{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H3HKQOFXWY5GANSGDAA3FIFJSG","short_pith_number":"pith:H3HKQOFX","canonical_record":{"source":{"id":"2605.20545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-19T22:39:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31eefc05481df3847765fc529f44610121680074685a883c7038d25da04cdc62","abstract_canon_sha256":"f431c7ca3b8ec0866ef4fffde729897a4e70087b0613c1742cdeac596bbce818"},"schema_version":"1.0"},"canonical_sha256":"3ecea838b7b63a6036461801b2a0a991a7000af2c7e15597405c0e6029fd30ee","source":{"kind":"arxiv","id":"2605.20545","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20545","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20545v1","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20545","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"H3HKQOFXWY5G","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"H3HKQOFXWY5GANSG","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"H3HKQOFX","created_at":"2026-05-21T01:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H3HKQOFXWY5GANSGDAA3FIFJSG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-19T22:39:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"31eefc05481df3847765fc529f44610121680074685a883c7038d25da04cdc62","abstract_canon_sha256":"f431c7ca3b8ec0866ef4fffde729897a4e70087b0613c1742cdeac596bbce818"},"schema_version":"1.0"},"canonical_sha256":"3ecea838b7b63a6036461801b2a0a991a7000af2c7e15597405c0e6029fd30ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:41.889380Z","signature_b64":"FaUgbFTSwSkLST3dMweuAjbwcg9kvfiHHA7YUyIb5IpYe+OhJchmITXvKoGKEOP71ftRsXrcO5P5b4nAzXSvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ecea838b7b63a6036461801b2a0a991a7000af2c7e15597405c0e6029fd30ee","last_reissued_at":"2026-05-21T01:04:41.888734Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:41.888734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20545","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":"2026-05-21T01:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CVx92KGk8jvO0HopfukR8dFTBuWZ6F5rNc4t6l3axbDx4KVzsQ4/TxT8uodPlHq2+gDo6xSuDYobxF4MexBUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T05:27:24.546135Z"},"content_sha256":"c98ac9a9429f5b882ec109e24f35c1c59658309b9cb92da4d09abbc98b5cba7b","schema_version":"1.0","event_id":"sha256:c98ac9a9429f5b882ec109e24f35c1c59658309b9cb92da4d09abbc98b5cba7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H3HKQOFXWY5GANSGDAA3FIFJSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Complexity of Transfer Learning: An Optimal Transport Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guan Wang, Haoyang Cao, Wenpin Tang, Xin Guo","submitted_at":"2026-05-19T22:39:03Z","abstract_excerpt":"Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI. The essence of transfer learning is to leverage knowledge from resolved source tasks for a new target task, especially when the sample size $m$ of the training data for the latter is low. In this work, we rigorously analyze the potential benefit of transfer learning in terms of sample efficiency. Specifically, taking an optimal transport viewpoint of transfer learning, we find that when the data dimension $d$ is higher than $3$, the sample compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20545","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/2605.20545/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":"2026-05-21T01:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xmMTIuC9s4QxQBf3Pzz2I/OAfULPRz7XIo9YmonNr3X3FkZ0a2vXmKN/MmCIvC2VlWVdU0LidocZ32c0wdRZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T05:27:24.546558Z"},"content_sha256":"0452c3a7a49fde26550f6d0614f11dbe8b845b00605e765613541396d4937b3e","schema_version":"1.0","event_id":"sha256:0452c3a7a49fde26550f6d0614f11dbe8b845b00605e765613541396d4937b3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3HKQOFXWY5GANSGDAA3FIFJSG/bundle.json","state_url":"https://pith.science/pith/H3HKQOFXWY5GANSGDAA3FIFJSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3HKQOFXWY5GANSGDAA3FIFJSG/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":"2026-05-25T05:27:24Z","links":{"resolver":"https://pith.science/pith/H3HKQOFXWY5GANSGDAA3FIFJSG","bundle":"https://pith.science/pith/H3HKQOFXWY5GANSGDAA3FIFJSG/bundle.json","state":"https://pith.science/pith/H3HKQOFXWY5GANSGDAA3FIFJSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3HKQOFXWY5GANSGDAA3FIFJSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H3HKQOFXWY5GANSGDAA3FIFJSG","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":"f431c7ca3b8ec0866ef4fffde729897a4e70087b0613c1742cdeac596bbce818","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-19T22:39:03Z","title_canon_sha256":"31eefc05481df3847765fc529f44610121680074685a883c7038d25da04cdc62"},"schema_version":"1.0","source":{"id":"2605.20545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20545","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20545v1","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20545","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"H3HKQOFXWY5G","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"H3HKQOFXWY5GANSG","created_at":"2026-05-21T01:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"H3HKQOFX","created_at":"2026-05-21T01:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:0452c3a7a49fde26550f6d0614f11dbe8b845b00605e765613541396d4937b3e","target":"graph","created_at":"2026-05-21T01:04:41Z","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/2605.20545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI. The essence of transfer learning is to leverage knowledge from resolved source tasks for a new target task, especially when the sample size $m$ of the training data for the latter is low. In this work, we rigorously analyze the potential benefit of transfer learning in terms of sample efficiency. Specifically, taking an optimal transport viewpoint of transfer learning, we find that when the data dimension $d$ is higher than $3$, the sample compl","authors_text":"Guan Wang, Haoyang Cao, Wenpin Tang, Xin Guo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-19T22:39:03Z","title":"Sample Complexity of Transfer Learning: An Optimal Transport Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20545","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:c98ac9a9429f5b882ec109e24f35c1c59658309b9cb92da4d09abbc98b5cba7b","target":"record","created_at":"2026-05-21T01:04:41Z","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":"f431c7ca3b8ec0866ef4fffde729897a4e70087b0613c1742cdeac596bbce818","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-19T22:39:03Z","title_canon_sha256":"31eefc05481df3847765fc529f44610121680074685a883c7038d25da04cdc62"},"schema_version":"1.0","source":{"id":"2605.20545","kind":"arxiv","version":1}},"canonical_sha256":"3ecea838b7b63a6036461801b2a0a991a7000af2c7e15597405c0e6029fd30ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ecea838b7b63a6036461801b2a0a991a7000af2c7e15597405c0e6029fd30ee","first_computed_at":"2026-05-21T01:04:41.888734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:41.888734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FaUgbFTSwSkLST3dMweuAjbwcg9kvfiHHA7YUyIb5IpYe+OhJchmITXvKoGKEOP71ftRsXrcO5P5b4nAzXSvCA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:41.889380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c98ac9a9429f5b882ec109e24f35c1c59658309b9cb92da4d09abbc98b5cba7b","sha256:0452c3a7a49fde26550f6d0614f11dbe8b845b00605e765613541396d4937b3e"],"state_sha256":"370350a28c911ce51645b109f2f3f8ad8d1b11d8a218ddaa55e3c9d8041d0d68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gt3oqxpgRtjyVmKYet4Lk+Oft0pePXPfNl00pMpUHvtD00iHN1WbIqQRw0c/za5CImus92eg1HlIIQQ7rpECAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T05:27:24.549768Z","bundle_sha256":"6a611ae65fa59a0b0c52bdb03c6b4e0162681325bfd30f1a86edecf7bdcad65f"}}