{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DCX5QCOHTTEAYI7VZRBHO2BNBU","short_pith_number":"pith:DCX5QCOH","canonical_record":{"source":{"id":"2605.13262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"ecfb724f3a9ac93429b8c6f95ac15d1f2ec97b7fa196a4088b0ffc5e475efa97","abstract_canon_sha256":"c8f0d517bcefeb0f640076c6e5cf5366d59abdc200a7b8eb6aceb0b9ab1b7738"},"schema_version":"1.0"},"canonical_sha256":"18afd809c79cc80c23f5cc4277682d0d39c9d76a48d75ba38a9c6554748be314","source":{"kind":"arxiv","id":"2605.13262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13262","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13262v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13262","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"DCX5QCOHTTEA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DCX5QCOHTTEAYI7V","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DCX5QCOH","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DCX5QCOHTTEAYI7VZRBHO2BNBU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"ecfb724f3a9ac93429b8c6f95ac15d1f2ec97b7fa196a4088b0ffc5e475efa97","abstract_canon_sha256":"c8f0d517bcefeb0f640076c6e5cf5366d59abdc200a7b8eb6aceb0b9ab1b7738"},"schema_version":"1.0"},"canonical_sha256":"18afd809c79cc80c23f5cc4277682d0d39c9d76a48d75ba38a9c6554748be314","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:49.343670Z","signature_b64":"AViKDVvHFngkHs9UNfwrcRGEs1vyjfb9Vf08cMrrXmU4wPLCV9Ud970rDnOnwoIgTUv5gbKDVdgTgqMhcHSSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18afd809c79cc80c23f5cc4277682d0d39c9d76a48d75ba38a9c6554748be314","last_reissued_at":"2026-05-18T02:44:49.343254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:49.343254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13262","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRgOCVXxnZpjZaBJ43o4VScnPMLB0JVlBtbxUazNoiCnMNQ7O4mrc6CSPxlmSBg/r76ySXmIU72SOYjtiyTeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:07:01.909112Z"},"content_sha256":"7c48d22c79975659e68d47a961c7aacf1230f6e605ea52cd0443255c1e065238","schema_version":"1.0","event_id":"sha256:7c48d22c79975659e68d47a961c7aacf1230f6e605ea52cd0443255c1e065238"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DCX5QCOHTTEAYI7VZRBHO2BNBU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Chem-GMNet, a sphere-native geometric transformer, outperforms same-sized ChemBERTa-2 on 7 of 10 MoleculeNet endpoints with about 35 percent fewer parameters.","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Deepak Warrier, Raja Sekhar Pappala","submitted_at":"2026-05-13T09:43:55Z","abstract_excerpt":"Modern SMILES-based chemical language models obtain strong MoleculeNet performance by treating SMILES as generic text and compensating with multi-million-molecule self-supervised pretraining. We ask: when a domain carries structural priors as rich as chemistry's, does it warrant a domain-native transformer rather than a generic one rescued by scale? We answer affirmatively with \\textbf{GM-Net} (Geometric Measure Network), a transformer family in which every module is replaced by a sphere-native counterpart, and instantiate it as \\textbf{Chem-GMNet}. Three blocks follow: SH-Embedding (tokens as"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On canonical DeepChem scaffold splits, random-initialised Chem-GMNet wins on 7 of 10 MoleculeNet endpoints at ~35% fewer parameters than same-shape ChemBERTa-2 baselines; pretrained on the same 10M-SMILES ZINC corpus it matches or beats the public release on 6 of 8 shared endpoints.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the reported performance gains arise from the sphere-native inductive biases rather than from differences in training protocol, hyperparameter tuning, or data handling that are not fully detailed in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Chem-GMNet, a sphere-native geometric transformer, outperforms same-sized ChemBERTa-2 on 7 of 10 MoleculeNet endpoints with about 35 percent fewer parameters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ab747a7f607569ac27790cb5fd86aef9a800cc076d95cdd23f5a6f62d7df4618"},"source":{"id":"2605.13262","kind":"arxiv","version":1},"verdict":{"id":"91a5a470-4dda-4f38-ad18-b0b104e36d88","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:48:15.988785Z","strongest_claim":"On canonical DeepChem scaffold splits, random-initialised Chem-GMNet wins on 7 of 10 MoleculeNet endpoints at ~35% fewer parameters than same-shape ChemBERTa-2 baselines; pretrained on the same 10M-SMILES ZINC corpus it matches or beats the public release on 6 of 8 shared endpoints.","one_line_summary":"Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the reported performance gains arise from the sphere-native inductive biases rather than from differences in training protocol, hyperparameter tuning, or data handling that are not fully detailed in the abstract.","pith_extraction_headline":"Chem-GMNet, a sphere-native geometric transformer, outperforms same-sized ChemBERTa-2 on 7 of 10 MoleculeNet endpoints with about 35 percent fewer parameters."