{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:M3J7WHEN3M5TESY6Q6K7EG3366","short_pith_number":"pith:M3J7WHEN","canonical_record":{"source":{"id":"1810.12521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T04:31:48Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"44626515793b19e178282c450ffec8415e45d233615fceea22797073cb0daeec","abstract_canon_sha256":"13f4ac88217c04ea71967776965d9f2427ff4b568ceb984fe7eb33c0ccaae4d5"},"schema_version":"1.0"},"canonical_sha256":"66d3fb1c8ddb3b324b1e8795f21b7bf7a45143907f38ae7a9dd4b201bc9db5e4","source":{"kind":"arxiv","id":"1810.12521","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12521","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12521v1","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12521","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"M3J7WHEN3M5T","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M3J7WHEN3M5TESY6","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M3J7WHEN","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:M3J7WHEN3M5TESY6Q6K7EG3366","target":"record","payload":{"canonical_record":{"source":{"id":"1810.12521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T04:31:48Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"44626515793b19e178282c450ffec8415e45d233615fceea22797073cb0daeec","abstract_canon_sha256":"13f4ac88217c04ea71967776965d9f2427ff4b568ceb984fe7eb33c0ccaae4d5"},"schema_version":"1.0"},"canonical_sha256":"66d3fb1c8ddb3b324b1e8795f21b7bf7a45143907f38ae7a9dd4b201bc9db5e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:56.846850Z","signature_b64":"PBoAWibLINed4LA2dSnimG/TEvwj0LVcp2CmN/rslojA40x89jo47IWIhntzOB6PtjTlwYkN7QYujM6uSeIDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66d3fb1c8ddb3b324b1e8795f21b7bf7a45143907f38ae7a9dd4b201bc9db5e4","last_reissued_at":"2026-05-18T00:01:56.846194Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:56.846194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.12521","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":"2026-05-18T00:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4LBL7J/jI6n3ErqqX0QO+nRTSKpbSJdES5so1T5aPfCx3H3jnKjO0FFWuRNhPK5eiSIyvoisjbBhNsLr68yFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:37:37.561371Z"},"content_sha256":"ca83c4d377cc294a727a96556b1bdc2ea00dcd55cb28663e5fb5540c86fcc5c4","schema_version":"1.0","event_id":"sha256:ca83c4d377cc294a727a96556b1bdc2ea00dcd55cb28663e5fb5540c86fcc5c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:M3J7WHEN3M5TESY6Q6K7EG3366","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gated Transfer Network for Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jia Xue, Shawn Newsam, Yi Zhu","submitted_at":"2018-10-30T04:31:48Z","abstract_excerpt":"Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the pre-trained models to the new tasks by fine-tuning. Classic model fine-tuning utilizes the fact that well trained neural networks appear to learn cross domain features. These features are treated equally during transfer learning. In this paper, we explore the impact of feature selection in model fine-tuning by introducing a transfer module, which assigns weights t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12521","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":"2026-05-18T00:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbwPYyZMNfpEMeK67iE0gTrHDPss17sGfU0K0C0Wwtvh2OH08Jeqq1w1jUvy9MpST7UCEyVw/AZu22qLiMTIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:37:37.561721Z"},"content_sha256":"3f5e17f5d538d451299db937b651c0a0a07877d485af264ae8bd4720c33969fd","schema_version":"1.0","event_id":"sha256:3f5e17f5d538d451299db937b651c0a0a07877d485af264ae8bd4720c33969fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3J7WHEN3M5TESY6Q6K7EG3366/bundle.json","state_url":"https://pith.science/pith/M3J7WHEN3M5TESY6Q6K7EG3366/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3J7WHEN3M5TESY6Q6K7EG3366/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":"2026-06-01T08:37:37Z","links":{"resolver":"https://pith.science/pith/M3J7WHEN3M5TESY6Q6K7EG3366","bundle":"https://pith.science/pith/M3J7WHEN3M5TESY6Q6K7EG3366/bundle.json","state":"https://pith.science/pith/M3J7WHEN3M5TESY6Q6K7EG3366/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3J7WHEN3M5TESY6Q6K7EG3366/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:M3J7WHEN3M5TESY6Q6K7EG3366","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":"13f4ac88217c04ea71967776965d9f2427ff4b568ceb984fe7eb33c0ccaae4d5","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T04:31:48Z","title_canon_sha256":"44626515793b19e178282c450ffec8415e45d233615fceea22797073cb0daeec"},"schema_version":"1.0","source":{"id":"1810.12521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12521","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12521v1","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12521","created_at":"2026-05-18T00:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"M3J7WHEN3M5T","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M3J7WHEN3M5TESY6","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M3J7WHEN","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:3f5e17f5d538d451299db937b651c0a0a07877d485af264ae8bd4720c33969fd","target":"graph","created_at":"2026-05-18T00:01:56Z","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":"Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the pre-trained models to the new tasks by fine-tuning. Classic model fine-tuning utilizes the fact that well trained neural networks appear to learn cross domain features. These features are treated equally during transfer learning. In this paper, we explore the impact of feature selection in model fine-tuning by introducing a transfer module, which assigns weights t","authors_text":"Jia Xue, Shawn Newsam, Yi Zhu","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T04:31:48Z","title":"Gated Transfer Network for Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12521","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:ca83c4d377cc294a727a96556b1bdc2ea00dcd55cb28663e5fb5540c86fcc5c4","target":"record","created_at":"2026-05-18T00:01:56Z","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":"13f4ac88217c04ea71967776965d9f2427ff4b568ceb984fe7eb33c0ccaae4d5","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-30T04:31:48Z","title_canon_sha256":"44626515793b19e178282c450ffec8415e45d233615fceea22797073cb0daeec"},"schema_version":"1.0","source":{"id":"1810.12521","kind":"arxiv","version":1}},"canonical_sha256":"66d3fb1c8ddb3b324b1e8795f21b7bf7a45143907f38ae7a9dd4b201bc9db5e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66d3fb1c8ddb3b324b1e8795f21b7bf7a45143907f38ae7a9dd4b201bc9db5e4","first_computed_at":"2026-05-18T00:01:56.846194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:56.846194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PBoAWibLINed4LA2dSnimG/TEvwj0LVcp2CmN/rslojA40x89jo47IWIhntzOB6PtjTlwYkN7QYujM6uSeIDDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:56.846850Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca83c4d377cc294a727a96556b1bdc2ea00dcd55cb28663e5fb5540c86fcc5c4","sha256:3f5e17f5d538d451299db937b651c0a0a07877d485af264ae8bd4720c33969fd"],"state_sha256":"fe7cca52dd06e89693d5763ddce29f6a7c6881c3d77454cdc79b51f1a89685b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQy5+NTk8SRf3n2sD3RI63swULeqvx3sSuSEZ+nqW93SBnj3IQuLXTzgSWCzZBvhfqzm0y4X5xBuVVV5cKGWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T08:37:37.563656Z","bundle_sha256":"d13573cc19a994945dea27b6349496c9978afa0cd601a0c72d1e0b5ae654751b"}}