{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TNSPCDURIDVSFCETX5DPYG43DN","short_pith_number":"pith:TNSPCDUR","schema_version":"1.0","canonical_sha256":"9b64f10e9140eb228893bf46fc1b9b1b7673412bb493a95d1893cb26e9d0372d","source":{"kind":"arxiv","id":"2503.15156","version":1},"attestation_state":"computed","paper":{"title":"ARC: Anchored Representation Clouds for High-Resolution INR Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Gielisse, Jan van Gemert, Joost Luijmes, Roman Knyazhitskiy","submitted_at":"2025-03-19T12:24:29Z","abstract_excerpt":"Implicit neural representations (INRs) encode signals in neural network weights as a memory-efficient representation, decoupling sampling resolution from the associated resource costs. Current INR image classification methods are demonstrated on low-resolution data and are sensitive to image-space transformations. We attribute these issues to the global, fully-connected MLP neural network architecture encoding of current INRs, which lack mechanisms for local representation: MLPs are sensitive to absolute image location and struggle with high-frequency details. We propose ARC: Anchored Represen"},"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":"2503.15156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T12:24:29Z","cross_cats_sorted":[],"title_canon_sha256":"4fda88af406922bb1c978f780859d7324d0d00ef47045069c457584e4eaedab6","abstract_canon_sha256":"77c5b52511c4d7adbcbd74d325556bf0d433b693b9a0618651423cfb2191e822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:47.258796Z","signature_b64":"ySNF8Hsx64AJ8HB6+QO0w1B99/V/p/6oydzm/yKT58IvzrBdVuUzt8pKOjQ2rhD6SGO50nh11pnB3YXM4k0NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b64f10e9140eb228893bf46fc1b9b1b7673412bb493a95d1893cb26e9d0372d","last_reissued_at":"2026-07-05T10:34:47.258153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:47.258153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARC: Anchored Representation Clouds for High-Resolution INR Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Gielisse, Jan van Gemert, Joost Luijmes, Roman Knyazhitskiy","submitted_at":"2025-03-19T12:24:29Z","abstract_excerpt":"Implicit neural representations (INRs) encode signals in neural network weights as a memory-efficient representation, decoupling sampling resolution from the associated resource costs. Current INR image classification methods are demonstrated on low-resolution data and are sensitive to image-space transformations. We attribute these issues to the global, fully-connected MLP neural network architecture encoding of current INRs, which lack mechanisms for local representation: MLPs are sensitive to absolute image location and struggle with high-frequency details. We propose ARC: Anchored Represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15156","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/2503.15156/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":"2503.15156","created_at":"2026-07-05T10:34:47.258239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15156v1","created_at":"2026-07-05T10:34:47.258239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15156","created_at":"2026-07-05T10:34:47.258239+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNSPCDURIDVS","created_at":"2026-07-05T10:34:47.258239+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNSPCDURIDVSFCET","created_at":"2026-07-05T10:34:47.258239+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNSPCDUR","created_at":"2026-07-05T10:34:47.258239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16035","citing_title":"Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN","json":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN.json","graph_json":"https://pith.science/api/pith-number/TNSPCDURIDVSFCETX5DPYG43DN/graph.json","events_json":"https://pith.science/api/pith-number/TNSPCDURIDVSFCETX5DPYG43DN/events.json","paper":"https://pith.science/paper/TNSPCDUR"},"agent_actions":{"view_html":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN","download_json":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN.json","view_paper":"https://pith.science/paper/TNSPCDUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15156&json=true","fetch_graph":"https://pith.science/api/pith-number/TNSPCDURIDVSFCETX5DPYG43DN/graph.json","fetch_events":"https://pith.science/api/pith-number/TNSPCDURIDVSFCETX5DPYG43DN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN/action/storage_attestation","attest_author":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN/action/author_attestation","sign_citation":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN/action/citation_signature","submit_replication":"https://pith.science/pith/TNSPCDURIDVSFCETX5DPYG43DN/action/replication_record"}},"created_at":"2026-07-05T10:34:47.258239+00:00","updated_at":"2026-07-05T10:34:47.258239+00:00"}