{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R5ESN5GXWVB6NPF3OZYKN4ECVK","short_pith_number":"pith:R5ESN5GX","schema_version":"1.0","canonical_sha256":"8f4926f4d7b543e6bcbb7670a6f082aab4a1c1a0dbcb983d8b43b0d637c97fcc","source":{"kind":"arxiv","id":"2301.05816","version":4},"attestation_state":"computed","paper":{"title":"Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John Lazzari, Xiuwen Liu","submitted_at":"2023-01-14T04:21:25Z","abstract_excerpt":"Spectral bias is an important observation of neural network training, stating that the network will learn a low frequency representation of the target function before converging to higher frequency components. This property is interesting due to its link to good generalization in over-parameterized networks. However, in low dimensional settings, a severe spectral bias occurs that obstructs convergence to high frequency components entirely. In order to overcome this limitation, one can encode the inputs using a high frequency sinusoidal encoding. Previous works attempted to explain this phenome"},"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":"2301.05816","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-14T04:21:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88bd47a330c550e034500cef78a708faba5d99b5d55324c2d5c81dc07c56b30c","abstract_canon_sha256":"c7ec76e787038b1428f8c1af4d8cac1988afd3efba9d56b1cab460d2576c5f7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:57.223482Z","signature_b64":"dwI+rOabqro2C1copQCnADp0GZ9svAUAjD5EaiLmPDk5duvmz5HQtSgx1vMFG4vPgjV2Drjyomz2gjEqpP+iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f4926f4d7b543e6bcbb7670a6f082aab4a1c1a0dbcb983d8b43b0d637c97fcc","last_reissued_at":"2026-07-05T06:06:57.223064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:57.223064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"John Lazzari, Xiuwen Liu","submitted_at":"2023-01-14T04:21:25Z","abstract_excerpt":"Spectral bias is an important observation of neural network training, stating that the network will learn a low frequency representation of the target function before converging to higher frequency components. This property is interesting due to its link to good generalization in over-parameterized networks. However, in low dimensional settings, a severe spectral bias occurs that obstructs convergence to high frequency components entirely. In order to overcome this limitation, one can encode the inputs using a high frequency sinusoidal encoding. Previous works attempted to explain this phenome"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05816","kind":"arxiv","version":4},"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/2301.05816/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":"2301.05816","created_at":"2026-07-05T06:06:57.223120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.05816v4","created_at":"2026-07-05T06:06:57.223120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05816","created_at":"2026-07-05T06:06:57.223120+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5ESN5GXWVB6","created_at":"2026-07-05T06:06:57.223120+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5ESN5GXWVB6NPF3","created_at":"2026-07-05T06:06:57.223120+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5ESN5GX","created_at":"2026-07-05T06:06:57.223120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20326","citing_title":"Quantum-classical physics-informed Kolmogorov-Arnold networks for PDEs","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK","json":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK.json","graph_json":"https://pith.science/api/pith-number/R5ESN5GXWVB6NPF3OZYKN4ECVK/graph.json","events_json":"https://pith.science/api/pith-number/R5ESN5GXWVB6NPF3OZYKN4ECVK/events.json","paper":"https://pith.science/paper/R5ESN5GX"},"agent_actions":{"view_html":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK","download_json":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK.json","view_paper":"https://pith.science/paper/R5ESN5GX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.05816&json=true","fetch_graph":"https://pith.science/api/pith-number/R5ESN5GXWVB6NPF3OZYKN4ECVK/graph.json","fetch_events":"https://pith.science/api/pith-number/R5ESN5GXWVB6NPF3OZYKN4ECVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK/action/storage_attestation","attest_author":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK/action/author_attestation","sign_citation":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK/action/citation_signature","submit_replication":"https://pith.science/pith/R5ESN5GXWVB6NPF3OZYKN4ECVK/action/replication_record"}},"created_at":"2026-07-05T06:06:57.223120+00:00","updated_at":"2026-07-05T06:06:57.223120+00:00"}