{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WLF2S3CUDILYONKYNHDHCWJVSD","short_pith_number":"pith:WLF2S3CU","canonical_record":{"source":{"id":"2305.15644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T01:44:09Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8f5402266fc440fbc74100b44d5486ebf44c2e836625f2762414ea14bc44e286","abstract_canon_sha256":"2ebe47aeff9ae60ce9f4ed6f163ff2d0de39229112b7f792111a7791f743899d"},"schema_version":"1.0"},"canonical_sha256":"b2cba96c541a1787355869c671593590ee847dd83e3066bc6c741a6b6e6d1346","source":{"kind":"arxiv","id":"2305.15644","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15644","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15644v1","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15644","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"WLF2S3CUDILY","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"WLF2S3CUDILYONKY","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"WLF2S3CU","created_at":"2026-07-05T06:13:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WLF2S3CUDILYONKYNHDHCWJVSD","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T01:44:09Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8f5402266fc440fbc74100b44d5486ebf44c2e836625f2762414ea14bc44e286","abstract_canon_sha256":"2ebe47aeff9ae60ce9f4ed6f163ff2d0de39229112b7f792111a7791f743899d"},"schema_version":"1.0"},"canonical_sha256":"b2cba96c541a1787355869c671593590ee847dd83e3066bc6c741a6b6e6d1346","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:42.824352Z","signature_b64":"BBbNxVMEb6WcPudoLpO6VpbNK4myYHoBJZ9bWAexLjI45Q8YXcu3FmSVnyCUAj31Fw4DycJlTqBIv5gtlbc5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2cba96c541a1787355869c671593590ee847dd83e3066bc6c741a6b6e6d1346","last_reissued_at":"2026-07-05T06:13:42.823932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:42.823932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15644","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":"2026-07-05T06:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9C2IdwSYzkWCb0P8CkiMVJTfQKV15VhLM24xmabdwjXUQXDLhKdItL27nSC4euK+pixOk8SYJf4XKtOuIUZiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:39:38.244419Z"},"content_sha256":"48eb686663726d5ad14292c9418a39f78df51977635f2007a7a6395aa7d7c0a2","schema_version":"1.0","event_id":"sha256:48eb686663726d5ad14292c9418a39f78df51977635f2007a7a6395aa7d7c0a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WLF2S3CUDILYONKYNHDHCWJVSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta Adaptive Task Sampling for Few-Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Furui Liu, Han Yu, Jiashuo Liu, Linjun Zhou, Peng Cui, Xingxuan Zhang, Zheyan Shen","submitted_at":"2023-05-25T01:44:09Z","abstract_excerpt":"To ensure the out-of-distribution (OOD) generalization performance, traditional domain generalization (DG) methods resort to training on data from multiple sources with different underlying distributions. And the success of those DG methods largely depends on the fact that there are diverse training distributions. However, it usually needs great efforts to obtain enough heterogeneous data due to the high expenses, privacy issues or the scarcity of data. Thus an interesting yet seldom investigated problem arises: how to improve the OOD generalization performance when the perceived heterogeneity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15644","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/2305.15644/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":"2026-07-05T06:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZto2MPqv5xZPxiTM4jNHcyH5tSfdhefJoow+T9r1x0kkxJvc925TY116pC2ZcXTStRJMZ8WsV0zSXHAvgsOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:39:38.245049Z"},"content_sha256":"823d5286bc7a26cd614e7177f77f4c3ec09a15d8a9f3335b284bd3aaf7a4de3b","schema_version":"1.0","event_id":"sha256:823d5286bc7a26cd614e7177f77f4c3ec09a15d8a9f3335b284bd3aaf7a4de3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLF2S3CUDILYONKYNHDHCWJVSD/bundle.json","state_url":"https://pith.science/pith/WLF2S3CUDILYONKYNHDHCWJVSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLF2S3CUDILYONKYNHDHCWJVSD/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":"2026-07-05T14:39:38Z","links":{"resolver":"https://pith.science/pith/WLF2S3CUDILYONKYNHDHCWJVSD","bundle":"https://pith.science/pith/WLF2S3CUDILYONKYNHDHCWJVSD/bundle.json","state":"https://pith.science/pith/WLF2S3CUDILYONKYNHDHCWJVSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLF2S3CUDILYONKYNHDHCWJVSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WLF2S3CUDILYONKYNHDHCWJVSD","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":"2ebe47aeff9ae60ce9f4ed6f163ff2d0de39229112b7f792111a7791f743899d","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T01:44:09Z","title_canon_sha256":"8f5402266fc440fbc74100b44d5486ebf44c2e836625f2762414ea14bc44e286"},"schema_version":"1.0","source":{"id":"2305.15644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15644","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15644v1","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15644","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"WLF2S3CUDILY","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"pith_short_16","alias_value":"WLF2S3CUDILYONKY","created_at":"2026-07-05T06:13:42Z"},{"alias_kind":"pith_short_8","alias_value":"WLF2S3CU","created_at":"2026-07-05T06:13:42Z"}],"graph_snapshots":[{"event_id":"sha256:823d5286bc7a26cd614e7177f77f4c3ec09a15d8a9f3335b284bd3aaf7a4de3b","target":"graph","created_at":"2026-07-05T06:13:42Z","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/2305.15644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To ensure the out-of-distribution (OOD) generalization performance, traditional domain generalization (DG) methods resort to training on data from multiple sources with different underlying distributions. And the success of those DG methods largely depends on the fact that there are diverse training distributions. However, it usually needs great efforts to obtain enough heterogeneous data due to the high expenses, privacy issues or the scarcity of data. Thus an interesting yet seldom investigated problem arises: how to improve the OOD generalization performance when the perceived heterogeneity","authors_text":"Furui Liu, Han Yu, Jiashuo Liu, Linjun Zhou, Peng Cui, Xingxuan Zhang, Zheyan Shen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T01:44:09Z","title":"Meta Adaptive Task Sampling for Few-Domain Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15644","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":"sha256:48eb686663726d5ad14292c9418a39f78df51977635f2007a7a6395aa7d7c0a2","target":"record","created_at":"2026-07-05T06:13:42Z","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":"2ebe47aeff9ae60ce9f4ed6f163ff2d0de39229112b7f792111a7791f743899d","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T01:44:09Z","title_canon_sha256":"8f5402266fc440fbc74100b44d5486ebf44c2e836625f2762414ea14bc44e286"},"schema_version":"1.0","source":{"id":"2305.15644","kind":"arxiv","version":1}},"canonical_sha256":"b2cba96c541a1787355869c671593590ee847dd83e3066bc6c741a6b6e6d1346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2cba96c541a1787355869c671593590ee847dd83e3066bc6c741a6b6e6d1346","first_computed_at":"2026-07-05T06:13:42.823932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:42.823932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBbNxVMEb6WcPudoLpO6VpbNK4myYHoBJZ9bWAexLjI45Q8YXcu3FmSVnyCUAj31Fw4DycJlTqBIv5gtlbc5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:42.824352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48eb686663726d5ad14292c9418a39f78df51977635f2007a7a6395aa7d7c0a2","sha256:823d5286bc7a26cd614e7177f77f4c3ec09a15d8a9f3335b284bd3aaf7a4de3b"],"state_sha256":"076776a5410f414955cbce85566fcefbd08b19e32032b231c7135a08e6072e67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYc6ZN8bLwW0EKkzaoQjkqa9CS7+krQZ6irEiXQOTl0k8XQ1bPuZ70d4IKpLXep+u86UbCfxMYmADKwiIQMvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:39:38.248385Z","bundle_sha256":"14a7124843be0e32355ef6c4cafc1c527b2cc4130a5ad84575f73cba985aefec"}}