{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TEANHXSLZ2ZIMUHTYEA4NII4YJ","short_pith_number":"pith:TEANHXSL","schema_version":"1.0","canonical_sha256":"9900d3de4bceb28650f3c101c6a11cc24fbf6901e962c385716c1fde1b6b7aeb","source":{"kind":"arxiv","id":"2109.09338","version":2},"attestation_state":"computed","paper":{"title":"Learning in Sinusoidal Spaces with Physics-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Chinchun Ooi, Jian Cheng Wong, Yew-Soon Ong","submitted_at":"2021-09-20T07:42:41Z","abstract_excerpt":"A physics-informed neural network (PINN) uses physics-augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamental physics laws. However, it turns out to be difficult to train an accurate PINN model for many problems in practice. In this paper, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs. By analyzing behavior at model initialization, we first show that a PINN of increasing expressiveness induces an initial bias around flat output functions. "},"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":"2109.09338","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T07:42:41Z","cross_cats_sorted":["cs.AI","cs.CE","physics.comp-ph"],"title_canon_sha256":"267f36c07da00e96614a06271d7d3609efdeb9cc3252a106fa4d7349b18732e6","abstract_canon_sha256":"572cae4a368b3cd21359874466c8e6d5966d0a3d100d18c1f4169bbc4f2534e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:27.069663Z","signature_b64":"SfQ+uo2uvx9Q9mPayjtEivUUVIFMZn7NSMSy67D6tf6q8dnY1eCpR+quiIsvlZQ2ID1BjrRmZwAgh2lp3SYPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9900d3de4bceb28650f3c101c6a11cc24fbf6901e962c385716c1fde1b6b7aeb","last_reissued_at":"2026-07-05T05:25:27.069168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:27.069168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in Sinusoidal Spaces with Physics-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Chinchun Ooi, Jian Cheng Wong, Yew-Soon Ong","submitted_at":"2021-09-20T07:42:41Z","abstract_excerpt":"A physics-informed neural network (PINN) uses physics-augmented loss functions, e.g., incorporating the residual term from governing partial differential equations (PDEs), to ensure its output is consistent with fundamental physics laws. However, it turns out to be difficult to train an accurate PINN model for many problems in practice. In this paper, we present a novel perspective of the merits of learning in sinusoidal spaces with PINNs. By analyzing behavior at model initialization, we first show that a PINN of increasing expressiveness induces an initial bias around flat output functions. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09338","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.09338/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":"2109.09338","created_at":"2026-07-05T05:25:27.069225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09338v2","created_at":"2026-07-05T05:25:27.069225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09338","created_at":"2026-07-05T05:25:27.069225+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEANHXSLZ2ZI","created_at":"2026-07-05T05:25:27.069225+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEANHXSLZ2ZIMUHT","created_at":"2026-07-05T05:25:27.069225+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEANHXSL","created_at":"2026-07-05T05:25:27.069225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28604","citing_title":"Cosmo-SPINN: Fuzzy Dark Matter Simulations with Physics-Informed Generative Networks","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ","json":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ.json","graph_json":"https://pith.science/api/pith-number/TEANHXSLZ2ZIMUHTYEA4NII4YJ/graph.json","events_json":"https://pith.science/api/pith-number/TEANHXSLZ2ZIMUHTYEA4NII4YJ/events.json","paper":"https://pith.science/paper/TEANHXSL"},"agent_actions":{"view_html":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ","download_json":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ.json","view_paper":"https://pith.science/paper/TEANHXSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09338&json=true","fetch_graph":"https://pith.science/api/pith-number/TEANHXSLZ2ZIMUHTYEA4NII4YJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TEANHXSLZ2ZIMUHTYEA4NII4YJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ/action/storage_attestation","attest_author":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ/action/author_attestation","sign_citation":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ/action/citation_signature","submit_replication":"https://pith.science/pith/TEANHXSLZ2ZIMUHTYEA4NII4YJ/action/replication_record"}},"created_at":"2026-07-05T05:25:27.069225+00:00","updated_at":"2026-07-05T05:25:27.069225+00:00"}