{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VNQMNISO5WJO7ZP34FJBM5255D","short_pith_number":"pith:VNQMNISO","canonical_record":{"source":{"id":"1902.00927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-03T16:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"4386edf7c5592eb7fb9ff6381b4cfa4832f99917154fa51383c247c8053919d3","abstract_canon_sha256":"8a387966ace0c2a2316431bf125f5c351fede4e73b557f69161610562501987c"},"schema_version":"1.0"},"canonical_sha256":"ab60c6a24eed92efe5fbe15216775de8d2b5d4071816d1480706b649a17f3962","source":{"kind":"arxiv","id":"1902.00927","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00927","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00927v2","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00927","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"VNQMNISO5WJO","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VNQMNISO5WJO7ZP3","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VNQMNISO","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VNQMNISO5WJO7ZP34FJBM5255D","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-03T16:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"4386edf7c5592eb7fb9ff6381b4cfa4832f99917154fa51383c247c8053919d3","abstract_canon_sha256":"8a387966ace0c2a2316431bf125f5c351fede4e73b557f69161610562501987c"},"schema_version":"1.0"},"canonical_sha256":"ab60c6a24eed92efe5fbe15216775de8d2b5d4071816d1480706b649a17f3962","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:41.062766Z","signature_b64":"oYBJvrIeEYkXG01vIZWseOnfn1K2UM2OtBvWkdKfdNa28GYYk0EfeKzik+fr/+TSCFCMlX2rYqQab4Ltj4BYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab60c6a24eed92efe5fbe15216775de8d2b5d4071816d1480706b649a17f3962","last_reissued_at":"2026-05-17T23:53:41.062280Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:41.062280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00927","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"woepGcm4VDbiF80nhySQY06scMTwpTosExDjuC1h/1gZEc58DcV2mdkDoBRyi3irXvNcknuEfPEJEXMPhcuaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T23:01:52.475478Z"},"content_sha256":"9b878f5ee0ff63c48853fc2ac11b6c336874467516dfcbf2e56554566748e1b4","schema_version":"1.0","event_id":"sha256:9b878f5ee0ff63c48853fc2ac11b6c336874467516dfcbf2e56554566748e1b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VNQMNISO5WJO7ZP34FJBM5255D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Depthwise Convolution is All You Need for Learning Multiple Visual Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Wang, Rogerio Feris, Tajana Rosing, Yandong Li, Yunhui Guo","submitted_at":"2019-02-03T16:58:19Z","abstract_excerpt":"There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a single model for all domains rather than one model per domain. A model aware of the relationships between different domains can also be trained to work on new domains with less resources. However, to identify the reusable structure in a model is not easy. In this paper, we propose a multi-domain learning architecture based on depthwise separable convolution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00927","kind":"arxiv","version":2},"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":"2026-05-17T23:53:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6eIiyN8hGM0K90NCQE5tP2slw2oaEEzTFy+Ni9rdlN04dTs+hIQ10Ss8yEqFJEaV/MB4kvmDuWsRMpIen3iiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T23:01:52.476216Z"},"content_sha256":"541db77a577e8496a659d450505ddfc9e543fa5359deb33501564ea42d8cf862","schema_version":"1.0","event_id":"sha256:541db77a577e8496a659d450505ddfc9e543fa5359deb33501564ea42d8cf862"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNQMNISO5WJO7ZP34FJBM5255D/bundle.json","state_url":"https://pith.science/pith/VNQMNISO5WJO7ZP34FJBM5255D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNQMNISO5WJO7ZP34FJBM5255D/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":"2026-05-20T23:01:52Z","links":{"resolver":"https://pith.science/pith/VNQMNISO5WJO7ZP34FJBM5255D","bundle":"https://pith.science/pith/VNQMNISO5WJO7ZP34FJBM5255D/bundle.json","state":"https://pith.science/pith/VNQMNISO5WJO7ZP34FJBM5255D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNQMNISO5WJO7ZP34FJBM5255D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VNQMNISO5WJO7ZP34FJBM5255D","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":"8a387966ace0c2a2316431bf125f5c351fede4e73b557f69161610562501987c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-03T16:58:19Z","title_canon_sha256":"4386edf7c5592eb7fb9ff6381b4cfa4832f99917154fa51383c247c8053919d3"},"schema_version":"1.0","source":{"id":"1902.00927","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00927","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00927v2","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00927","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"VNQMNISO5WJO","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VNQMNISO5WJO7ZP3","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VNQMNISO","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:541db77a577e8496a659d450505ddfc9e543fa5359deb33501564ea42d8cf862","target":"graph","created_at":"2026-05-17T23:53:41Z","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"},"paper":{"abstract_excerpt":"There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a single model for all domains rather than one model per domain. A model aware of the relationships between different domains can also be trained to work on new domains with less resources. However, to identify the reusable structure in a model is not easy. In this paper, we propose a multi-domain learning architecture based on depthwise separable convolution","authors_text":"Liqiang Wang, Rogerio Feris, Tajana Rosing, Yandong Li, Yunhui Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-03T16:58:19Z","title":"Depthwise Convolution is All You Need for Learning Multiple Visual Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00927","kind":"arxiv","version":2},"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":"sha256:9b878f5ee0ff63c48853fc2ac11b6c336874467516dfcbf2e56554566748e1b4","target":"record","created_at":"2026-05-17T23:53:41Z","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":"8a387966ace0c2a2316431bf125f5c351fede4e73b557f69161610562501987c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-03T16:58:19Z","title_canon_sha256":"4386edf7c5592eb7fb9ff6381b4cfa4832f99917154fa51383c247c8053919d3"},"schema_version":"1.0","source":{"id":"1902.00927","kind":"arxiv","version":2}},"canonical_sha256":"ab60c6a24eed92efe5fbe15216775de8d2b5d4071816d1480706b649a17f3962","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab60c6a24eed92efe5fbe15216775de8d2b5d4071816d1480706b649a17f3962","first_computed_at":"2026-05-17T23:53:41.062280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:41.062280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYBJvrIeEYkXG01vIZWseOnfn1K2UM2OtBvWkdKfdNa28GYYk0EfeKzik+fr/+TSCFCMlX2rYqQab4Ltj4BYBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:41.062766Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00927","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b878f5ee0ff63c48853fc2ac11b6c336874467516dfcbf2e56554566748e1b4","sha256:541db77a577e8496a659d450505ddfc9e543fa5359deb33501564ea42d8cf862"],"state_sha256":"79cd0c1ed1facf6c3b732a20aeda803fdb04dd60c336b85c830da113b1baee1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSkem/5yhOtG5bcLfLu/jroFl//35CYavrfzDg/ZmURHhybRSQcRl1vFKL//ZlfX99VvtZ1JEu8ddjGbpKPXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T23:01:52.480092Z","bundle_sha256":"9a4a56dc91570a22429f03cfd5960b8ad8171ec36ab66ce24164ef3f99fa35df"}}