{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YE3QK2HAPJF4K4GNVXZMY3F7SI","short_pith_number":"pith:YE3QK2HA","schema_version":"1.0","canonical_sha256":"c1370568e07a4bc570cdadf2cc6cbf92183625eb4f5a3b4cb8561cd9ebcdf79d","source":{"kind":"arxiv","id":"2301.12780","version":2},"attestation_state":"computed","paper":{"title":"Equivariant Architectures for Learning in Deep Weight Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Haggai Maron, Idan Achituve","submitted_at":"2023-01-30T10:50:33Z","abstract_excerpt":"Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction. Unfortunately, the unique symmetry structure of deep weight spaces makes this design very challenging. If successful, such architectures would be capable of performing a wide range of intriguing tasks, from adapting a pre-trained network to a new domain to editing objects represented as functions (INRs or NeRFs). As a first step towards this goal, we present here a novel network architecture for learning in deep weight spaces. It takes as input a con"},"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":"2301.12780","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T10:50:33Z","cross_cats_sorted":[],"title_canon_sha256":"7f64a900e9112f7b96acd77bffdc53e5be5cb082075c8a09ff74595552e4883c","abstract_canon_sha256":"6743c4e4a268c49db6652ce7a14fef5f8c25cb8e1f854dcad8c59281fc07319e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:15.480411Z","signature_b64":"p/NXHveOJTUvQHc/9QWDHqvm3cSlzjAiDAJABIGgMDiHQh4wp+NlybZ1K0HIyCMlIHAHhKUkzyN3DBrB2x9oBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1370568e07a4bc570cdadf2cc6cbf92183625eb4f5a3b4cb8561cd9ebcdf79d","last_reissued_at":"2026-07-05T06:16:15.479789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:15.479789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Architectures for Learning in Deep Weight Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Haggai Maron, Idan Achituve","submitted_at":"2023-01-30T10:50:33Z","abstract_excerpt":"Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction. Unfortunately, the unique symmetry structure of deep weight spaces makes this design very challenging. If successful, such architectures would be capable of performing a wide range of intriguing tasks, from adapting a pre-trained network to a new domain to editing objects represented as functions (INRs or NeRFs). As a first step towards this goal, we present here a novel network architecture for learning in deep weight spaces. It takes as input a con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12780","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/2301.12780/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":"2301.12780","created_at":"2026-07-05T06:16:15.479888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12780v2","created_at":"2026-07-05T06:16:15.479888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12780","created_at":"2026-07-05T06:16:15.479888+00:00"},{"alias_kind":"pith_short_12","alias_value":"YE3QK2HAPJF4","created_at":"2026-07-05T06:16:15.479888+00:00"},{"alias_kind":"pith_short_16","alias_value":"YE3QK2HAPJF4K4GN","created_at":"2026-07-05T06:16:15.479888+00:00"},{"alias_kind":"pith_short_8","alias_value":"YE3QK2HA","created_at":"2026-07-05T06:16:15.479888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI","json":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI.json","graph_json":"https://pith.science/api/pith-number/YE3QK2HAPJF4K4GNVXZMY3F7SI/graph.json","events_json":"https://pith.science/api/pith-number/YE3QK2HAPJF4K4GNVXZMY3F7SI/events.json","paper":"https://pith.science/paper/YE3QK2HA"},"agent_actions":{"view_html":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI","download_json":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI.json","view_paper":"https://pith.science/paper/YE3QK2HA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12780&json=true","fetch_graph":"https://pith.science/api/pith-number/YE3QK2HAPJF4K4GNVXZMY3F7SI/graph.json","fetch_events":"https://pith.science/api/pith-number/YE3QK2HAPJF4K4GNVXZMY3F7SI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI/action/storage_attestation","attest_author":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI/action/author_attestation","sign_citation":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI/action/citation_signature","submit_replication":"https://pith.science/pith/YE3QK2HAPJF4K4GNVXZMY3F7SI/action/replication_record"}},"created_at":"2026-07-05T06:16:15.479888+00:00","updated_at":"2026-07-05T06:16:15.479888+00:00"}