{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QL53QNRZIAOABPVTPO6EFN345R","short_pith_number":"pith:QL53QNRZ","schema_version":"1.0","canonical_sha256":"82fbb83639401c00beb37bbc42b77cec7c1fed794850c7a19ac478d1108a004c","source":{"kind":"arxiv","id":"2207.01395","version":2},"attestation_state":"computed","paper":{"title":"Memory Efficient Patch-based Training for INR-based GANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gayoung Lee, Hyunsu Kim, Namwoo Lee, Sungjoo Yoo, Yunjey Choi","submitted_at":"2022-07-04T13:28:53Z","abstract_excerpt":"Recent studies have shown remarkable progress in GANs based on implicit neural representation (INR) - an MLP that produces an RGB value given its (x, y) coordinate. They represent an image as a continuous version of the underlying 2D signal instead of a 2D array of pixels, which opens new horizons for GAN applications (e.g., zero-shot super-resolution, image outpainting). However, training existing approaches require a heavy computational cost proportional to the image resolution, since they compute an MLP operation for every (x, y) coordinate. To alleviate this issue, we propose a multi-stage"},"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":"2207.01395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-04T13:28:53Z","cross_cats_sorted":[],"title_canon_sha256":"1bf95f98b8114eaa5a68b233844d74a0e57558a7e32306f2fbabc5d09bc3e1cc","abstract_canon_sha256":"7229b17a0f99ed029703df6b518b7b901ed8f3f1bbe9c08cb2902b640ffa645b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:54.360023Z","signature_b64":"2RgPTXbZgLz7fyWJZio6qpZBZOTTnnkAowev0cqBfKqGXkp7xYmkwLUylKA0Pa3a3hwfiQerZ0k7m/D+DclSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82fbb83639401c00beb37bbc42b77cec7c1fed794850c7a19ac478d1108a004c","last_reissued_at":"2026-07-05T04:38:54.359564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:54.359564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Efficient Patch-based Training for INR-based GANs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gayoung Lee, Hyunsu Kim, Namwoo Lee, Sungjoo Yoo, Yunjey Choi","submitted_at":"2022-07-04T13:28:53Z","abstract_excerpt":"Recent studies have shown remarkable progress in GANs based on implicit neural representation (INR) - an MLP that produces an RGB value given its (x, y) coordinate. They represent an image as a continuous version of the underlying 2D signal instead of a 2D array of pixels, which opens new horizons for GAN applications (e.g., zero-shot super-resolution, image outpainting). However, training existing approaches require a heavy computational cost proportional to the image resolution, since they compute an MLP operation for every (x, y) coordinate. To alleviate this issue, we propose a multi-stage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01395","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/2207.01395/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":"2207.01395","created_at":"2026-07-05T04:38:54.359623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01395v2","created_at":"2026-07-05T04:38:54.359623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01395","created_at":"2026-07-05T04:38:54.359623+00:00"},{"alias_kind":"pith_short_12","alias_value":"QL53QNRZIAOA","created_at":"2026-07-05T04:38:54.359623+00:00"},{"alias_kind":"pith_short_16","alias_value":"QL53QNRZIAOABPVT","created_at":"2026-07-05T04:38:54.359623+00:00"},{"alias_kind":"pith_short_8","alias_value":"QL53QNRZ","created_at":"2026-07-05T04:38:54.359623+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/QL53QNRZIAOABPVTPO6EFN345R","json":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R.json","graph_json":"https://pith.science/api/pith-number/QL53QNRZIAOABPVTPO6EFN345R/graph.json","events_json":"https://pith.science/api/pith-number/QL53QNRZIAOABPVTPO6EFN345R/events.json","paper":"https://pith.science/paper/QL53QNRZ"},"agent_actions":{"view_html":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R","download_json":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R.json","view_paper":"https://pith.science/paper/QL53QNRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01395&json=true","fetch_graph":"https://pith.science/api/pith-number/QL53QNRZIAOABPVTPO6EFN345R/graph.json","fetch_events":"https://pith.science/api/pith-number/QL53QNRZIAOABPVTPO6EFN345R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R/action/storage_attestation","attest_author":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R/action/author_attestation","sign_citation":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R/action/citation_signature","submit_replication":"https://pith.science/pith/QL53QNRZIAOABPVTPO6EFN345R/action/replication_record"}},"created_at":"2026-07-05T04:38:54.359623+00:00","updated_at":"2026-07-05T04:38:54.359623+00:00"}