening pre-processing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16247","kind":"arxiv","version":3},"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/2412.16247/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":"2412.16247","created_at":"2026-07-05T11:39:06.005405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16247v3","created_at":"2026-07-05T11:39:06.005405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16247","created_at":"2026-07-05T11:39:06.005405+00:00"},{"alias_kind":"pith_short_12","alias_value":"2THACNB5B44V","created_at":"2026-07-05T11:39:06.005405+00:00"},{"alias_kind":"pith_short_16","alias_value":"2THACNB5B44VXSZS","created_at":"2026-07-05T11:39:06.005405+00:00"},{"alias_kind":"pith_short_8","alias_value":"2THACNB5","created_at":"2026-07-05T11:39:06.005405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05211","citing_title":"Learned Dictionaries with Total Variation and Non-Negativity for Single-Cell Microscopy: Convergence Theory and Deterministic Multi-Channel Cell Feature Unification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS","json":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS.json","graph_json":"https://pith.science/api/pith-number/2THACNB5B44VXSZSJCZCL32JMS/graph.json","events_json":"https://pith.science/api/pith-number/2THACNB5B44VXSZSJCZCL32JMS/events.json","paper":"https://pith.science/paper/2THACNB5"},"agent_actions":{"view_html":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS","download_json":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS.json","view_paper":"https://pith.science/paper/2THACNB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16247&json=true","fetch_graph":"https://pith.science/api/pith-number/2THACNB5B44VXSZSJCZCL32JMS/graph.json","fetch_events":"https://pith.science/api/pith-number/2THACNB5B44VXSZSJCZCL32JMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS/action/storage_attestation","attest_author":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS/action/author_attestation","sign_citation":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS/action/citation_signature","submit_replication":"https://pith.science/pith/2THACNB5B44VXSZSJCZCL32JMS/action/replication_record"}},"created_at":"2026-07-05T11:39:06.005405+00:00","updated_at":"2026-07-05T11:39:06.005405+00:00"}