{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SVOW2NYMQ5RQFOOVJCQMRZF764","short_pith_number":"pith:SVOW2NYM","canonical_record":{"source":{"id":"2410.18894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T16:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"258b1e9551fbeb127eb1b265dd607bc2e112758a0dcd63987e7f1dea971e6cef","abstract_canon_sha256":"e1d8e7d574b4ede4d2bb606cc4235a58c6a1c83292fee060362507ca09d20572"},"schema_version":"1.0"},"canonical_sha256":"955d6d370c876302b9d548a0c8e4bff70e42825c6600d33b2225c0f1352504de","source":{"kind":"arxiv","id":"2410.18894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18894","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18894v1","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18894","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"SVOW2NYMQ5RQ","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"SVOW2NYMQ5RQFOOV","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"SVOW2NYM","created_at":"2026-07-05T09:25:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SVOW2NYMQ5RQFOOVJCQMRZF764","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T16:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"258b1e9551fbeb127eb1b265dd607bc2e112758a0dcd63987e7f1dea971e6cef","abstract_canon_sha256":"e1d8e7d574b4ede4d2bb606cc4235a58c6a1c83292fee060362507ca09d20572"},"schema_version":"1.0"},"canonical_sha256":"955d6d370c876302b9d548a0c8e4bff70e42825c6600d33b2225c0f1352504de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:21.713883Z","signature_b64":"eawJKXY+onoThwBseE7oPbCk1Vrplpo1TAQ2PGAQVwA+lbxVEIvUucr32km/CSblrbMLh32ZHjpdl9oA6yV+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"955d6d370c876302b9d548a0c8e4bff70e42825c6600d33b2225c0f1352504de","last_reissued_at":"2026-07-05T09:25:21.713460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:21.713460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18894","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":"2026-07-05T09:25:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5tEIFwViz6mqnYWaheQT7Y3ykl0fnisUBHjAJ4tlJnKvlX/WLG/0U84lP45PEib5gqe1BPmcqgIiJI3EOvD3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:44:32.714558Z"},"content_sha256":"81d4d7ff5f810c43a3946f265d11c1186a57f6eea73c09559ed117eb3cefa9bc","schema_version":"1.0","event_id":"sha256:81d4d7ff5f810c43a3946f265d11c1186a57f6eea73c09559ed117eb3cefa9bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SVOW2NYMQ5RQFOOVJCQMRZF764","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning with Heterogeneous Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiyi Ji, Shu Hu, Siwei Lyu, Zhaofeng Si","submitted_at":"2024-10-24T16:32:23Z","abstract_excerpt":"Meta-learning is a general approach to equip machine learning models with the ability to handle few-shot scenarios when dealing with many tasks. Most existing meta-learning methods work based on the assumption that all tasks are of equal importance. However, real-world applications often present heterogeneous tasks characterized by varying difficulty levels, noise in training samples, or being distinctively different from most other tasks. In this paper, we introduce a novel meta-learning method designed to effectively manage such heterogeneous tasks by employing rank-based task-level learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18894","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/2410.18894/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":"2026-07-05T09:25:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4y3IyVA3gq1GwsoCBQrOG/E+WmFEqL356WyGfAHQ1KBn3yFVDwCLPOFUVqAqxlx6YiysRLqTbeW6ibREJypAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:44:32.715507Z"},"content_sha256":"20bdb1398afdfd8adc3c47a4642cecc242359119c57a8f7da0021fd3002fd8fc","schema_version":"1.0","event_id":"sha256:20bdb1398afdfd8adc3c47a4642cecc242359119c57a8f7da0021fd3002fd8fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVOW2NYMQ5RQFOOVJCQMRZF764/bundle.json","state_url":"https://pith.science/pith/SVOW2NYMQ5RQFOOVJCQMRZF764/