{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P4OCF7WMJLDLRWIGAZYGCCWEFX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7db6d8fa14d6b7504a3a63f8ea98ec013f2951065bd465b0ece3312a3ac07343","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-22T09:01:21Z","title_canon_sha256":"827bf9fada24aab8613271e79b5ede633c593b3db9079f60bfe9dd36d7115c28"},"schema_version":"1.0","source":{"id":"2207.10951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10951","created_at":"2026-07-05T04:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10951v1","created_at":"2026-07-05T04:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10951","created_at":"2026-07-05T04:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"P4OCF7WMJLDL","created_at":"2026-07-05T04:42:41Z"},{"alias_kind":"pith_short_16","alias_value":"P4OCF7WMJLDLRWIG","created_at":"2026-07-05T04:42:41Z"},{"alias_kind":"pith_short_8","alias_value":"P4OCF7WM","created_at":"2026-07-05T04:42:41Z"}],"graph_snapshots":[{"event_id":"sha256:551ab7e016166df2c70f7108d1682bccfac4cbb9659e4fad69eb0a109037f356","target":"graph","created_at":"2026-07-05T04:42:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.10951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an autoencoder trained on a model zoo was able to learn a hyper-representation, which captures intrinsic and extrinsic properties of the models in the zoo. In this work, we extend hyper-representations for generative use to sample new model weights as pre-training. We propose layer-wise loss normalization which we demonstrate is key to generate high-performing models an","authors_text":"Boris Knyazev, Damian Borth, Konstantin Sch\\\"urholt, Xavier Gir\\'o-i-Nieto","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-22T09:01:21Z","title":"Hyper-Representations for Pre-Training and Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10951","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d6a6eafda31460e92d504e0ae35a08ca76e5cffda5b5cfbc8620d176d9873154","target":"record","created_at":"2026-07-05T04:42:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7db6d8fa14d6b7504a3a63f8ea98ec013f2951065bd465b0ece3312a3ac07343","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-22T09:01:21Z","title_canon_sha256":"827bf9fada24aab8613271e79b5ede633c593b3db9079f60bfe9dd36d7115c28"},"schema_version":"1.0","source":{"id":"2207.10951","kind":"arxiv","version":1}},"canonical_sha256":"7f1c22fecc4ac6b8d9060670610ac42dedea86a076a6349f13d4b61685910280","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f1c22fecc4ac6b8d9060670610ac42dedea86a076a6349f13d4b61685910280","first_computed_at":"2026-07-05T04:42:41.834376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:41.834376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NCoNUy14La5JTZ9Ie+mevwkk+xGbB2aUfQuMxLB1vYFQTCmt+YElQ/G5ChJSQ66oygB1Fs90GsRIQu5JQEK5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:41.834771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.10951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6a6eafda31460e92d504e0ae35a08ca76e5cffda5b5cfbc8620d176d9873154","sha256:551ab7e016166df2c70f7108d1682bccfac4cbb9659e4fad69eb0a109037f356"],"state_sha256":"9adad646ab6f63768aeb09302f73882c2b351e2764293bead22fad582b8dbbe2"}