{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SYENSNTG2SJZO5TJAC3IIFQTZ4","short_pith_number":"pith:SYENSNTG","canonical_record":{"source":{"id":"2604.08324","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-09T14:55:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c9ebf048320b667acb632d18395369f479a7eaa5c856ec005ba4cd395d5543d","abstract_canon_sha256":"5403a71c759e81aa0543492264ba46c90be7a2eba9751d257b99a089eab6d560"},"schema_version":"1.0"},"canonical_sha256":"9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48","source":{"kind":"arxiv","id":"2604.08324","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08324","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08324v3","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08324","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"SYENSNTG2SJZ","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"SYENSNTG2SJZO5TJ","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"SYENSNTG","created_at":"2026-06-02T02:04:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SYENSNTG2SJZO5TJAC3IIFQTZ4","target":"record","payload":{"canonical_record":{"source":{"id":"2604.08324","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-09T14:55:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c9ebf048320b667acb632d18395369f479a7eaa5c856ec005ba4cd395d5543d","abstract_canon_sha256":"5403a71c759e81aa0543492264ba46c90be7a2eba9751d257b99a089eab6d560"},"schema_version":"1.0"},"canonical_sha256":"9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:17.239743Z","signature_b64":"xwghxDI6n9i58yATQy66Itjh2Fl+l5GsvbkU1pDMorqSWBQCgzodXrAk1SBCifBfuVWvr5eZ6+pjbSP43e9HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48","last_reissued_at":"2026-06-02T02:04:17.239321Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:17.239321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.08324","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CapqWrhK1cTcwPJFeOAOOSPKsAPjgGNMdNNFb6jIAbS1MxmDweZme2X7r/pg7cGic6FDN+o1nCntvd0Tpa6PDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:53:29.048035Z"},"content_sha256":"37ec9cf16c5cd0c1fce38f834d068e9b6f3a5d0e1dadfdb7eb52e1701bddf71c","schema_version":"1.0","event_id":"sha256:37ec9cf16c5cd0c1fce38f834d068e9b6f3a5d0e1dadfdb7eb52e1701bddf71c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SYENSNTG2SJZO5TJAC3IIFQTZ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search.","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Benjamin L\\'eger, Christian Gagn\\'e, Kazem Meidani","submitted_at":"2026-04-09T14:55:36Z","abstract_excerpt":"Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use neural encoders to map symbolic expressions into continuous spaces, transforming the combinatorial search into continuous optimization. SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal approach: aligning symbolic and numeric encoders in a shared latent space to learn the phenotype-genotype"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our experiments show that: (1) cross-modal alignment does not improve during optimization, even as fitness increases, and (2) the alignment learned by SNIP is too coarse to efficiently conduct principled search in the symbolic space.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the chosen metrics for cross-modal alignment and the optimization process accurately capture whether the alignment enables effective bi-modal search, without confounding factors from the specific experimental setup or choice of SNIP hyperparameters.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Experiments reveal that cross-modal alignment in SNIP does not improve with increasing fitness and is too coarse for effective symbolic search in latent space optimization for symbolic regression.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1eb511dbde064a89b3acbe074b5ebe487a1956342b62072c4cddccc86b2acaaf"},"source":{"id":"2604.08324","kind":"arxiv","version":3},"verdict":{"id":"130c01c4-9376-4805-ada9-5c7e7b007168","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:24:26.074534Z","strongest_claim":"Our experiments show that: (1) cross-modal alignment does not improve during optimization, even as fitness increases, and (2) the alignment learned by SNIP is too coarse to efficiently conduct principled search in the symbolic space.","one_line_summary":"Experiments reveal that cross-modal alignment in SNIP does not improve with increasing fitness and is too coarse for effective symbolic search in latent space optimization for symbolic regression.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the chosen metrics for cross-modal alignment and the optimization process accurately capture whether the alignment enables effective bi-modal search, without confounding factors from the specific experimental setup or choice of SNIP hyperparameters.","pith_extraction_headline":"SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08324/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"},"verdict_id":"130c01c4-9376-4805-ada9-5c7e7b007168"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWpNW0Kq+us61i2JGKikoEEq756cE1qie4CG1bVvI4agTU2yJiUcjUbCsS0y3uNkxCQH+uvyxEkaYCgr1Bo4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:53:29.048514Z"},"content_sha256":"356b28903d2c4523185da932c187be66f0a1c7ee9431f90337f8529900c4af6c","schema_version":"1.0","event_id":"sha256:356b28903d2c4523185da932c187be66f0a1c7ee9431f90337f8529900c4af6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4/bundle.json","state_url":"https://pith.science/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T07:53:29Z","links":{"resolver":"https://pith.science/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