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVOW2NYMQ5RQFOOVJCQMRZF764/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":"2026-08-04T02:44:32Z","links":{"resolver":"https://pith.science/pith/SVOW2NYMQ5RQFOOVJCQMRZF764","bundle":"https://pith.science/pith/SVOW2NYMQ5RQFOOVJCQMRZF764/bundle.json","state":"https://pith.science/pith/SVOW2NYMQ5RQFOOVJCQMRZF764/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVOW2NYMQ5RQFOOVJCQMRZF764/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SVOW2NYMQ5RQFOOVJCQMRZF764","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":"e1d8e7d574b4ede4d2bb606cc4235a58c6a1c83292fee060362507ca09d20572","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T16:32:23Z","title_canon_sha256":"258b1e9551fbeb127eb1b265dd607bc2e112758a0dcd63987e7f1dea971e6cef"},"schema_version":"1.0","source":{"id":"2410.18894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18894","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18894v1","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18894","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"pith_short_12","alias_value":"SVOW2NYMQ5RQ","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"pith_short_16","alias_value":"SVOW2NYMQ5RQFOOV","created_at":"2026-07-05T09:25:21Z"},{"alias_kind":"pith_short_8","alias_value":"SVOW2NYM","created_at":"2026-07-05T09:25:21Z"}],"graph_snapshots":[{"event_id":"sha256:20bdb1398afdfd8adc3c47a4642cecc242359119c57a8f7da0021fd3002fd8fc","target":"graph","created_at":"2026-07-05T09:25:21Z","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/2410.18894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-learning is a general approach to equip machine learning models with the ability to handle few-shot scenarios when dealing with many tasks. Most existing meta-learning methods work based on the assumption that all tasks are of equal importance. However, real-world applications often present heterogeneous tasks characterized by varying difficulty levels, noise in training samples, or being distinctively different from most other tasks. In this paper, we introduce a novel meta-learning method designed to effectively manage such heterogeneous tasks by employing rank-based task-level learning","authors_text":"Kaiyi Ji, Shu Hu, Siwei Lyu, Zhaofeng Si","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T16:32:23Z","title":"Meta-Learning with Heterogeneous Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18894","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":"sha256:81d4d7ff5f810c43a3946f265d11c1186a57f6eea73c09559ed117eb3cefa9bc","target":"record","created_at":"2026-07-05T09:25:21Z","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":"e1d8e7d574b4ede4d2bb606cc4235a58c6a1c83292fee060362507ca09d20572","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T16:32:23Z","title_canon_sha256":"258b1e9551fbeb127eb1b265dd607bc2e112758a0dcd63987e7f1dea971e6cef"},"schema_version":"1.0","source":{"id":"2410.18894","kind":"arxiv","version":1}},"canonical_sha256":"955d6d370c876302b9d548a0c8e4bff70e42825c6600d33b2225c0f1352504de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"955d6d370c876302b9d548a0c8e4bff70e42825c6600d33b2225c0f1352504de","first_computed_at":"2026-07-05T09:25:21.713460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:21.713460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eawJKXY+onoThwBseE7oPbCk1Vrplpo1TAQ2PGAQVwA+lbxVEIvUucr32km/CSblrbMLh32ZHjpdl9oA6yV+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:21.713883Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81d4d7ff5f810c43a3946f265d11c1186a57f6eea73c09559ed117eb3cefa9bc","sha256:20bdb1398afdfd8adc3c47a4642cecc242359119c57a8f7da0021fd3002fd8fc"],"state_sha256":"295ceefe197a17506aee826c9b24ffac056b472afb2d422355df07c76d666046"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"npWtHqkEtVY7Nv3+RHJAxq5sq5DlTiYK2CyDG9zsORrs4V1QnqXX2aBHEUHx7m9Rj+siCZSqx0vLmfbdVhmrDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:44:32.784944Z","bundle_sha256":"5379103884ce4c889b8b7d5691180518829d3d02531c26356d917089f97ee914"}}