{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DKB72V4TOOV6VQAO724QSKY2DN","short_pith_number":"pith:DKB72V4T","canonical_record":{"source":{"id":"2107.09661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T17:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"8d3149178235e963604dfb99124e99bd55b9f0148083a62015b3e4ef565745c1","abstract_canon_sha256":"47bef75cc43a00e7ce4e5d41d9d5320caa6264b377b0fe560765b13b80e2514b"},"schema_version":"1.0"},"canonical_sha256":"1a83fd579373abeac00efeb9092b1a1b44a4f57b5dcdcc02ab95e4e40592fc91","source":{"kind":"arxiv","id":"2107.09661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09661","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09661v1","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09661","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"DKB72V4TOOV6","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"pith_short_16","alias_value":"DKB72V4TOOV6VQAO","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"pith_short_8","alias_value":"DKB72V4T","created_at":"2026-07-05T02:59:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DKB72V4TOOV6VQAO724QSKY2DN","target":"record","payload":{"canonical_record":{"source":{"id":"2107.09661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T17:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"8d3149178235e963604dfb99124e99bd55b9f0148083a62015b3e4ef565745c1","abstract_canon_sha256":"47bef75cc43a00e7ce4e5d41d9d5320caa6264b377b0fe560765b13b80e2514b"},"schema_version":"1.0"},"canonical_sha256":"1a83fd579373abeac00efeb9092b1a1b44a4f57b5dcdcc02ab95e4e40592fc91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:33.703819Z","signature_b64":"ikHzgvmsfVbi9nWUJYUssBfaFXiVcsQrpIoI3eNcm/psYwKB9cbB/eEEN93/Gbc1z0Qu2y7tTfShbOFbSnmgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a83fd579373abeac00efeb9092b1a1b44a4f57b5dcdcc02ab95e4e40592fc91","last_reissued_at":"2026-07-05T02:59:33.703402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:33.703402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.09661","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":"2026-07-05T02:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2pt1Qiy8X7Z7Xacwjdq1iuO2atxbURmTqmJnyxGeO9Z2dN8wmeXd17rl6ptGASb0IJZ1f9xn/5jGS+BvKuUWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:12:27.572541Z"},"content_sha256":"221ea9ef7634bb405c23599e070e73140a80d257d849947581a334a394f61fae","schema_version":"1.0","event_id":"sha256:221ea9ef7634bb405c23599e070e73140a80d257d849947581a334a394f61fae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DKB72V4TOOV6VQAO724QSKY2DN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learn2Hop: Learned Optimization on Rough Landscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amil Merchant, Ekin Dogus Cubuk, Luke Metz, Sam Schoenholz","submitted_at":"2021-07-20T17:57:19Z","abstract_excerpt":"Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design. Yet, current techniques either require extremely high iteration counts or a large number of random restarts for good performance. In this work, we propose adapting recent developments in meta-learning to these many-minima problems by learning the optimization algorithm for various loss landscapes. We focus on problems from atomic structural optimization--finding low energy configurations of many-atom systems--"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09661","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/2107.09661/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":"2026-07-05T02:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1u7zBNP4d0RdKxtU2EXWlcOM9eLM2xwUO+ECP8mEa+wZt9sHylmuDnW3CpfTlhcSkDyDEaCmeSC8sg18pVopCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:12:27.572923Z"},"content_sha256":"b56e9ceb8192b5882043b0ab9eed203f8ce7e3b6015a3543ea4692f16114fa79","schema_version":"1.0","event_id":"sha256:b56e9ceb8192b5882043b0ab9eed203f8ce7e3b6015a3543ea4692f16114fa79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKB72V4TOOV6VQAO724QSKY2DN/bundle.json","state_url":"https://pith.science/pith/DKB72V4TOOV6VQAO724QSKY2DN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKB72V4TOOV6VQAO724QSKY2DN/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":"2026-07-05T07:12:27Z","links":{"resolver":"https://pith.science/pith/DKB72V4TOOV6VQAO724QSKY2DN","bundle":"https://pith.science/pith/DKB72V4TOOV6VQAO724QSKY2DN/bundle.json","state":"https://pith.science/pith/DKB72V4TOOV6VQAO724QSKY2DN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKB72V4TOOV6VQAO724QSKY2DN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DKB72V4TOOV6VQAO724QSKY2DN","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":"47bef75cc43a00e7ce4e5d41d9d5320caa6264b377b0fe560765b13b80e2514b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T17:57:19Z","title_canon_sha256":"8d3149178235e963604dfb99124e99bd55b9f0148083a62015b3e4ef565745c1"},"schema_version":"1.0","source":{"id":"2107.09661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09661","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09661v1","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09661","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"DKB72V4TOOV6","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"pith_short_16","alias_value":"DKB72V4TOOV6VQAO","created_at":"2026-07-05T02:59:33Z"},{"alias_kind":"pith_short_8","alias_value":"DKB72V4T","created_at":"2026-07-05T02:59:33Z"}],"graph_snapshots":[{"event_id":"sha256:b56e9ceb8192b5882043b0ab9eed203f8ce7e3b6015a3543ea4692f16114fa79","target":"graph","created_at":"2026-07-05T02:59:33Z","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/2107.09661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design. Yet, current techniques either require extremely high iteration counts or a large number of random restarts for good performance. In this work, we propose adapting recent developments in meta-learning to these many-minima problems by learning the optimization algorithm for various loss landscapes. We focus on problems from atomic structural optimization--finding low energy configurations of many-atom systems--","authors_text":"Amil Merchant, Ekin Dogus Cubuk, Luke Metz, Sam Schoenholz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T17:57:19Z","title":"Learn2Hop: Learned Optimization on Rough Landscapes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09661","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":"sha256:221ea9ef7634bb405c23599e070e73140a80d257d849947581a334a394f61fae","target":"record","created_at":"2026-07-05T02:59:33Z","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":"47bef75cc43a00e7ce4e5d41d9d5320caa6264b377b0fe560765b13b80e2514b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-20T17:57:19Z","title_canon_sha256":"8d3149178235e963604dfb99124e99bd55b9f0148083a62015b3e4ef565745c1"},"schema_version":"1.0","source":{"id":"2107.09661","kind":"arxiv","version":1}},"canonical_sha256":"1a83fd579373abeac00efeb9092b1a1b44a4f57b5dcdcc02ab95e4e40592fc91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a83fd579373abeac00efeb9092b1a1b44a4f57b5dcdcc02ab95e4e40592fc91","first_computed_at":"2026-07-05T02:59:33.703402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:33.703402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ikHzgvmsfVbi9nWUJYUssBfaFXiVcsQrpIoI3eNcm/psYwKB9cbB/eEEN93/Gbc1z0Qu2y7tTfShbOFbSnmgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:33.703819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:221ea9ef7634bb405c23599e070e73140a80d257d849947581a334a394f61fae","sha256:b56e9ceb8192b5882043b0ab9eed203f8ce7e3b6015a3543ea4692f16114fa79"],"state_sha256":"811d66ef6f800e2b2e3d362cee1c0cffd632c56805ef5fb40ff727edaabf955f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FBvdR7zBoe5YDZdfga7C7af4PcgVwfalPknSddACY4C9DeL+hr9INeI2MyLmhaf/IVPQ8XcAA85VZMSpXjWVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T07:12:27.575265Z","bundle_sha256":"cf3dc16dd13c36665270feea1370687e6512c093322bc85639788f982c3ee8a3"}}