{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Q3UBEBJJZ364V3QOEK3X35EBIE","short_pith_number":"pith:Q3UBEBJJ","canonical_record":{"source":{"id":"1709.02995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-09T18:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"024a7c95298beaeefd0d822c178163829c6aea1639534ab795d73e5921d18ecd","abstract_canon_sha256":"a931eeb8ba1455f8b9abf0f9daa7be2dff4d0f05eb448ba861b9042b2ce24240"},"schema_version":"1.0"},"canonical_sha256":"86e8120529cefdcaee0e22b77df4814106508279ac8d2d95e0010846ff8564c8","source":{"kind":"arxiv","id":"1709.02995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02995","created_at":"2026-05-18T00:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02995v1","created_at":"2026-05-18T00:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02995","created_at":"2026-05-18T00:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q3UBEBJJZ364","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q3UBEBJJZ364V3QO","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q3UBEBJJ","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Q3UBEBJJZ364V3QOEK3X35EBIE","target":"record","payload":{"canonical_record":{"source":{"id":"1709.02995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-09T18:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"024a7c95298beaeefd0d822c178163829c6aea1639534ab795d73e5921d18ecd","abstract_canon_sha256":"a931eeb8ba1455f8b9abf0f9daa7be2dff4d0f05eb448ba861b9042b2ce24240"},"schema_version":"1.0"},"canonical_sha256":"86e8120529cefdcaee0e22b77df4814106508279ac8d2d95e0010846ff8564c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:39.759773Z","signature_b64":"8RHy6YpJsbGMNfQ2Dq/BZCT2d9GPevlSU4m8lXF1VF2hBfriBPAOP4Kp+sYsw22+vmXmj33KRFh2PSn/SDFtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e8120529cefdcaee0e22b77df4814106508279ac8d2d95e0010846ff8564c8","last_reissued_at":"2026-05-18T00:35:39.759158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:39.759158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.02995","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":"2026-05-18T00:35:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+eXSmVLjTnbZTDEg/04aUYde6ZjX9ghsgB8eYqE74w3JB3QTgjyja0rGT3L1mGyszqXVL/ktp3BCKGwpGtPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:40:44.139052Z"},"content_sha256":"3e2d9b905e8c80facdf1de5d61157d8243daeec06108ddb90b3644f1cf9e13ee","schema_version":"1.0","event_id":"sha256:3e2d9b905e8c80facdf1de5d61157d8243daeec06108ddb90b3644f1cf9e13ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Q3UBEBJJZ364V3QOEK3X35EBIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Transport for Deep Joint Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Saidi, Liming Chen, Ying Lu","submitted_at":"2017-09-09T18:56:05Z","abstract_excerpt":"Training a Deep Neural Network (DNN) from scratch requires a large amount of labeled data. For a classification task where only small amount of training data is available, a common solution is to perform fine-tuning on a DNN which is pre-trained with related source data. This consecutive training process is time consuming and does not consider explicitly the relatedness between different source and target tasks.\n  In this paper, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02995","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":"2026-05-18T00:35:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqDZAs5lUaJd6aHruD1/Z/Yfu5ubaVxzNQNP1BwOKGEqy4cj6Ir1wM5cK1RjvgLgrJdivn3NIWCsmJY2U8waDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:40:44.139423Z"},"content_sha256":"e67392c7df9ea557010d3548dbbfa4eb4a879ad111ebff19a6d3df1b89d7ccc1","schema_version":"1.0","event_id":"sha256:e67392c7df9ea557010d3548dbbfa4eb4a879ad111ebff19a6d3df1b89d7ccc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3UBEBJJZ364V3QOEK3X35EBIE/bundle.json","state_url":"https://pith.science/pith/Q3UBEBJJZ364V3QOEK3X35EBIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3UBEBJJZ364V3QOEK3X35EBIE/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":"2026-05-30T16:40:44Z","links":{"resolver":"https://pith.science/pith/Q3UBEBJJZ364V3QOEK3X35EBIE","bundle":"https://pith.science/pith/Q3UBEBJJZ364V3QOEK3X35EBIE/bundle.json","state":"https://pith.science/pith/Q3UBEBJJZ364V3QOEK3X35EBIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3UBEBJJZ364V3QOEK3X35EBIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Q3UBEBJJZ364V3QOEK3X35EBIE","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":"a931eeb8ba1455f8b9abf0f9daa7be2dff4d0f05eb448ba861b9042b2ce24240","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-09T18:56:05Z","title_canon_sha256":"024a7c95298beaeefd0d822c178163829c6aea1639534ab795d73e5921d18ecd"},"schema_version":"1.0","source":{"id":"1709.02995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02995","created_at":"2026-05-18T00:35:39Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02995v1","created_at":"2026-05-18T00:35:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02995","created_at":"2026-05-18T00:35:39Z"},{"alias_kind":"pith_short_12","alias_value":"Q3UBEBJJZ364","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q3UBEBJJZ364V3QO","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q3UBEBJJ","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:e67392c7df9ea557010d3548dbbfa4eb4a879ad111ebff19a6d3df1b89d7ccc1","target":"graph","created_at":"2026-05-18T00:35:39Z","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":"Training a Deep Neural Network (DNN) from scratch requires a large amount of labeled data. For a classification task where only small amount of training data is available, a common solution is to perform fine-tuning on a DNN which is pre-trained with related source data. This consecutive training process is time consuming and does not consider explicitly the relatedness between different source and target tasks.\n  In this paper, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and","authors_text":"Alexandre Saidi, Liming Chen, Ying Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-09T18:56:05Z","title":"Optimal Transport for Deep Joint Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02995","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":"sha256:3e2d9b905e8c80facdf1de5d61157d8243daeec06108ddb90b3644f1cf9e13ee","target":"record","created_at":"2026-05-18T00:35:39Z","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":"a931eeb8ba1455f8b9abf0f9daa7be2dff4d0f05eb448ba861b9042b2ce24240","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-09T18:56:05Z","title_canon_sha256":"024a7c95298beaeefd0d822c178163829c6aea1639534ab795d73e5921d18ecd"},"schema_version":"1.0","source":{"id":"1709.02995","kind":"arxiv","version":1}},"canonical_sha256":"86e8120529cefdcaee0e22b77df4814106508279ac8d2d95e0010846ff8564c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86e8120529cefdcaee0e22b77df4814106508279ac8d2d95e0010846ff8564c8","first_computed_at":"2026-05-18T00:35:39.759158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:39.759158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8RHy6YpJsbGMNfQ2Dq/BZCT2d9GPevlSU4m8lXF1VF2hBfriBPAOP4Kp+sYsw22+vmXmj33KRFh2PSn/SDFtDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:39.759773Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.02995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e2d9b905e8c80facdf1de5d61157d8243daeec06108ddb90b3644f1cf9e13ee","sha256:e67392c7df9ea557010d3548dbbfa4eb4a879ad111ebff19a6d3df1b89d7ccc1"],"state_sha256":"deb285daf19ff93c3f121371b36361ce80a0a43438b1a87163dbee1a868bdd2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVASvht+QxoRZNATgMZfNA9s5EfX1mcxOUbg1habvNfD9Pxi9C/AGjIwCL8aaVyso+4toBh+ge6J+x0iHgSWDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:40:44.143998Z","bundle_sha256":"a1f47815ea2e3f0fd1e3f0d9ce33b814c0af4d963add07d2ce335020543b6350"}}