4","bundle":"https://pith.science/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4/bundle.json","state":"https://pith.science/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYENSNTG2SJZO5TJAC3IIFQTZ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SYENSNTG2SJZO5TJAC3IIFQTZ4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5403a71c759e81aa0543492264ba46c90be7a2eba9751d257b99a089eab6d560","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-09T14:55:36Z","title_canon_sha256":"3c9ebf048320b667acb632d18395369f479a7eaa5c856ec005ba4cd395d5543d"},"schema_version":"1.0","source":{"id":"2604.08324","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08324","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08324v3","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08324","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_12","alias_value":"SYENSNTG2SJZ","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_16","alias_value":"SYENSNTG2SJZO5TJ","created_at":"2026-06-02T02:04:17Z"},{"alias_kind":"pith_short_8","alias_value":"SYENSNTG","created_at":"2026-06-02T02:04:17Z"}],"graph_snapshots":[{"event_id":"sha256:356b28903d2c4523185da932c187be66f0a1c7ee9431f90337f8529900c4af6c","target":"graph","created_at":"2026-06-02T02:04:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our experiments show that: (1) cross-modal alignment does not improve during optimization, even as fitness increases, and (2) the alignment learned by SNIP is too coarse to efficiently conduct principled search in the symbolic space."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the chosen metrics for cross-modal alignment and the optimization process accurately capture whether the alignment enables effective bi-modal search, without confounding factors from the specific experimental setup or choice of SNIP hyperparameters."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Experiments reveal that cross-modal alignment in SNIP does not improve with increasing fitness and is too coarse for effective symbolic search in latent space optimization for symbolic regression."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search."}],"snapshot_sha256":"1eb511dbde064a89b3acbe074b5ebe487a1956342b62072c4cddccc86b2acaaf"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.08324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use neural encoders to map symbolic expressions into continuous spaces, transforming the combinatorial search into continuous optimization. SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal approach: aligning symbolic and numeric encoders in a shared latent space to learn the phenotype-genotype","authors_text":"Benjamin L\\'eger, Christian Gagn\\'e, Kazem Meidani","cross_cats":["cs.AI"],"headline":"SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-09T14:55:36Z","title":"Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.08324","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T17:24:26.074534Z","id":"130c01c4-9376-4805-ada9-5c7e7b007168","model_set":{"reader":"grok-4.3"},"one_line_summary":"Experiments reveal that cross-modal alignment in SNIP does not improve with increasing fitness and is too coarse for effective symbolic search in latent space optimization for symbolic regression.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SNIP's cross-modal alignment does not improve during optimization even as fitness rises, and stays too coarse for effective symbolic search.","strongest_claim":"Our experiments show that: (1) cross-modal alignment does not improve during optimization, even as fitness increases, and (2) the alignment learned by SNIP is too coarse to efficiently conduct principled search in the symbolic space.","weakest_assumption":"The assumption that the chosen metrics for cross-modal alignment and the optimization process accurately capture whether the alignment enables effective bi-modal search, without confounding factors from the specific experimental setup or choice of SNIP hyperparameters."}},"verdict_id":"130c01c4-9376-4805-ada9-5c7e7b007168"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37ec9cf16c5cd0c1fce38f834d068e9b6f3a5d0e1dadfdb7eb52e1701bddf71c","target":"record","created_at":"2026-06-02T02:04:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5403a71c759e81aa0543492264ba46c90be7a2eba9751d257b99a089eab6d560","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-04-09T14:55:36Z","title_canon_sha256":"3c9ebf048320b667acb632d18395369f479a7eaa5c856ec005ba4cd395d5543d"},"schema_version":"1.0","source":{"id":"2604.08324","kind":"arxiv","version":3}},"canonical_sha256":"9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9608d93666d49397766900b6841613cf104938c82254b4736b32a4766ae87f48","first_computed_at":"2026-06-02T02:04:17.239321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:17.239321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xwghxDI6n9i58yATQy66Itjh2Fl+l5GsvbkU1pDMorqSWBQCgzodXrAk1SBCifBfuVWvr5eZ6+pjbSP43e9HAA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:17.239743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.08324","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37ec9cf16c5cd0c1fce38f834d068e9b6f3a5d0e1dadfdb7eb52e1701bddf71c","sha256:356b28903d2c4523185da932c187be66f0a1c7ee9431f90337f8529900c4af6c"],"state_sha256":"eb04fafb38f68a52d2c88c7eb8f5bacaf4532f0a624489660f3f9c823fd4567c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZmr2RxLKR1Ed1wz8CPE0FVTb6rMU04BM/gGKzuP/1+UsJDyntdKutw0hGbpRUMtrFf4PTm6Ie+oxCDFF69fDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T07:53:29.050777Z","bundle_sha256":"e9712e153f822c55113434928bcd4e4cf56dcc1a6b085435062136f4b10b503a"}}