{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:547GPV56QK23CYQE3F2YQ4XWM4","short_pith_number":"pith:547GPV56","canonical_record":{"source":{"id":"2103.04691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T11:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"bdf2e914f04e910327627eacbb23d08ebbdec6d5b76601ccf38c6283795da68b","abstract_canon_sha256":"b971808558f1442b04f72e32c0140882aa4c41813f5766268b6b37cc6a824b21"},"schema_version":"1.0"},"canonical_sha256":"ef3e67d7be82b5b16204d9758872f667155cae264889262e341231257f37299f","source":{"kind":"arxiv","id":"2103.04691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04691","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04691v1","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04691","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"547GPV56QK23","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"547GPV56QK23CYQE","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"547GPV56","created_at":"2026-07-05T02:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:547GPV56QK23CYQE3F2YQ4XWM4","target":"record","payload":{"canonical_record":{"source":{"id":"2103.04691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T11:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"bdf2e914f04e910327627eacbb23d08ebbdec6d5b76601ccf38c6283795da68b","abstract_canon_sha256":"b971808558f1442b04f72e32c0140882aa4c41813f5766268b6b37cc6a824b21"},"schema_version":"1.0"},"canonical_sha256":"ef3e67d7be82b5b16204d9758872f667155cae264889262e341231257f37299f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:08.450044Z","signature_b64":"cv+fLl1CqyF9S2p2bkXnyBnc3taKJb88KHnoWcFSxJc5Z+lxOpUqCdxnHpUz19bpvXgAjzZ/nkTtNfl9VpotBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3e67d7be82b5b16204d9758872f667155cae264889262e341231257f37299f","last_reissued_at":"2026-07-05T02:21:08.449658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:08.449658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.04691","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":"2026-07-05T02:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nti2TEIT7Hsa/4FL/lB7RwKMu6UQma11N5BGGW4QFTllzhsRa4amXD7EoT9qRpxLJJZ42XnmwAR+cYoEyxcrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:09:03.054340Z"},"content_sha256":"b6e228836a1d5699f5f908a5699207561159ed9110a6a4c2547b08428d5cb94f","schema_version":"1.0","event_id":"sha256:b6e228836a1d5699f5f908a5699207561159ed9110a6a4c2547b08428d5cb94f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:547GPV56QK23CYQE3F2YQ4XWM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning with MAML on Trees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Bernacchia, Da-shan Shiu, Federica Freddi, Feng-Ting Liao, Jamie McGowan, Jezabel R. Garcia, Tim Nieradzik, Ye Tian","submitted_at":"2021-03-08T11:58:48Z","abstract_excerpt":"In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related. Sharing information between unrelated tasks might hurt performance, and it is unclear how to transfer knowledge across tasks with a hierarchical structure. Our research extends a model agnostic meta-learning model, MAML, by exploiting hierarchical task relationships. Our algorithm, TreeMAML, adapts the model to each task with a few gradient steps, but the adaptation follows the hierarchical tree structure: in each step, gradients are pooled across tasks clu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04691","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/2103.04691/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":"2026-07-05T02:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2GM4uaFnSZY9mcbSarOi7j5LYBQkHvi6fyPwVCQC/W3TEnhqcQO+FN+6CIAQpG+q+bw7KcB93dzEsIrOVtXkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:09:03.054721Z"},"content_sha256":"953fbf583c7e5be22fcdc18346749ddb7e7cb19c5d949b68e5156ec304bac1e3","schema_version":"1.0","event_id":"sha256:953fbf583c7e5be22fcdc18346749ddb7e7cb19c5d949b68e5156ec304bac1e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/547GPV56QK23CYQE3F2YQ4XWM4/bundle.json","state_url":"https://pith.science/pith/547GPV56QK23CYQE3F2YQ4XWM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/547GPV56QK23CYQE3F2YQ4XWM4/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":"2026-07-07T08:09:03Z","links":{"resolver":"https://pith.science/pith/547GPV56QK23CYQE3F2YQ4XWM4","bundle":"https://pith.science/pith/547GPV56QK23CYQE3F2YQ4XWM4/bundle.json","state":"https://pith.science/pith/547GPV56QK23CYQE3F2YQ4XWM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/547GPV56QK23CYQE3F2YQ4XWM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:547GPV56QK23CYQE3F2YQ4XWM4","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":"b971808558f1442b04f72e32c0140882aa4c41813f5766268b6b37cc6a824b21","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T11:58:48Z","title_canon_sha256":"bdf2e914f04e910327627eacbb23d08ebbdec6d5b76601ccf38c6283795da68b"},"schema_version":"1.0","source":{"id":"2103.04691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04691","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04691v1","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04691","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"547GPV56QK23","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"547GPV56QK23CYQE","created_at":"2026-07-05T02:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"547GPV56","created_at":"2026-07-05T02:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:953fbf583c7e5be22fcdc18346749ddb7e7cb19c5d949b68e5156ec304bac1e3","target":"graph","created_at":"2026-07-05T02:21:08Z","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/2103.04691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related. Sharing information between unrelated tasks might hurt performance, and it is unclear how to transfer knowledge across tasks with a hierarchical structure. Our research extends a model agnostic meta-learning model, MAML, by exploiting hierarchical task relationships. Our algorithm, TreeMAML, adapts the model to each task with a few gradient steps, but the adaptation follows the hierarchical tree structure: in each step, gradients are pooled across tasks clu","authors_text":"Alberto Bernacchia, Da-shan Shiu, Federica Freddi, Feng-Ting Liao, Jamie McGowan, Jezabel R. Garcia, Tim Nieradzik, Ye Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T11:58:48Z","title":"Meta-Learning with MAML on Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04691","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:b6e228836a1d5699f5f908a5699207561159ed9110a6a4c2547b08428d5cb94f","target":"record","created_at":"2026-07-05T02:21:08Z","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":"b971808558f1442b04f72e32c0140882aa4c41813f5766268b6b37cc6a824b21","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T11:58:48Z","title_canon_sha256":"bdf2e914f04e910327627eacbb23d08ebbdec6d5b76601ccf38c6283795da68b"},"schema_version":"1.0","source":{"id":"2103.04691","kind":"arxiv","version":1}},"canonical_sha256":"ef3e67d7be82b5b16204d9758872f667155cae264889262e341231257f37299f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef3e67d7be82b5b16204d9758872f667155cae264889262e341231257f37299f","first_computed_at":"2026-07-05T02:21:08.449658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:21:08.449658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cv+fLl1CqyF9S2p2bkXnyBnc3taKJb88KHnoWcFSxJc5Z+lxOpUqCdxnHpUz19bpvXgAjzZ/nkTtNfl9VpotBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:21:08.450044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6e228836a1d5699f5f908a5699207561159ed9110a6a4c2547b08428d5cb94f","sha256:953fbf583c7e5be22fcdc18346749ddb7e7cb19c5d949b68e5156ec304bac1e3"],"state_sha256":"66b0a97a7fcaac4da1a3d1c1a83ee9f4626d49ec35d5b6487102acfcda151b3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OSA6iEx7YD+WBrDWXq+wEK427IPSrWw/e+5yIbN1poXZnM4gIE/0gMM8IU9Owr1uAUwIarniM6e2O4IJqNPfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:09:03.056671Z","bundle_sha256":"7441928c8a0626aefd26ada4d252c29a6a0ed6d7341234ccbb1e7533ffaae192"}}