},"references":{"count":37,"sample":[{"doi":"","year":2024,"title":"Kendall Atkinson and Weimin Han.Spherical Harmonics and Approximations on the Unit Sphere: An Introduc- tion, volume 2044 ofLecture Notes in Mathematics","work_id":"7f7dbda8-3cb4-472c-a440-a82227746c52","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1007/97","year":null,"title":"A Practical Guide to TPM 2.0","work_id":"0ea0856b-5e33-4766-9b0a-4041f79be461","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1038/s41467-022-29939-5","year":null,"title":"E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials","work_id":"f52ce8d5-e753-4360-a60f-60c8faae7c16","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1038/s41570","year":null,"title":"Boris Bonev, Thorsten Kurth, Tom Kölbl, et al","work_id":"9ddf75c9-5940-43de-abbb-133dd54e4e26","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Seyone Chithrananda, Gabriel Grand, and Bharath Ram- sundar","work_id":"2e8f3af2-95cf-4889-9301-a4b279aea96c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"70e2cf5e55b29d5061326ae56c1fee57c56bb7b7a3d57b1a6edc41248f4fe48a","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1a35cc4079fbbc24f3620203bca31fee01a1d4f6c15b91130af121718aa28977"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"91a5a470-4dda-4f38-ad18-b0b104e36d88"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RAMbgCEtJPv+N50YMz58sfsvyf/6EDpMZyJAI4dP8lvLJi1hOfP3khJIMRswBlTx+pyZ6y7VPlUsvrBQ9H7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:07:01.909678Z"},"content_sha256":"01e034aa779100b942e539ca7f5aa548f0832957d55cdcd16902ae5e6ce9a655","schema_version":"1.0","event_id":"sha256:01e034aa779100b942e539ca7f5aa548f0832957d55cdcd16902ae5e6ce9a655"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:DCX5QCOHTTEAYI7VZRBHO2BNBU","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.drudis.2023.103563) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://doi.org/10.1016/j.dr udis.2023.103563. Benedek Fabian, Thomas Edlich, Heloisa Gaspar, Marwin Segler, Joshua Meyers, Marco Fiscato, and Mohamed H. S. Segler. Molecular representation learning with language models and domain-relev","arxiv_id":"2605.13262","detector":"doi_compliance","evidence":{"ref_index":10,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://doi.org/10.1016/j.dr udis.2023.103563. Benedek Fabian, Thomas Edlich, Heloisa Gaspar, Marwin Segler, Joshua Meyers, Marco Fiscato, and Mohamed H. S. Segler. Molecular representation learning with language models and domain-relev","reconstructed_doi":"10.1016/j.drudis.2023.103563"},"severity":"advisory","ref_index":10,"audited_at":"2026-05-19T06:42:26.401668Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.drudis.2023.103563","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5a39a9a4b340239253af8b0a66b8fbc8379ce770b7d3ebe68a49a8a51e6a4e1a","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":196,"payload_sha256":"9f3fb1a2ddb34b63adac8091e9778268e067c5d5527d5295466d38cd0cb1aedf","signature_b64":"hYgfWK+TTu3vveo8nCtuBi7G7wbFfa12F2WBvFoXOtY9DpbEBJ2ot1t4WeEYVDgkJepYz5Fpq08zVF1d94QGDQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T06:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Zz9VNC7KN5oromUuGzQJV3s0bu/LDaLOOUBBCWRwiZoXw7JLrnLrpHmXzH4YXcYoYizmFn96FQlCoSe4Wq7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:07:01.910563Z"},"content_sha256":"a794e0934d2dd4434eba2d9aba6cc408e7aca14e8288e7bac1cb9e9dd16c00c3","schema_version":"1.0","event_id":"sha256:a794e0934d2dd4434eba2d9aba6cc408e7aca14e8288e7bac1cb9e9dd16c00c3"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:DCX5QCOHTTEAYI7VZRBHO2BNBU","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/978-3-642-25983-8.Ilyes) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://doi.org/10.1007/97 8-3-642-25983-8. Ilyes Batatia, David Peter Kovacs, Gregor N. C. Simm, Christoph Ortner, and Gábor Csányi. MACE: Higher order equivariant message passing neural