{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5KM2J4QMVNFUT3XH5SG5GG5RZK","short_pith_number":"pith:5KM2J4QM","canonical_record":{"source":{"id":"1904.04061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-08T13:44:22Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6ec736f94c8d00f6b2cc43f148256c56becd3c54a28ce860bb87df3e98b138a0","abstract_canon_sha256":"e7e9003346dbdc30ca7c227fea81d3b9fce74f959dafe8d30511d80fb946a181"},"schema_version":"1.0"},"canonical_sha256":"ea99a4f20cab4b49eee7ec8dd31bb1caa82803d524e349c0816cf855127cf772","source":{"kind":"arxiv","id":"1904.04061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04061","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04061v1","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04061","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"5KM2J4QMVNFU","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5KM2J4QMVNFUT3XH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5KM2J4QM","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5KM2J4QMVNFUT3XH5SG5GG5RZK","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-08T13:44:22Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6ec736f94c8d00f6b2cc43f148256c56becd3c54a28ce860bb87df3e98b138a0","abstract_canon_sha256":"e7e9003346dbdc30ca7c227fea81d3b9fce74f959dafe8d30511d80fb946a181"},"schema_version":"1.0"},"canonical_sha256":"ea99a4f20cab4b49eee7ec8dd31bb1caa82803d524e349c0816cf855127cf772","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:07.192164Z","signature_b64":"3wojG4RjhENW8Fqa1wEKmZyaWITjXGCH4tQolroJ4J9GuT/IJuGdfOaVK03xITTxH7toeMzG2BUFgDblkrCCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea99a4f20cab4b49eee7ec8dd31bb1caa82803d524e349c0816cf855127cf772","last_reissued_at":"2026-05-17T23:49:07.191422Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:07.191422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04061","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":"2026-05-17T23:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ifQu1IcivN+SOhWyvfdeqFb2VlC+fzmoHcv5ub+lSgz5Yfpz0BVwWq9xeiYAR3b5zWNQH/9FbyjtfsqgMaudBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:19:36.162659Z"},"content_sha256":"cc9c7a7955dd5ee1406f971d069ee8f89d6e3c49db1b828f222cbe538533b882","schema_version":"1.0","event_id":"sha256:cc9c7a7955dd5ee1406f971d069ee8f89d6e3c49db1b828f222cbe538533b882"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5KM2J4QMVNFUT3XH5SG5GG5RZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dacheng Tao, Tongliang Liu, Yonggang Wen, Yong Luo","submitted_at":"2019-04-08T13:44:22Z","abstract_excerpt":"The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, we examine the problem of transfer distance metric learning (DML), which usually aims to mitigate the label information deficiency issue in the target DML. Most of the current Transfer DML (TDML) methods are not applicable to the scenario where data are drawn from heterogeneous domains. Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04061","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":""},"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":"2026-05-17T23:49:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZeDjMpnyPJp7vxvy3Xpt/uHhEJN6VILjqPfLTRaHKDsvDOS9QE4MyC7T8hpcxfwK3GZdBHIrsWLLCzwlwvHqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:19:36.163011Z"},"content_sha256":"276946720d4b09869f1c98cca6a5fd02833faf881cdffff194331100e826d376","schema_version":"1.0","event_id":"sha256:276946720d4b09869f1c98cca6a5fd02833faf881cdffff194331100e826d376"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK/bundle.json","state_url":"https://pith.science/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK/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":"2026-05-28T19:19:36Z","links":{"resolver":"https://pith.science/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK","bundle":"https://pith.science/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK/bundle.json","state":"https://pith.science/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5KM2J4QMVNFUT3XH5SG5GG5RZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5KM2J4QMVNFUT3XH5SG5GG5RZK","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":"e7e9003346dbdc30ca7c227fea81d3b9fce74f959dafe8d30511d80fb946a181","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-08T13:44:22Z","title_canon_sha256":"6ec736f94c8d00f6b2cc43f148256c56becd3c54a28ce860bb87df3e98b138a0"},"schema_version":"1.0","source":{"id":"1904.04061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04061","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04061v1","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04061","created_at":"2026-05-17T23:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"5KM2J4QMVNFU","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5KM2J4QMVNFUT3XH","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5KM2J4QM","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:276946720d4b09869f1c98cca6a5fd02833faf881cdffff194331100e826d376","target":"graph","created_at":"2026-05-17T23:49:07Z","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"},"paper":{"abstract_excerpt":"The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, we examine the problem of transfer distance metric learning (DML), which usually aims to mitigate the label information deficiency issue in the target DML. Most of the current Transfer DML (TDML) methods are not applicable to the scenario where data are drawn from heterogeneous domains. Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples o","authors_text":"Dacheng Tao, Tongliang Liu, Yonggang Wen, Yong Luo","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-08T13:44:22Z","title":"Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04061","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:cc9c7a7955dd5ee1406f971d069ee8f89d6e3c49db1b828f222cbe538533b882","target":"record","created_at":"2026-05-17T23:49:07Z","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":"e7e9003346dbdc30ca7c227fea81d3b9fce74f959dafe8d30511d80fb946a181","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-04-08T13:44:22Z","title_canon_sha256":"6ec736f94c8d00f6b2cc43f148256c56becd3c54a28ce860bb87df3e98b138a0"},"schema_version":"1.0","source":{"id":"1904.04061","kind":"arxiv","version":1}},"canonical_sha256":"ea99a4f20cab4b49eee7ec8dd31bb1caa82803d524e349c0816cf855127cf772","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea99a4f20cab4b49eee7ec8dd31bb1caa82803d524e349c0816cf855127cf772","first_computed_at":"2026-05-17T23:49:07.191422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:07.191422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wojG4RjhENW8Fqa1wEKmZyaWITjXGCH4tQolroJ4J9GuT/IJuGdfOaVK03xITTxH7toeMzG2BUFgDblkrCCDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:07.192164Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc9c7a7955dd5ee1406f971d069ee8f89d6e3c49db1b828f222cbe538533b882","sha256:276946720d4b09869f1c98cca6a5fd02833faf881cdffff194331100e826d376"],"state_sha256":"eb7726130ef02d831d2d16ca707000f4ad85c3e01822f87482a912ecb4eb8bd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oa6BU/d1JYsP4okQkjTTBEv53ogLKgCxGXI+h2BBkSQods4aG+rBd+gEdL5PWPz6bZIu70Ex7HkkG0scqsGHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T19:19:36.165100Z","bundle_sha256":"23db10b3ea6ed0798fd9a8803c585a41be205c21b6339eb932f83e26f86d9360"}}