{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CUYMXIMT2IJTWBEKQHECNDP6V2","short_pith_number":"pith:CUYMXIMT","schema_version":"1.0","canonical_sha256":"1530cba193d2133b048a81c8268dfeaea99a09a64955ab79b088dbc9cd556aec","source":{"kind":"arxiv","id":"1912.12355","version":1},"attestation_state":"computed","paper":{"title":"SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Ali Heydari, Asif Mehmood, Craig A. Thompson","submitted_at":"2019-12-27T22:23:16Z","abstract_excerpt":"Adaptive loss function formulation is an active area of research and has gained a great deal of popularity in recent years, following the success of deep learning. However, existing frameworks of adaptive loss functions often suffer from slow convergence and poor choice of weights for the loss components. Traditionally, the elements of a multi-part loss function are weighted equally or their weights are determined through heuristic approaches that yield near-optimal (or sub-optimal) results. To address this problem, we propose a family of methods, called SoftAdapt, that dynamically change func"},"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":"1912.12355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-27T22:23:16Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"cc51134206090bcd6849a614ff791250a44f11ddbfb8285325c0ff99d8bb4ea3","abstract_canon_sha256":"1584716e1484edfb35be3038893dc2bd3e5cc1fd5a0f64a52c1527aae06500f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:58.777861Z","signature_b64":"by2NE0ZUZ/vbzudIXt6j/KDNFXRjWZNWeCPuMra/ixbkGEvqwAzTHyynwkDQ6zkIojJ2xdKvo/NNJD8XT0Z0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1530cba193d2133b048a81c8268dfeaea99a09a64955ab79b088dbc9cd556aec","last_reissued_at":"2026-07-05T00:28:58.777400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:58.777400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Ali Heydari, Asif Mehmood, Craig A. Thompson","submitted_at":"2019-12-27T22:23:16Z","abstract_excerpt":"Adaptive loss function formulation is an active area of research and has gained a great deal of popularity in recent years, following the success of deep learning. However, existing frameworks of adaptive loss functions often suffer from slow convergence and poor choice of weights for the loss components. Traditionally, the elements of a multi-part loss function are weighted equally or their weights are determined through heuristic approaches that yield near-optimal (or sub-optimal) results. To address this problem, we propose a family of methods, called SoftAdapt, that dynamically change func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.12355","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/1912.12355/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":"1912.12355","created_at":"2026-07-05T00:28:58.777468+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.12355v1","created_at":"2026-07-05T00:28:58.777468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.12355","created_at":"2026-07-05T00:28:58.777468+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUYMXIMT2IJT","created_at":"2026-07-05T00:28:58.777468+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUYMXIMT2IJTWBEK","created_at":"2026-07-05T00:28:58.777468+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUYMXIMT","created_at":"2026-07-05T00:28:58.777468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26013","citing_title":"G-PINNs: Gaussian-based spatially weighted formulation for PINNs: 1D low-viscous Burgers","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21945","citing_title":"Beyond Data-Driven: How Physics-Informed Neural Networks are Reshaping Multi-Physics Design and Discovery","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19562","citing_title":"Advances in Scientific Machine Learning for Coupled Fluid Flow and Transport","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07982","citing_title":"Overcoming the Limits of Finite Difference Method; Physics-Informed Neural Network for Noisy High-Dimensional Heat Diffusion","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23999","citing_title":"Auto-Adaptive PINNs with Applications to Phase Transitions","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10136","citing_title":"Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10047","citing_title":"Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00863","citing_title":"Physics-informed neural networks for form-finding of unilateral membrane structures","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2","json":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2.json","graph_json":"https://pith.science/api/pith-number/CUYMXIMT2IJTWBEKQHECNDP6V2/graph.json","events_json":"https://pith.science/api/pith-number/CUYMXIMT2IJTWBEKQHECNDP6V2/events.json","paper":"https://pith.science/paper/CUYMXIMT"},"agent_actions":{"view_html":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2","download_json":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2.json","view_paper":"https://pith.science/paper/CUYMXIMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.12355&json=true","fetch_graph":"https://pith.science/api/pith-number/CUYMXIMT2IJTWBEKQHECNDP6V2/graph.json","fetch_events":"https://pith.science/api/pith-number/CUYMXIMT2IJTWBEKQHECNDP6V2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2/action/storage_attestation","attest_author":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2/action/author_attestation","sign_citation":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2/action/citation_signature","submit_replication":"https://pith.science/pith/CUYMXIMT2IJTWBEKQHECNDP6V2/action/replication_record"}},"created_at":"2026-07-05T00:28:58.777468+00:00","updated_at":"2026-07-05T00:28:58.777468+00:00"}