{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IS6LUFRVXEKR4JUYGB7XVLL2CL","short_pith_number":"pith:IS6LUFRV","canonical_record":{"source":{"id":"2509.02418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T15:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"3501625ee681d6d5dd9525407317c8a53a9c230168f22de717d9d04b00bc5ba4","abstract_canon_sha256":"81022b7a2325a797c9190eaed771e4d98ffa9b42f6ef55ed68c8af0c0e5697d2"},"schema_version":"1.0"},"canonical_sha256":"44bcba1635b9151e2698307f7aad7a12e397bd7eb313d5d055c6fa4767a4cce9","source":{"kind":"arxiv","id":"2509.02418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02418","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02418v1","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02418","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"pith_short_12","alias_value":"IS6LUFRVXEKR","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"pith_short_16","alias_value":"IS6LUFRVXEKR4JUY","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"pith_short_8","alias_value":"IS6LUFRV","created_at":"2026-07-05T12:03:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IS6LUFRVXEKR4JUYGB7XVLL2CL","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T15:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"3501625ee681d6d5dd9525407317c8a53a9c230168f22de717d9d04b00bc5ba4","abstract_canon_sha256":"81022b7a2325a797c9190eaed771e4d98ffa9b42f6ef55ed68c8af0c0e5697d2"},"schema_version":"1.0"},"canonical_sha256":"44bcba1635b9151e2698307f7aad7a12e397bd7eb313d5d055c6fa4767a4cce9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:38.200907Z","signature_b64":"WcLQmXSyo2rZZtVsu1BWkZScVI0TdX5QZzVe6kFg8zHrKo6zHz1XQ1xJovOyS9K9v8f0rXJSS6YMgiQMWs6zDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44bcba1635b9151e2698307f7aad7a12e397bd7eb313d5d055c6fa4767a4cce9","last_reissued_at":"2026-07-05T12:03:38.200439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:38.200439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02418","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":"2026-07-05T12:03:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+7MO9+O+B49mgd5aTs20mMItIt+EJceerYUgWM5t3PdD4DrhmdjN7sI9ldBxIOtyamBrPXgkxhiSJV5qTMTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:08:13.547689Z"},"content_sha256":"66ab97c64d7ca79359f608f162ab193d572a16dbade65b07e8d0e5743013b245","schema_version":"1.0","event_id":"sha256:66ab97c64d7ca79359f608f162ab193d572a16dbade65b07e8d0e5743013b245"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IS6LUFRVXEKR4JUYGB7XVLL2CL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingcong Li, Georgios B. Giannakis, Yilang Zhang","submitted_at":"2025-09-02T15:23:21Z","abstract_excerpt":"Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sample-efficient adaptation of this prior information is a major challenge facing meta-learning, and plays an important role because it facilitates training the sought task-specific model with just a few optimization steps. Past works deal with this challenge through preconditioning that speeds up convergence of the per-task training. Though effective in representing locally quadratic loss curvatures, simple linear pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02418","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/2509.02418/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":"2026-07-05T12:03:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nyj9ALbYfUphJVP6p4+rVxyhNok8OQklMQm4YDg1FYPP/xSWww04N/+gxMmAhlHA3eLvwPG7dxoac7p6qQMIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:08:13.548231Z"},"content_sha256":"ac015a8f27cee0aa120275f6a5c508bef60590d0d84050205bdf4a825de4fb4d","schema_version":"1.0","event_id":"sha256:ac015a8f27cee0aa120275f6a5c508bef60590d0d84050205bdf4a825de4fb4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL/bundle.json","state_url":"https://pith.science/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL/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":"2026-08-06T16:08:13Z","links":{"resolver":"https://pith.science/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL","bundle":"https://pith.science/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL/bundle.json","state":"https://pith.science/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IS6LUFRVXEKR4JUYGB7XVLL2CL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IS6LUFRVXEKR4JUYGB7XVLL2CL","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":"81022b7a2325a797c9190eaed771e4d98ffa9b42f6ef55ed68c8af0c0e5697d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T15:23:21Z","title_canon_sha256":"3501625ee681d6d5dd9525407317c8a53a9c230168f22de717d9d04b00bc5ba4"},"schema_version":"1.0","source":{"id":"2509.02418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02418","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02418v1","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02418","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"pith_short_12","alias_value":"IS6LUFRVXEKR","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"pith_short_16","alias_value":"IS6LUFRVXEKR4JUY","created_at":"2026-07-05T12:03:38Z"},{"alias_kind":"pith_short_8","alias_value":"IS6LUFRV","created_at":"2026-07-05T12:03:38Z"}],"graph_snapshots":[{"event_id":"sha256:ac015a8f27cee0aa120275f6a5c508bef60590d0d84050205bdf4a825de4fb4d","target":"graph","created_at":"2026-07-05T12:03:38Z","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/2509.02418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sample-efficient adaptation of this prior information is a major challenge facing meta-learning, and plays an important role because it facilitates training the sought task-specific model with just a few optimization steps. Past works deal with this challenge through preconditioning that speeds up convergence of the per-task training. Though effective in representing locally quadratic loss curvatures, simple linear pre","authors_text":"Bingcong Li, Georgios B. Giannakis, Yilang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T15:23:21Z","title":"Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02418","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":"sha256:66ab97c64d7ca79359f608f162ab193d572a16dbade65b07e8d0e5743013b245","target":"record","created_at":"2026-07-05T12:03:38Z","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":"81022b7a2325a797c9190eaed771e4d98ffa9b42f6ef55ed68c8af0c0e5697d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T15:23:21Z","title_canon_sha256":"3501625ee681d6d5dd9525407317c8a53a9c230168f22de717d9d04b00bc5ba4"},"schema_version":"1.0","source":{"id":"2509.02418","kind":"arxiv","version":1}},"canonical_sha256":"44bcba1635b9151e2698307f7aad7a12e397bd7eb313d5d055c6fa4767a4cce9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44bcba1635b9151e2698307f7aad7a12e397bd7eb313d5d055c6fa4767a4cce9","first_computed_at":"2026-07-05T12:03:38.200439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:38.200439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WcLQmXSyo2rZZtVsu1BWkZScVI0TdX5QZzVe6kFg8zHrKo6zHz1XQ1xJovOyS9K9v8f0rXJSS6YMgiQMWs6zDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:38.200907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66ab97c64d7ca79359f608f162ab193d572a16dbade65b07e8d0e5743013b245","sha256:ac015a8f27cee0aa120275f6a5c508bef60590d0d84050205bdf4a825de4fb4d"],"state_sha256":"f55f54533e385be517919fee79f6dc5d0f4b09f4fe1b8b34cf768011638c3166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QRuuYzMBgQAHLWEgmzCK5IgypkhSxRm7ItOeSBop6eQjJtWyruIGCJRgeuVNg4plC4huBzAvsxk6iJIVK8nHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:08:13.553257Z","bundle_sha256":"bb8b301929462048fdd61d5f614f2f7cae609dd5d26ab6eb4dc459c3d481b91a"}}