{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZWGBDDIB7SCMM4VKOLCHDWUZVP","short_pith_number":"pith:ZWGBDDIB","schema_version":"1.0","canonical_sha256":"cd8c118d01fc84c672aa72c471da99abedc3cc9e3796630e4ffb62b900ac21e8","source":{"kind":"arxiv","id":"2306.09346","version":2},"attestation_state":"computed","paper":{"title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Amil Dravid, Assaf Shocher, Yossi Gandelsman","submitted_at":"2023-06-15T17:59:54Z","abstract_excerpt":"Do different neural networks, trained for various vision tasks, share some common representations? In this paper, we demonstrate the existence of common features we call \"Rosetta Neurons\" across a range of models with different architectures, different tasks (generative and discriminative), and different types of supervision (class-supervised, text-supervised, self-supervised). We present an algorithm for mining a dictionary of Rosetta Neurons across several popular vision models: Class Supervised-ResNet50, DINO-ResNet50, DINO-ViT, MAE, CLIP-ResNet50, BigGAN, StyleGAN-2, StyleGAN-XL. Our findi"},"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":"2306.09346","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T17:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"4e8e032742d846e7bcdd90a1f097b88517f35e0772c9ca8313d4307bc3ea8abe","abstract_canon_sha256":"72e46aca1da920f267415a379dd296b4740c91025ad8ad397dfe9bb085115701"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:18.421634Z","signature_b64":"Q8YLKNxcPg/g+PQYTFdyVNfg+MCPffb8xwHounVxVRZgiSV1cWCmOVcoRJXO5dfA80Shv+HGTBwA5igxH0LrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd8c118d01fc84c672aa72c471da99abedc3cc9e3796630e4ffb62b900ac21e8","last_reissued_at":"2026-07-05T06:21:18.421252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:18.421252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Amil Dravid, Assaf Shocher, Yossi Gandelsman","submitted_at":"2023-06-15T17:59:54Z","abstract_excerpt":"Do different neural networks, trained for various vision tasks, share some common representations? In this paper, we demonstrate the existence of common features we call \"Rosetta Neurons\" across a range of models with different architectures, different tasks (generative and discriminative), and different types of supervision (class-supervised, text-supervised, self-supervised). We present an algorithm for mining a dictionary of Rosetta Neurons across several popular vision models: Class Supervised-ResNet50, DINO-ResNet50, DINO-ViT, MAE, CLIP-ResNet50, BigGAN, StyleGAN-2, StyleGAN-XL. Our findi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09346","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/2306.09346/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":"2306.09346","created_at":"2026-07-05T06:21:18.421304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09346v2","created_at":"2026-07-05T06:21:18.421304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09346","created_at":"2026-07-05T06:21:18.421304+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWGBDDIB7SCM","created_at":"2026-07-05T06:21:18.421304+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWGBDDIB7SCMM4VK","created_at":"2026-07-05T06:21:18.421304+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWGBDDIB","created_at":"2026-07-05T06:21:18.421304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01803","citing_title":"Discovering Chunks in Neural Embeddings for Interpretability","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP","json":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP.json","graph_json":"https://pith.science/api/pith-number/ZWGBDDIB7SCMM4VKOLCHDWUZVP/graph.json","events_json":"https://pith.science/api/pith-number/ZWGBDDIB7SCMM4VKOLCHDWUZVP/events.json","paper":"https://pith.science/paper/ZWGBDDIB"},"agent_actions":{"view_html":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP","download_json":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP.json","view_paper":"https://pith.science/paper/ZWGBDDIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09346&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWGBDDIB7SCMM4VKOLCHDWUZVP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWGBDDIB7SCMM4VKOLCHDWUZVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP/action/storage_attestation","attest_author":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP/action/author_attestation","sign_citation":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP/action/citation_signature","submit_replication":"https://pith.science/pith/ZWGBDDIB7SCMM4VKOLCHDWUZVP/action/replication_record"}},"created_at":"2026-07-05T06:21:18.421304+00:00","updated_at":"2026-07-05T06:21:18.421304+00:00"}