{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GCHLPNMLH64DQ3L6OQOU6ACEXE","short_pith_number":"pith:GCHLPNML","canonical_record":{"source":{"id":"2209.12892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T17:59:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"aba860c0abf96090ef916c8978b1bf5188725ceb4da99a81634f657141806164","abstract_canon_sha256":"b1d06b26eae19e3a8e17853d4933f3eb5bf6f018f791fca3e0930fe56d00fead"},"schema_version":"1.0"},"canonical_sha256":"308eb7b58b3fb8386d7e741d4f0044b912d13d0dec95dd0d553abe72818b00fe","source":{"kind":"arxiv","id":"2209.12892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12892","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12892v1","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12892","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"GCHLPNMLH64D","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"GCHLPNMLH64DQ3L6","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"GCHLPNML","created_at":"2026-07-05T05:00:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GCHLPNMLH64DQ3L6OQOU6ACEXE","target":"record","payload":{"canonical_record":{"source":{"id":"2209.12892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T17:59:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"aba860c0abf96090ef916c8978b1bf5188725ceb4da99a81634f657141806164","abstract_canon_sha256":"b1d06b26eae19e3a8e17853d4933f3eb5bf6f018f791fca3e0930fe56d00fead"},"schema_version":"1.0"},"canonical_sha256":"308eb7b58b3fb8386d7e741d4f0044b912d13d0dec95dd0d553abe72818b00fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:57.254553Z","signature_b64":"StqOOhKddoN4O70xnK9GNB042cxyia+M3wmTLYTKGtuOMmahKagtb0UlxYiEphI2CVLWdas5pnkOUSvC4WJDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"308eb7b58b3fb8386d7e741d4f0044b912d13d0dec95dd0d553abe72818b00fe","last_reissued_at":"2026-07-05T05:00:57.254182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:57.254182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.12892","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:00:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"szZTQi7oL9mhlwFdYIth5WPDhhm9msZEAFmARD3XILECwv9FikPuH8HlVwGmJkin5k9QXPf687xE7SXrfv+lCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:01.138444Z"},"content_sha256":"4050c03bd3750c2afb868b8f1f9685eeacee1ae975a27c3c449d0bcb01b109c0","schema_version":"1.0","event_id":"sha256:4050c03bd3750c2afb868b8f1f9685eeacee1ae975a27c3c449d0bcb01b109c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GCHLPNMLH64DQ3L6OQOU6ACEXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Learn with Generative Models of Neural Network Checkpoints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Ilija Radosavovic, Jitendra Malik, Tim Brooks, William Peebles","submitted_at":"2022-09-26T17:59:58Z","abstract_excerpt":"We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer that, given an initial input parameter vector and a prompted loss, error, or return, predicts the distribution over parameter updates that achieve the desired metric. At test time, it can optimize neural networks with unseen parameters for downstream tasks in just one update. We find that our approach successfully generates parameters for a wide range of lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12892","kind":"arxiv","version":1},"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/2209.12892/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:00:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s/TXvbMYH6/6fp/JcQyeDHucdkPyaNLzNAHzJDxaAopesp1pwyL/aOHkDiC10TCWeyDWV/f5AD65mD+EKqpKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:01.139301Z"},"content_sha256":"b13a9b0eed48965b22b75c09b28074603a328ec90475c6a0e0c4b155e504a142","schema_version":"1.0","event_id":"sha256:b13a9b0eed48965b22b75c09b28074603a328ec90475c6a0e0c4b155e504a142"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE/bundle.json","state_url":"https://pith.science/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T12:59:01Z","links":{"resolver":"https://pith.science/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE","bundle":"https://pith.science/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE/bundle.json","state":"https://pith.science/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCHLPNMLH64DQ3L6OQOU6ACEXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GCHLPNMLH64DQ3L6OQOU6ACEXE","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":"b1d06b26eae19e3a8e17853d4933f3eb5bf6f018f791fca3e0930fe56d00fead","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T17:59:58Z","title_canon_sha256":"aba860c0abf96090ef916c8978b1bf5188725ceb4da99a81634f657141806164"},"schema_version":"1.0","source":{"id":"2209.12892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.12892","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2209.12892v1","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.12892","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"GCHLPNMLH64D","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"GCHLPNMLH64DQ3L6","created_at":"2026-07-05T05:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"GCHLPNML","created_at":"2026-07-05T05:00:57Z"}],"graph_snapshots":[{"event_id":"sha256:b13a9b0eed48965b22b75c09b28074603a328ec90475c6a0e0c4b155e504a142","target":"graph","created_at":"2026-07-05T05:00:57Z","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/2209.12892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer that, given an initial input parameter vector and a prompted loss, error, or return, predicts the distribution over parameter updates that achieve the desired metric. At test time, it can optimize neural networks with unseen parameters for downstream tasks in just one update. We find that our approach successfully generates parameters for a wide range of lo","authors_text":"Alexei A. Efros, Ilija Radosavovic, Jitendra Malik, Tim Brooks, William Peebles","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T17:59:58Z","title":"Learning to Learn with Generative Models of Neural Network Checkpoints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.12892","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":"sha256:4050c03bd3750c2afb868b8f1f9685eeacee1ae975a27c3c449d0bcb01b109c0","target":"record","created_at":"2026-07-05T05:00:57Z","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":"b1d06b26eae19e3a8e17853d4933f3eb5bf6f018f791fca3e0930fe56d00fead","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-26T17:59:58Z","title_canon_sha256":"aba860c0abf96090ef916c8978b1bf5188725ceb4da99a81634f657141806164"},"schema_version":"1.0","source":{"id":"2209.12892","kind":"arxiv","version":1}},"canonical_sha256":"308eb7b58b3fb8386d7e741d4f0044b912d13d0dec95dd0d553abe72818b00fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"308eb7b58b3fb8386d7e741d4f0044b912d13d0dec95dd0d553abe72818b00fe","first_computed_at":"2026-07-05T05:00:57.254182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:57.254182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"StqOOhKddoN4O70xnK9GNB042cxyia+M3wmTLYTKGtuOMmahKagtb0UlxYiEphI2CVLWdas5pnkOUSvC4WJDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:57.254553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.12892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4050c03bd3750c2afb868b8f1f9685eeacee1ae975a27c3c449d0bcb01b109c0","sha256:b13a9b0eed48965b22b75c09b28074603a328ec90475c6a0e0c4b155e504a142"],"state_sha256":"cd62ab02ef076bfb35195311bd47ea926921f8c5e5218f994c3482f6f6fd0650"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXdxkUKGkOwtoD2Owd5GHogr5kv6Gmkr9OJxsLVzOZ+Z9cRFSnMxeI8dri2WPCXHiSGv4kJXetAFcXB3cNOWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:59:01.150161Z","bundle_sha256":"30c1405c6b7e86c6c0a64089f017f780111804baf7e14c43d532b4f9cb861d87"}}