{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WBHSHWEGEPBQXNP4H745P2CVR5","short_pith_number":"pith:WBHSHWEG","schema_version":"1.0","canonical_sha256":"b04f23d88623c30bb5fc3ff9d7e8558f4aedbc7be192937e13bb4a78109aedf3","source":{"kind":"arxiv","id":"2002.10006","version":2},"attestation_state":"computed","paper":{"title":"On the Modularity of Hypernetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lior Wolf, Tomer Galanti","submitted_at":"2020-02-23T22:51:52Z","abstract_excerpt":"In the context of learning to map an input $I$ to a function $h_I:\\mathcal{X}\\to \\mathbb{R}$, two alternative methods are compared: (i) an embedding-based method, which learns a fixed function in which $I$ is encoded as a conditioning signal $e(I)$ and the learned function takes the form $h_I(x) = q(x,e(I))$, and (ii) hypernetworks, in which the weights $\\theta_I$ of the function $h_I(x) = g(x;\\theta_I)$ are given by a hypernetwork $f$ as $\\theta_I=f(I)$. In this paper, we define the property of modularity as the ability to effectively learn a different function for each input instance $I$. Fo"},"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":"2002.10006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T22:51:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22de338e085d06472bcd1eb1ea45ade85f39474aaec279ccdcc5eef259bd61b4","abstract_canon_sha256":"374140e2c0d60cc88781228b0fe8f30229f3dbbd21133efd1634079e6a6f2f7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:08.096062Z","signature_b64":"Xb+sYV9+miA8fW/R9SRyA7WbKu3TEZSfKg5+e4eAs7QPAakn9TiqdQdInnCLzawBFCWVRmzML/GXpCIkCYOdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b04f23d88623c30bb5fc3ff9d7e8558f4aedbc7be192937e13bb4a78109aedf3","last_reissued_at":"2026-07-05T01:48:08.095682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:08.095682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Modularity of Hypernetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lior Wolf, Tomer Galanti","submitted_at":"2020-02-23T22:51:52Z","abstract_excerpt":"In the context of learning to map an input $I$ to a function $h_I:\\mathcal{X}\\to \\mathbb{R}$, two alternative methods are compared: (i) an embedding-based method, which learns a fixed function in which $I$ is encoded as a conditioning signal $e(I)$ and the learned function takes the form $h_I(x) = q(x,e(I))$, and (ii) hypernetworks, in which the weights $\\theta_I$ of the function $h_I(x) = g(x;\\theta_I)$ are given by a hypernetwork $f$ as $\\theta_I=f(I)$. In this paper, we define the property of modularity as the ability to effectively learn a different function for each input instance $I$. Fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10006","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/2002.10006/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":"2002.10006","created_at":"2026-07-05T01:48:08.095749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10006v2","created_at":"2026-07-05T01:48:08.095749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10006","created_at":"2026-07-05T01:48:08.095749+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBHSHWEGEPBQ","created_at":"2026-07-05T01:48:08.095749+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBHSHWEGEPBQXNP4","created_at":"2026-07-05T01:48:08.095749+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBHSHWEG","created_at":"2026-07-05T01:48:08.095749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12124","citing_title":"Searching for Falsified Clause in Random (log n)-CNFs is Hard for Randomized Communication","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5","json":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5.json","graph_json":"https://pith.science/api/pith-number/WBHSHWEGEPBQXNP4H745P2CVR5/graph.json","events_json":"https://pith.science/api/pith-number/WBHSHWEGEPBQXNP4H745P2CVR5/events.json","paper":"https://pith.science/paper/WBHSHWEG"},"agent_actions":{"view_html":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5","download_json":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5.json","view_paper":"https://pith.science/paper/WBHSHWEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10006&json=true","fetch_graph":"https://pith.science/api/pith-number/WBHSHWEGEPBQXNP4H745P2CVR5/graph.json","fetch_events":"https://pith.science/api/pith-number/WBHSHWEGEPBQXNP4H745P2CVR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5/action/storage_attestation","attest_author":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5/action/author_attestation","sign_citation":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5/action/citation_signature","submit_replication":"https://pith.science/pith/WBHSHWEGEPBQXNP4H745P2CVR5/action/replication_record"}},"created_at":"2026-07-05T01:48:08.095749+00:00","updated_at":"2026-07-05T01:48:08.095749+00:00"}