{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AMKNFLVTOXJK76JZJJ4A7QABBA","short_pith_number":"pith:AMKNFLVT","canonical_record":{"source":{"id":"2607.23925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T01:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"0cfc5af3acee1502222dd85005093bdff5fb4e98315a4e152a84c31369111005","abstract_canon_sha256":"433c67dfe43286f5c87dadd8d307d9ade76d4296db0d3fa462cd88bcc610dc60"},"schema_version":"1.0"},"canonical_sha256":"0314d2aeb375d2aff9394a780fc00108120259e82f8b0c4f0add38517594f8ab","source":{"kind":"arxiv","id":"2607.23925","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23925","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23925v1","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23925","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"AMKNFLVTOXJK","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"AMKNFLVTOXJK76JZ","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"AMKNFLVT","created_at":"2026-07-28T01:23:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AMKNFLVTOXJK76JZJJ4A7QABBA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T01:36:40Z","cross_cats_sorted":[],"title_canon_sha256":"0cfc5af3acee1502222dd85005093bdff5fb4e98315a4e152a84c31369111005","abstract_canon_sha256":"433c67dfe43286f5c87dadd8d307d9ade76d4296db0d3fa462cd88bcc610dc60"},"schema_version":"1.0"},"canonical_sha256":"0314d2aeb375d2aff9394a780fc00108120259e82f8b0c4f0add38517594f8ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:18.048552Z","signature_b64":"wbbFhskQSpGGXSWLAZxB3HzIA+YRpXBEdwuQlnoZo7jfUTBO9I85AFnXPkHRIq8jAR2a4GBKpCgoRLTRTfRiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0314d2aeb375d2aff9394a780fc00108120259e82f8b0c4f0add38517594f8ab","last_reissued_at":"2026-07-28T01:23:18.047696Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:18.047696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23925","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":"2026-07-28T01:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zNVhUcGaQg4yUc5onQyvRFYqDRxoQIXaav479Hiz8m3eSiDrZ9WnbP8eYrkg1PGCFa/ftwInyM2YdQFNBjg2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:57.744118Z"},"content_sha256":"3ec4fa7995f1ba5907dccd2ea7a717321e07ae775dc97957ffae0ab311d56498","schema_version":"1.0","event_id":"sha256:3ec4fa7995f1ba5907dccd2ea7a717321e07ae775dc97957ffae0ab311d56498"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AMKNFLVTOXJK76JZJJ4A7QABBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Greedy dynamical meta-learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aria Yom","submitted_at":"2026-07-27T01:36:40Z","abstract_excerpt":"Gradient descent scales well to large models, but becomes unstable over long time horizons. Gradient-free optimizers can scale to arbitrary timespans, but are hobbled by high dimensions. Since learning occurs in large models over long timescales, neither of these approaches is likely to produce traits which can accelerate the learning process. Instead, we propose a meta-learning algorithm in which the agent learns to modify its own weights and biases. Our algorithm consists of an inner loop, wherein the agent performs some high-dimensional optimization upon itself, and an outer loop, wherein w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23925","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/2607.23925/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":"2026-07-28T01:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xtPP+TwSW2UZStWnotQ+TmGVlHs8Sjd+QmC9Tjjq6vuiYM0cWH7J5YK09z6GUT9hnOJ9Zsm3HvpS1McvsHXtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:05:57.744723Z"},"content_sha256":"f0adf5e59a4cfa2101a7d0c8357bf9e08e7dc6dcb2f5acb2ae768573065cfae5","schema_version":"1.0","event_id":"sha256:f0adf5e59a4cfa2101a7d0c8357bf9e08e7dc6dcb2f5acb2ae768573065cfae5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMKNFLVTOXJK76JZJJ4A7QABBA/bundle.json","state_url":"https://pith.science/pith/AMKNFLVTOXJK76JZJJ4A7QABBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMKNFLVTOXJK76JZJJ4A7QABBA/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":"2026-08-04T19:05:57Z","links":{"resolver":"https://pith.science/pith/AMKNFLVTOXJK76JZJJ4A7QABBA","bundle":"https://pith.science/pith/AMKNFLVTOXJK76JZJJ4A7QABBA/bundle.json","state":"https://pith.science/pith/AMKNFLVTOXJK76JZJJ4A7QABBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMKNFLVTOXJK76JZJJ4A7QABBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AMKNFLVTOXJK76JZJJ4A7QABBA","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":"433c67dfe43286f5c87dadd8d307d9ade76d4296db0d3fa462cd88bcc610dc60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T01:36:40Z","title_canon_sha256":"0cfc5af3acee1502222dd85005093bdff5fb4e98315a4e152a84c31369111005"},"schema_version":"1.0","source":{"id":"2607.23925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23925","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23925v1","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23925","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"AMKNFLVTOXJK","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"AMKNFLVTOXJK76JZ","created_at":"2026-07-28T01:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"AMKNFLVT","created_at":"2026-07-28T01:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:f0adf5e59a4cfa2101a7d0c8357bf9e08e7dc6dcb2f5acb2ae768573065cfae5","target":"graph","created_at":"2026-07-28T01:23:18Z","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/2607.23925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient descent scales well to large models, but becomes unstable over long time horizons. Gradient-free optimizers can scale to arbitrary timespans, but are hobbled by high dimensions. Since learning occurs in large models over long timescales, neither of these approaches is likely to produce traits which can accelerate the learning process. Instead, we propose a meta-learning algorithm in which the agent learns to modify its own weights and biases. Our algorithm consists of an inner loop, wherein the agent performs some high-dimensional optimization upon itself, and an outer loop, wherein w","authors_text":"Aria Yom","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T01:36:40Z","title":"Greedy dynamical meta-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23925","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":"sha256:3ec4fa7995f1ba5907dccd2ea7a717321e07ae775dc97957ffae0ab311d56498","target":"record","created_at":"2026-07-28T01:23:18Z","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":"433c67dfe43286f5c87dadd8d307d9ade76d4296db0d3fa462cd88bcc610dc60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T01:36:40Z","title_canon_sha256":"0cfc5af3acee1502222dd85005093bdff5fb4e98315a4e152a84c31369111005"},"schema_version":"1.0","source":{"id":"2607.23925","kind":"arxiv","version":1}},"canonical_sha256":"0314d2aeb375d2aff9394a780fc00108120259e82f8b0c4f0add38517594f8ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0314d2aeb375d2aff9394a780fc00108120259e82f8b0c4f0add38517594f8ab","first_computed_at":"2026-07-28T01:23:18.047696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:18.047696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbbFhskQSpGGXSWLAZxB3HzIA+YRpXBEdwuQlnoZo7jfUTBO9I85AFnXPkHRIq8jAR2a4GBKpCgoRLTRTfRiAg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:18.048552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ec4fa7995f1ba5907dccd2ea7a717321e07ae775dc97957ffae0ab311d56498","sha256:f0adf5e59a4cfa2101a7d0c8357bf9e08e7dc6dcb2f5acb2ae768573065cfae5"],"state_sha256":"27d88b3e0097ab13a01666be19498066b63d9720a3298fd599cc63cf15df668b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQqSi+3CxPm1VRLye6pe1rlGi5hWNnpcOucwK+yXjShPtHbb1xwh3PNizNqkkH1l6JOno0fT7aVPJ5PNjNAECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:05:57.749951Z","bundle_sha256":"699e31f9b9da6285ecf68f8e23467d042a179bd552f7893478dfad4155433932"}}