{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I5Y3325GYAX5646X4V4EHIM545","short_pith_number":"pith:I5Y3325G","schema_version":"1.0","canonical_sha256":"4771bdeba6c02fdf73d7e57843a19de776a88bb5c045cba5a313600c59232b7d","source":{"kind":"arxiv","id":"2503.15420","version":1},"attestation_state":"computed","paper":{"title":"LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amirhossein Kazerouni, Babak Taati, Michael Brudno, Soroush Mehraban","submitted_at":"2025-03-19T17:00:58Z","abstract_excerpt":"Implicit Neural Representations (INRs) are proving to be a powerful paradigm in unifying task modeling across diverse data domains, offering key advantages such as memory efficiency and resolution independence. Conventional deep learning models are typically modality-dependent, often requiring custom architectures and objectives for different types of signals. However, existing INR frameworks frequently rely on global latent vectors or exhibit computational inefficiencies that limit their broader applicability. We introduce LIFT, a novel, high-performance framework that addresses these challen"},"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":"2503.15420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T17:00:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a8351e7bdf98a51d746fe9fc8f438f446dfc89ae9c9aae1c415f01e005430ca5","abstract_canon_sha256":"631139f11387fd9762242208519210ac2d60a40a8f206ceb58cb04d2bc86de82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:25.952405Z","signature_b64":"GykujTp/dtNE2j2BARO6AR8I1t+V7KcRFEuOfcFi8CLyHLPrWznIBQWTvwU2KbyDp4Dzs1Qg9fRN9bNkvwbVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4771bdeba6c02fdf73d7e57843a19de776a88bb5c045cba5a313600c59232b7d","last_reissued_at":"2026-07-05T10:35:25.951810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:25.951810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amirhossein Kazerouni, Babak Taati, Michael Brudno, Soroush Mehraban","submitted_at":"2025-03-19T17:00:58Z","abstract_excerpt":"Implicit Neural Representations (INRs) are proving to be a powerful paradigm in unifying task modeling across diverse data domains, offering key advantages such as memory efficiency and resolution independence. Conventional deep learning models are typically modality-dependent, often requiring custom architectures and objectives for different types of signals. However, existing INR frameworks frequently rely on global latent vectors or exhibit computational inefficiencies that limit their broader applicability. We introduce LIFT, a novel, high-performance framework that addresses these challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15420","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/2503.15420/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":"2503.15420","created_at":"2026-07-05T10:35:25.951879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15420v1","created_at":"2026-07-05T10:35:25.951879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15420","created_at":"2026-07-05T10:35:25.951879+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5Y3325GYAX5","created_at":"2026-07-05T10:35:25.951879+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5Y3325GYAX5646X","created_at":"2026-07-05T10:35:25.951879+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5Y3325G","created_at":"2026-07-05T10:35:25.951879+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":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545","json":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545.json","graph_json":"https://pith.science/api/pith-number/I5Y3325GYAX5646X4V4EHIM545/graph.json","events_json":"https://pith.science/api/pith-number/I5Y3325GYAX5646X4V4EHIM545/events.json","paper":"https://pith.science/paper/I5Y3325G"},"agent_actions":{"view_html":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545","download_json":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545.json","view_paper":"https://pith.science/paper/I5Y3325G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15420&json=true","fetch_graph":"https://pith.science/api/pith-number/I5Y3325GYAX5646X4V4EHIM545/graph.json","fetch_events":"https://pith.science/api/pith-number/I5Y3325GYAX5646X4V4EHIM545/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545/action/storage_attestation","attest_author":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545/action/author_attestation","sign_citation":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545/action/citation_signature","submit_replication":"https://pith.science/pith/I5Y3325GYAX5646X4V4EHIM545/action/replication_record"}},"created_at":"2026-07-05T10:35:25.951879+00:00","updated_at":"2026-07-05T10:35:25.951879+00:00"}