networks. In Advances in Neural Information Proc","arxiv_id":"2605.13262","detector":"doi_compliance","evidence":{"ref_index":2,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://doi.org/10.1007/97 8-3-642-25983-8. Ilyes Batatia, David Peter Kovacs, Gregor N. C. Simm, Christoph Ortner, and Gábor Csányi. MACE: Higher order equivariant message passing neural networks. In Advances in Neural Information Proc","reconstructed_doi":"10.1007/978-3-642-25983-8.Ilyes"},"severity":"advisory","ref_index":2,"audited_at":"2026-05-19T06:42:26.401668Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/978-3-642-25983-8.Ilyes","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"c99cfc3f3d14e169a6f889f5e28887f61b8a4f9ed8c29336b2f3135d0c18cc6c","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":195,"payload_sha256":"d67779959f09f063cbaa42711b29e77da3e6182e301f228c81b6b23dc9965951","signature_b64":"h04ApHxkz5NsuriPO2Rb01DfP45Q6wSqVKJq6e9q50Ke17wkSch1AEEWsBuCcjPbsWc8N7VjSFLU7TaHB+i6Cg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T06:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wwaxiaoAVUNbsVR+1s0Z85lGAnneJ+i2MdMUzZUouKAhlXiFhMkI712mfzCj0TSNksP4O48HLSO6IkgUDY1NCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:07:01.910857Z"},"content_sha256":"51c7df7e15821fb73b557c77af8b71d8411f845ebaf9c68a447e758107e545e9","schema_version":"1.0","event_id":"sha256:51c7df7e15821fb73b557c77af8b71d8411f845ebaf9c68a447e758107e545e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU/bundle.json","state_url":"https://pith.science/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU/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":"2026-05-21T09:07:01Z","links":{"resolver":"https://pith.science/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU","bundle":"https://pith.science/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU/bundle.json","state":"https://pith.science/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DCX5QCOHTTEAYI7VZRBHO2BNBU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DCX5QCOHTTEAYI7VZRBHO2BNBU","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c8f0d517bcefeb0f640076c6e5cf5366d59abdc200a7b8eb6aceb0b9ab1b7738","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55Z","title_canon_sha256":"ecfb724f3a9ac93429b8c6f95ac15d1f2ec97b7fa196a4088b0ffc5e475efa97"},"schema_version":"1.0","source":{"id":"2605.13262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13262","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13262v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13262","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"DCX5QCOHTTEA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DCX5QCOHTTEAYI7V","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DCX5QCOH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:01e034aa779100b942e539ca7f5aa548f0832957d55cdcd16902ae5e6ce9a655","target":"graph","created_at":"2026-05-18T02:44:49Z","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":"On canonical DeepChem scaffold splits, random-initialised Chem-GMNet wins on 7 of 10 MoleculeNet endpoints at ~35% fewer parameters than same-shape ChemBERTa-2 baselines; pretrained on the same 10M-SMILES ZINC corpus it matches or beats the public release on 6 of 8 shared endpoints."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the reported performance gains arise from the sphere-native inductive biases rather than from differences in training protocol, hyperparameter tuning, or data handling that are not fully detailed in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Chem-GMNet, a sphere-native geometric transformer, outperforms same-sized ChemBERTa-2 on 7 of 10 MoleculeNet endpoints with about 35 percent fewer parameters."}],"snapshot_sha256":"ab747a7f607569ac27790cb5fd86aef9a800cc076d95cdd23f5a6f62d7df4618"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1a35cc4079fbbc24f3620203bca31fee01a1d4f6c15b91130af121718aa28977"},"paper":{"abstract_excerpt":"Modern SMILES-based chemical language models obtain strong MoleculeNet performance by treating SMILES as generic text and compensating with multi-million-molecule self-supervised pretraining. We ask: when a domain carries structural priors as rich as chemistry's, does it warrant a domain-native transformer rather than a generic one rescued by scale? We answer affirmatively with \\textbf{GM-Net} (Geometric Measure Network), a transformer family in which every module is replaced by a sphere-native counterpart, and instantiate it as \\textbf{Chem-GMNet}. Three blocks follow: SH-Embedding (tokens as","authors_text":"Deepak Warrier, Raja Sekhar Pappala","cross_cats":["q-bio.QM"],"headline":"Chem-GMNet, a sphere-native geometric transformer, outperforms same-sized ChemBERTa-2 on 7 of 10 MoleculeNet endpoints with about 35 percent fewer parameters.