{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G46S23ALC46NMOY2GRDX3GIGWM","short_pith_number":"pith:G46S23AL","schema_version":"1.0","canonical_sha256":"373d2d6c0b173cd63b1a34477d9906b3160e9207ed4b6b0d34d8534c323bbd36","source":{"kind":"arxiv","id":"2605.27245","version":1},"attestation_state":"computed","paper":{"title":"Symbolic Regression via Latent Iterative Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sriram Vishwanath, Vijay Ganesh, Xieting Chu","submitted_at":"2026-05-26T16:25:05Z","abstract_excerpt":"Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized inference leaves a residual amortization gap between its one-shot prediction and the true posterior. We propose Latent Equation Embedding (LEE), a framework that closes this gap through iterative amortized inference in a functionally grounded latent space. LEE learns a shared latent space Z equipped with three components: an encoder f_theta that jointly embeds sym"},"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":"2605.27245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T16:25:05Z","cross_cats_sorted":[],"title_canon_sha256":"cf84e7b46daf61df45c344adf4daa6ea7c931e5de05d177120695f563cba3144","abstract_canon_sha256":"120daf82b6f466f3e86c106f7e790a2773d08027c6c7d9e58baced87308518ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:07.439438Z","signature_b64":"OhdZ6JNqWYIdxANdiLshdijcvjoLeoFBd8nZCbNvGg9PEftuJvsHj0//Rsx8o6AwDG6iYyQz9IAZDdhLNl7QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"373d2d6c0b173cd63b1a34477d9906b3160e9207ed4b6b0d34d8534c323bbd36","last_reissued_at":"2026-05-27T02:06:07.438751Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:07.438751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Regression via Latent Iterative Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sriram Vishwanath, Vijay Ganesh, Xieting Chu","submitted_at":"2026-05-26T16:25:05Z","abstract_excerpt":"Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized inference leaves a residual amortization gap between its one-shot prediction and the true posterior. We propose Latent Equation Embedding (LEE), a framework that closes this gap through iterative amortized inference in a functionally grounded latent space. LEE learns a shared latent space Z equipped with three components: an encoder f_theta that jointly embeds sym"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27245","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/2605.27245/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":"2605.27245","created_at":"2026-05-27T02:06:07.438840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27245v1","created_at":"2026-05-27T02:06:07.438840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27245","created_at":"2026-05-27T02:06:07.438840+00:00"},{"alias_kind":"pith_short_12","alias_value":"G46S23ALC46N","created_at":"2026-05-27T02:06:07.438840+00:00"},{"alias_kind":"pith_short_16","alias_value":"G46S23ALC46NMOY2","created_at":"2026-05-27T02:06:07.438840+00:00"},{"alias_kind":"pith_short_8","alias_value":"G46S23AL","created_at":"2026-05-27T02:06:07.438840+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/G46S23ALC46NMOY2GRDX3GIGWM","json":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM.json","graph_json":"https://pith.science/api/pith-number/G46S23ALC46NMOY2GRDX3GIGWM/graph.json","events_json":"https://pith.science/api/pith-number/G46S23ALC46NMOY2GRDX3GIGWM/events.json","paper":"https://pith.science/paper/G46S23AL"},"agent_actions":{"view_html":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM","download_json":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM.json","view_paper":"https://pith.science/paper/G46S23AL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27245&json=true","fetch_graph":"https://pith.science/api/pith-number/G46S23ALC46NMOY2GRDX3GIGWM/graph.json","fetch_events":"https://pith.science/api/pith-number/G46S23ALC46NMOY2GRDX3GIGWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM/action/storage_attestation","attest_author":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM/action/author_attestation","sign_citation":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM/action/citation_signature","submit_replication":"https://pith.science/pith/G46S23ALC46NMOY2GRDX3GIGWM/action/replication_record"}},"created_at":"2026-05-27T02:06:07.438840+00:00","updated_at":"2026-05-27T02:06:07.438840+00:00"}