{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:A4C7ODYYCUGEJQGQY7DM6JIP65","short_pith_number":"pith:A4C7ODYY","canonical_record":{"source":{"id":"2301.01400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T01:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"606eec9dcb70771ec2b312595eaf463e7cabb6e0683bc0fb85cab52a653b2255","abstract_canon_sha256":"b02e27c528819488247e58860714432aa54f2fe9ac55ebf96ca91ade98e7cee2"},"schema_version":"1.0"},"canonical_sha256":"0705f70f18150c44c0d0c7c6cf250ff7791480654e75af9cd90bb4d3647a6609","source":{"kind":"arxiv","id":"2301.01400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01400","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01400v1","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01400","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"A4C7ODYYCUGE","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"pith_short_16","alias_value":"A4C7ODYYCUGEJQGQ","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"pith_short_8","alias_value":"A4C7ODYY","created_at":"2026-07-05T05:30:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:A4C7ODYYCUGEJQGQY7DM6JIP65","target":"record","payload":{"canonical_record":{"source":{"id":"2301.01400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T01:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"606eec9dcb70771ec2b312595eaf463e7cabb6e0683bc0fb85cab52a653b2255","abstract_canon_sha256":"b02e27c528819488247e58860714432aa54f2fe9ac55ebf96ca91ade98e7cee2"},"schema_version":"1.0"},"canonical_sha256":"0705f70f18150c44c0d0c7c6cf250ff7791480654e75af9cd90bb4d3647a6609","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:35.660372Z","signature_b64":"Jb+eF14Hoz7Q5AXOHcsbffOVAwr0FT2FDjA/qxb71Tcd1IE/MkV25rFs9WYYoM6CSuRiTWi6GPyl9mblfM72CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0705f70f18150c44c0d0c7c6cf250ff7791480654e75af9cd90bb4d3647a6609","last_reissued_at":"2026-07-05T05:30:35.659892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:35.659892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.01400","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":"2026-07-05T05:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NPr1Ik9ZJekDS7i4eqGYJFd2ioeLtT66KrZFU+vhkPx/l4YZHN8xxo7Y8MNdrMyD2W4roj5cwozVUuKIJvABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T19:39:02.643797Z"},"content_sha256":"38887b416576228b8688c6c2a79e425c803b2652a596456ea2878291545f34c3","schema_version":"1.0","event_id":"sha256:38887b416576228b8688c6c2a79e425c803b2652a596456ea2878291545f34c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:A4C7ODYYCUGEJQGQY7DM6JIP65","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Weighting in Meta-learning with Trajectory Optimisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cuong Nguyen, Gustavo Carneiro, Thanh-Toan Do","submitted_at":"2023-01-04T01:36:09Z","abstract_excerpt":"Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions. In this paper, we introduce a new principled and fully-automated task-weighting algorithm for meta-learning methods. By considering the weights of tasks within the same mini-batch as an action, and the meta-parameter of interest as the system state, we cast the task-weighting meta-learning problem to a trajectory optimisation and employ the iterative linear quadratic regulator to determine the optimal act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01400","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/2301.01400/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":"2026-07-05T05:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T9MA9cgrY0O7Uij3sbbbvV0sNWc8UZkOW9W7ojhdU8Q3WXjLr+8ob6UGAopsOVmYS0RMuH/EB37T0rKrb1DkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T19:39:02.644166Z"},"content_sha256":"96fef2151eac6feda420cdb3d0ecf5d9052f5d6524efa6ce2009c0c321ab89af","schema_version":"1.0","event_id":"sha256:96fef2151eac6feda420cdb3d0ecf5d9052f5d6524efa6ce2009c0c321ab89af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4C7ODYYCUGEJQGQY7DM6JIP65/bundle.json","state_url":"https://pith.science/pith/A4C7ODYYCUGEJQGQY7DM6JIP65/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4C7ODYYCUGEJQGQY7DM6JIP65/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":"2026-07-15T19:39:02Z","links":{"resolver":"https://pith.science/pith/A4C7ODYYCUGEJQGQY7DM6JIP65","bundle":"https://pith.science/pith/A4C7ODYYCUGEJQGQY7DM6JIP65/bundle.json","state":"https://pith.science/pith/A4C7ODYYCUGEJQGQY7DM6JIP65/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4C7ODYYCUGEJQGQY7DM6JIP65/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A4C7ODYYCUGEJQGQY7DM6JIP65","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":"b02e27c528819488247e58860714432aa54f2fe9ac55ebf96ca91ade98e7cee2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T01:36:09Z","title_canon_sha256":"606eec9dcb70771ec2b312595eaf463e7cabb6e0683bc0fb85cab52a653b2255"},"schema_version":"1.0","source":{"id":"2301.01400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01400","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01400v1","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01400","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"A4C7ODYYCUGE","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"pith_short_16","alias_value":"A4C7ODYYCUGEJQGQ","created_at":"2026-07-05T05:30:35Z"},{"alias_kind":"pith_short_8","alias_value":"A4C7ODYY","created_at":"2026-07-05T05:30:35Z"}],"graph_snapshots":[{"event_id":"sha256:96fef2151eac6feda420cdb3d0ecf5d9052f5d6524efa6ce2009c0c321ab89af","target":"graph","created_at":"2026-07-05T05:30:35Z","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/2301.01400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions. In this paper, we introduce a new principled and fully-automated task-weighting algorithm for meta-learning methods. By considering the weights of tasks within the same mini-batch as an action, and the meta-parameter of interest as the system state, we cast the task-weighting meta-learning problem to a trajectory optimisation and employ the iterative linear quadratic regulator to determine the optimal act","authors_text":"Cuong Nguyen, Gustavo Carneiro, Thanh-Toan Do","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T01:36:09Z","title":"Task Weighting in Meta-learning with Trajectory Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01400","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":"sha256:38887b416576228b8688c6c2a79e425c803b2652a596456ea2878291545f34c3","target":"record","created_at":"2026-07-05T05:30:35Z","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":"b02e27c528819488247e58860714432aa54f2fe9ac55ebf96ca91ade98e7cee2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T01:36:09Z","title_canon_sha256":"606eec9dcb70771ec2b312595eaf463e7cabb6e0683bc0fb85cab52a653b2255"},"schema_version":"1.0","source":{"id":"2301.01400","kind":"arxiv","version":1}},"canonical_sha256":"0705f70f18150c44c0d0c7c6cf250ff7791480654e75af9cd90bb4d3647a6609","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0705f70f18150c44c0d0c7c6cf250ff7791480654e75af9cd90bb4d3647a6609","first_computed_at":"2026-07-05T05:30:35.659892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:35.659892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jb+eF14Hoz7Q5AXOHcsbffOVAwr0FT2FDjA/qxb71Tcd1IE/MkV25rFs9WYYoM6CSuRiTWi6GPyl9mblfM72CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:35.660372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.01400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38887b416576228b8688c6c2a79e425c803b2652a596456ea2878291545f34c3","sha256:96fef2151eac6feda420cdb3d0ecf5d9052f5d6524efa6ce2009c0c321ab89af"],"state_sha256":"021c192f61a3da74702eb2077bcf1a172f36d8b0576815aed0bcf1bd20294319"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYV9EJC0rQd8gRYvKBJyWS5kpsIWft6OKB83OiyGPpKSbOktXejN/3JSVfxj0dVQ1Xx0hyKRIxI0ntkATOoECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T19:39:02.646238Z","bundle_sha256":"bdd0ee4f3bd51dc76587333ca992f291f3fa89c2ed193eb7b6ad211a5573165e"}}