{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R557JY7NBQDXOEDH5ZG7YCMRGE","short_pith_number":"pith:R557JY7N","schema_version":"1.0","canonical_sha256":"8f7bf4e3ed0c07771067ee4dfc09913127db48caf9aeeb8277ba2817c475f134","source":{"kind":"arxiv","id":"2201.12204","version":3},"attestation_state":"computed","paper":{"title":"From data to functa: Your data point is a function and you can treat it like one","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danilo Rezende, Dan Rosenbaum, Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami","submitted_at":"2022-01-28T15:59:58Z","abstract_excerpt":"It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often continuous, e.g. the scene depicted in an image. A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location. In this paper, we take this idea to its next level: what would it take to perform deep learning on these functions instead, treating th"},"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":"2201.12204","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T15:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"dbc7e568460c21426ef333db7f138096425e672bbc7cb908bf7c4ef6e02b25f1","abstract_canon_sha256":"ae44108540b87e252a6e90df515003364f48d21d08fafe25bf43da2b7831af90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:56.260390Z","signature_b64":"xFo5LbqPSiYfNEsXSdrDVPe8xCJUHcgpAzGJb4kphUCSidl/2azNTTfkbcR47EDjZ58PiBlmiGgQbtXlooO6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f7bf4e3ed0c07771067ee4dfc09913127db48caf9aeeb8277ba2817c475f134","last_reissued_at":"2026-07-05T05:14:56.259949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:56.259949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From data to functa: Your data point is a function and you can treat it like one","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danilo Rezende, Dan Rosenbaum, Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami","submitted_at":"2022-01-28T15:59:58Z","abstract_excerpt":"It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often continuous, e.g. the scene depicted in an image. A powerful continuous alternative is then to represent these measurements using an implicit neural representation, a neural function trained to output the appropriate measurement value for any input spatial location. In this paper, we take this idea to its next level: what would it take to perform deep learning on these functions instead, treating th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12204","kind":"arxiv","version":3},"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/2201.12204/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":"2201.12204","created_at":"2026-07-05T05:14:56.260007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12204v3","created_at":"2026-07-05T05:14:56.260007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12204","created_at":"2026-07-05T05:14:56.260007+00:00"},{"alias_kind":"pith_short_12","alias_value":"R557JY7NBQDX","created_at":"2026-07-05T05:14:56.260007+00:00"},{"alias_kind":"pith_short_16","alias_value":"R557JY7NBQDXOEDH","created_at":"2026-07-05T05:14:56.260007+00:00"},{"alias_kind":"pith_short_8","alias_value":"R557JY7N","created_at":"2026-07-05T05:14:56.260007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02166","citing_title":"Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12200","citing_title":"Implicit Neural Representations of Individual Behavior","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00404","citing_title":"Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13919","citing_title":"Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19959","citing_title":"Learning Orthonormal Bases for Function Spaces","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20098","citing_title":"Incomplete Data, Complete Dynamics: A Diffusion Approach","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23748","citing_title":"A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2305.02463","citing_title":"Shap-E: Generating Conditional 3D Implicit Functions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08058","citing_title":"Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08298","citing_title":"What Cohort INRs Encode and Where to Freeze Them","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06298","citing_title":"Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06298","citing_title":"Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07444","citing_title":"Accelerated and data-efficient flow prediction in stirred tanks via physics-informed learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05700","citing_title":"Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE","json":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE.json","graph_json":"https://pith.science/api/pith-number/R557JY7NBQDXOEDH5ZG7YCMRGE/graph.json","events_json":"https://pith.science/api/pith-number/R557JY7NBQDXOEDH5ZG7YCMRGE/events.json","paper":"https://pith.science/paper/R557JY7N"},"agent_actions":{"view_html":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE","download_json":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE.json","view_paper":"https://pith.science/paper/R557JY7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12204&json=true","fetch_graph":"https://pith.science/api/pith-number/R557JY7NBQDXOEDH5ZG7YCMRGE/graph.json","fetch_events":"https://pith.science/api/pith-number/R557JY7NBQDXOEDH5ZG7YCMRGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE/action/storage_attestation","attest_author":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE/action/author_attestation","sign_citation":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE/action/citation_signature","submit_replication":"https://pith.science/pith/R557JY7NBQDXOEDH5ZG7YCMRGE/action/replication_record"}},"created_at":"2026-07-05T05:14:56.260007+00:00","updated_at":"2026-07-05T05:14:56.260007+00:00"}