{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6KJEUCPZ4Q445TUEHFCF72W42E","short_pith_number":"pith:6KJEUCPZ","schema_version":"1.0","canonical_sha256":"f2924a09f9e439cece8439445feadcd12ae438b4aa5635874b6fa410837a97ec","source":{"kind":"arxiv","id":"2505.12137","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.LG","authors_text":"Can Polat, Erchin Serpedin, Hasan Kurban, Mustafa Kurban","submitted_at":"2025-05-17T20:42:16Z","abstract_excerpt":"Molecular graph neural networks (GNNs) often focus exclusively on XYZ-based geometric representations and thus overlook valuable chemical context available in public databases like PubChem. This work introduces a multimodal framework that integrates textual descriptors, such as IUPAC names, molecular formulas, physicochemical properties, and synonyms, alongside molecular graphs. A gated fusion mechanism balances geometric and textual features, allowing models to exploit complementary information. Experiments on benchmark datasets indicate that adding textual data yields notable improvements fo"},"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":"2505.12137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T20:42:16Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"f3888ac774b6dff654b8464864c62f3bc493a91814bfb1306b9ebe6c00ecf16e","abstract_canon_sha256":"a766f648bc9016c9bf234192f55d9411396381a0ddba630fa91a80c9e6a75878"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:59.166748Z","signature_b64":"6RvyJ2bRFzAlyZMw2zp8l8hF+ILdKBUSyaMETHsZB+OhoLmcKzKYM4we1Rg0GDzXeqn14AHDRr0xMw+/HsMZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2924a09f9e439cece8439445feadcd12ae438b4aa5635874b6fa410837a97ec","last_reissued_at":"2026-07-05T11:04:59.166252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:59.166252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.LG","authors_text":"Can Polat, Erchin Serpedin, Hasan Kurban, Mustafa Kurban","submitted_at":"2025-05-17T20:42:16Z","abstract_excerpt":"Molecular graph neural networks (GNNs) often focus exclusively on XYZ-based geometric representations and thus overlook valuable chemical context available in public databases like PubChem. This work introduces a multimodal framework that integrates textual descriptors, such as IUPAC names, molecular formulas, physicochemical properties, and synonyms, alongside molecular graphs. A gated fusion mechanism balances geometric and textual features, allowing models to exploit complementary information. Experiments on benchmark datasets indicate that adding textual data yields notable improvements fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12137","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/2505.12137/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":"2505.12137","created_at":"2026-07-05T11:04:59.166327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12137v1","created_at":"2026-07-05T11:04:59.166327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12137","created_at":"2026-07-05T11:04:59.166327+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KJEUCPZ4Q44","created_at":"2026-07-05T11:04:59.166327+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KJEUCPZ4Q445TUE","created_at":"2026-07-05T11:04:59.166327+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KJEUCPZ","created_at":"2026-07-05T11:04:59.166327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20574","citing_title":"xChemAgents: Agentic AI for Explainable Quantum Chemistry","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E","json":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E.json","graph_json":"https://pith.science/api/pith-number/6KJEUCPZ4Q445TUEHFCF72W42E/graph.json","events_json":"https://pith.science/api/pith-number/6KJEUCPZ4Q445TUEHFCF72W42E/events.json","paper":"https://pith.science/paper/6KJEUCPZ"},"agent_actions":{"view_html":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E","download_json":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E.json","view_paper":"https://pith.science/paper/6KJEUCPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12137&json=true","fetch_graph":"https://pith.science/api/pith-number/6KJEUCPZ4Q445TUEHFCF72W42E/graph.json","fetch_events":"https://pith.science/api/pith-number/6KJEUCPZ4Q445TUEHFCF72W42E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E/action/storage_attestation","attest_author":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E/action/author_attestation","sign_citation":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E/action/citation_signature","submit_replication":"https://pith.science/pith/6KJEUCPZ4Q445TUEHFCF72W42E/action/replication_record"}},"created_at":"2026-07-05T11:04:59.166327+00:00","updated_at":"2026-07-05T11:04:59.166327+00:00"}