{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IL6FNN4MSLMJOPNPKX3EQLUH5I","short_pith_number":"pith:IL6FNN4M","schema_version":"1.0","canonical_sha256":"42fc56b78c92d8973daf55f6482e87ea2d67b33cb6b0f5e1c3943bfda8c056ab","source":{"kind":"arxiv","id":"2403.14356","version":1},"attestation_state":"computed","paper":{"title":"DomainLab: A modular Python package for domain generalization in deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Alexej Gossmann, Armin Gruber, Carla Feistner, Carsten Marr, Florian Buettner, George Schwarz, Lisa Beer, Nutan Chen, Patrick Rockenschaub, Rahul Babu Shrestha, Rao Muhammad Umer, Sayedali Shetab Boushehri, Xudong Sun","submitted_at":"2024-03-21T12:35:46Z","abstract_excerpt":"Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant regularization loss terms during training. However, there is a lack of modular software that allows users to combine the advantages of different methods with minimal effort for reproducibility. DomainLab is a modular Python package for training user specified neural networks with composable regularization loss terms. Its decoupled design allows the separation of n"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.14356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T12:35:46Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"b4296e0ab78f67bddfeb8c078db93343a6b3a5905353147ef27f5ded45fc6418","abstract_canon_sha256":"0b2aa6db8383988d6ccd670e5e84c889b6c2b9e7e567bdf81ed8fb4c9160a799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:07.591204Z","signature_b64":"ZL3SwJP9LgN2Sg2RRuPNSwrDWzXEe9kQxmhaT14ayUOEh3axicps2E0xVBDrqvcuz9TsK6WQL4Jvrtu9bEjhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42fc56b78c92d8973daf55f6482e87ea2d67b33cb6b0f5e1c3943bfda8c056ab","last_reissued_at":"2026-07-05T07:59:07.590653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:07.590653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DomainLab: A modular Python package for domain generalization in deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Alexej Gossmann, Armin Gruber, Carla Feistner, Carsten Marr, Florian Buettner, George Schwarz, Lisa Beer, Nutan Chen, Patrick Rockenschaub, Rahul Babu Shrestha, Rao Muhammad Umer, Sayedali Shetab Boushehri, Xudong Sun","submitted_at":"2024-03-21T12:35:46Z","abstract_excerpt":"Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant regularization loss terms during training. However, there is a lack of modular software that allows users to combine the advantages of different methods with minimal effort for reproducibility. DomainLab is a modular Python package for training user specified neural networks with composable regularization loss terms. Its decoupled design allows the separation of n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14356","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/2403.14356/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.14356","created_at":"2026-07-05T07:59:07.590740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14356v1","created_at":"2026-07-05T07:59:07.590740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14356","created_at":"2026-07-05T07:59:07.590740+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL6FNN4MSLMJ","created_at":"2026-07-05T07:59:07.590740+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL6FNN4MSLMJOPNP","created_at":"2026-07-05T07:59:07.590740+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL6FNN4M","created_at":"2026-07-05T07:59:07.590740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I","json":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I.json","graph_json":"https://pith.science/api/pith-number/IL6FNN4MSLMJOPNPKX3EQLUH5I/graph.json","events_json":"https://pith.science/api/pith-number/IL6FNN4MSLMJOPNPKX3EQLUH5I/events.json","paper":"https://pith.science/paper/IL6FNN4M"},"agent_actions":{"view_html":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I","download_json":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I.json","view_paper":"https://pith.science/paper/IL6FNN4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14356&json=true","fetch_graph":"https://pith.science/api/pith-number/IL6FNN4MSLMJOPNPKX3EQLUH5I/graph.json","fetch_events":"https://pith.science/api/pith-number/IL6FNN4MSLMJOPNPKX3EQLUH5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I/action/storage_attestation","attest_author":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I/action/author_attestation","sign_citation":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I/action/citation_signature","submit_replication":"https://pith.science/pith/IL6FNN4MSLMJOPNPKX3EQLUH5I/action/replication_record"}},"created_at":"2026-07-05T07:59:07.590740+00:00","updated_at":"2026-07-05T07:59:07.590740+00:00"}