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55Z","title":"Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction"},"references":{"count":37,"internal_anchors":5,"resolved_work":37,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Kendall Atkinson and Weimin Han.Spherical Harmonics and Approximations on the Unit Sphere: An Introduc- tion, volume 2044 ofLecture Notes in Mathematics","work_id":"7f7dbda8-3cb4-472c-a440-a82227746c52","year":2024},{"cited_arxiv_id":"","doi":"10.1007/97","is_internal_anchor":false,"ref_index":2,"title":"A Practical Guide to TPM 2.0","work_id":"0ea0856b-5e33-4766-9b0a-4041f79be461","year":null},{"cited_arxiv_id":"","doi":"10.1038/s41467-022-29939-5","is_internal_anchor":false,"ref_index":3,"title":"E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials","work_id":"f52ce8d5-e753-4360-a60f-60c8faae7c16","year":null},{"cited_arxiv_id":"","doi":"10.1038/s41570","is_internal_anchor":false,"ref_index":4,"title":"Boris Bonev, Thorsten Kurth, Tom Kölbl, et al","work_id":"9ddf75c9-5940-43de-abbb-133dd54e4e26","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Seyone Chithrananda, Gabriel Grand, and Bharath Ram- sundar","work_id":"2e8f3af2-95cf-4889-9301-a4b279aea96c","year":2010}],"snapshot_sha256":"70e2cf5e55b29d5061326ae56c1fee57c56bb7b7a3d57b1a6edc41248f4fe48a"},"source":{"id":"2605.13262","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:48:15.988785Z","id":"91a5a470-4dda-4f38-ad18-b0b104e36d88","model_set":{"reader":"grok-4.3"},"one_line_summary":"Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Chem-GMNet, a sphere-native geometric transformer, outperforms same-sized ChemBERTa-2 on 7 of 10 MoleculeNet endpoints with about 35 percent fewer parameters.","strongest_claim":"On canonical DeepChem scaffold splits, random-initialised Chem-GMNet wins on 7 of 10 MoleculeNet endpoints at ~35% fewer parameters than same-shape ChemBERTa-2 baselines; pretrained on the same 10M-SMILES ZINC corpus it matches or beats the public release on 6 of 8 shared endpoints.","weakest_assumption":"That the reported performance gains arise from the sphere-native inductive biases rather than from differences in training protocol, hyperparameter tuning, or data handling that are not fully detailed in the abstract."}},"verdict_id":"91a5a470-4dda-4f38-ad18-b0b104e36d88"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7c48d22c79975659e68d47a961c7aacf1230f6e605ea52cd0443255c1e065238","target":"record","created_at":"2026-05-18T02:44:49Z","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":"c8f0d517bcefeb0f640076c6e5cf5366d59abdc200a7b8eb6aceb0b9ab1b7738","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T09:43:55Z","title_canon_sha256":"ecfb724f3a9ac93429b8c6f95ac15d1f2ec97b7fa196a4088b0ffc5e475efa97"},"schema_version":"1.0","source":{"id":"2605.13262","kind":"arxiv","version":1}},"canonical_sha256":"18afd809c79cc80c23f5cc4277682d0d39c9d76a48d75ba38a9c6554748be314","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18afd809c79cc80c23f5cc4277682d0d39c9d76a48d75ba38a9c6554748be314","first_computed_at":"2026-05-18T02:44:49.343254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:49.343254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AViKDVvHFngkHs9UNfwrcRGEs1vyjfb9Vf08cMrrXmU4wPLCV9Ud970rDnOnwoIgTUv5gbKDVdgTgqMhcHSSDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:49.343670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13262","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:51c7df7e15821fb73b557c77af8b71d8411f845ebaf9c68a447e758107e545e9","sha256:a794e0934d2dd4434eba2d9aba6cc408e7aca14e8288e7bac1cb9e9dd16c00c3"]}],"invalid_events":[],"applied_event_ids":["sha256:7c48d22c79975659e68d47a961c7aacf1230f6e605ea52cd0443255c1e065238","sha256:01e034aa779100b942e539ca7f5aa548f0832957d55cdcd16902ae5e6ce9a655"],"state_sha256":"96aa79d31f5c1beedb7c038100b0c51a34bce96619358290d6191abcbe0884ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGIStrATlKZxc+B112EDYf7lg5aH5qh2vH39h7TDpYXdcLM+q7xGeceZDzNxsv0rELjpPfkjRgcpO3hy/8lSDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T09:07:01.913416Z","bundle_sha256":"3918de1798d56ffd6112d4a01bbcde329ccba4ea07da1f75c3f206f96143202c"}}