{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KUC7UFUFKRW73XTYRLCHBXT73T","short_pith_number":"pith:KUC7UFUF","schema_version":"1.0","canonical_sha256":"5505fa1685546dfdde788ac470de7fdcf2f47cf534d85379c8ee1dc86547a420","source":{"kind":"arxiv","id":"2401.13923","version":2},"attestation_state":"computed","paper":{"title":"Towards 3D Molecule-Text Interpretation in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Kenji Kawaguchi, Qi Tian, Sihang Li, Tat-Seng Chua, Xiangnan He, Xiang Wang, Yanchen Luo, Zhiyuan Liu","submitted_at":"2024-01-25T03:42:00Z","abstract_excerpt":"Language Models (LMs) have greatly influenced diverse domains. However, their inherent limitation in comprehending 3D molecular structures has considerably constrained their potential in the biomolecular domain. To bridge this gap, we focus on 3D molecule-text interpretation, and propose 3D-MoLM: 3D-Molecular Language Modeling. Specifically, 3D-MoLM enables an LM to interpret and analyze 3D molecules by equipping the LM with a 3D molecular encoder. This integration is achieved by a 3D molecule-text projector, bridging the 3D molecular encoder's representation space and the LM's input space. Mo"},"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":"2401.13923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-25T03:42:00Z","cross_cats_sorted":["cs.IR","q-bio.BM"],"title_canon_sha256":"f3ad3c9b4a7ff8bb8d255f1d6d4fe78c98ede4983d37c1f6e9324c3baf13d146","abstract_canon_sha256":"8b55b3b89117eb87c17ab33760fae12ae9d727beaecc5433c6f286018c4e0d37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:58.858608Z","signature_b64":"HfeTdrqCQ2iNWAC7949AAAbE+zoMpvjD+8cXGsdVDbi1mWWIU2aNEYs+lIYOfr7GtHZBR5kUshzMDS+mEpbmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5505fa1685546dfdde788ac470de7fdcf2f47cf534d85379c8ee1dc86547a420","last_reissued_at":"2026-07-05T07:56:58.858144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:58.858144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards 3D Molecule-Text Interpretation in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Kenji Kawaguchi, Qi Tian, Sihang Li, Tat-Seng Chua, Xiangnan He, Xiang Wang, Yanchen Luo, Zhiyuan Liu","submitted_at":"2024-01-25T03:42:00Z","abstract_excerpt":"Language Models (LMs) have greatly influenced diverse domains. However, their inherent limitation in comprehending 3D molecular structures has considerably constrained their potential in the biomolecular domain. To bridge this gap, we focus on 3D molecule-text interpretation, and propose 3D-MoLM: 3D-Molecular Language Modeling. Specifically, 3D-MoLM enables an LM to interpret and analyze 3D molecules by equipping the LM with a 3D molecular encoder. This integration is achieved by a 3D molecule-text projector, bridging the 3D molecular encoder's representation space and the LM's input space. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13923","kind":"arxiv","version":2},"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/2401.13923/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":"2401.13923","created_at":"2026-07-05T07:56:58.858205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13923v2","created_at":"2026-07-05T07:56:58.858205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13923","created_at":"2026-07-05T07:56:58.858205+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUC7UFUFKRW7","created_at":"2026-07-05T07:56:58.858205+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUC7UFUFKRW73XTY","created_at":"2026-07-05T07:56:58.858205+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUC7UFUF","created_at":"2026-07-05T07:56:58.858205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2411.14721","citing_title":"MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22287","citing_title":"SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04403","citing_title":"MolDA: Molecular Understanding and Generation via Large Language Diffusion Model","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T","json":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T.json","graph_json":"https://pith.science/api/pith-number/KUC7UFUFKRW73XTYRLCHBXT73T/graph.json","events_json":"https://pith.science/api/pith-number/KUC7UFUFKRW73XTYRLCHBXT73T/events.json","paper":"https://pith.science/paper/KUC7UFUF"},"agent_actions":{"view_html":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T","download_json":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T.json","view_paper":"https://pith.science/paper/KUC7UFUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13923&json=true","fetch_graph":"https://pith.science/api/pith-number/KUC7UFUFKRW73XTYRLCHBXT73T/graph.json","fetch_events":"https://pith.science/api/pith-number/KUC7UFUFKRW73XTYRLCHBXT73T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T/action/storage_attestation","attest_author":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T/action/author_attestation","sign_citation":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T/action/citation_signature","submit_replication":"https://pith.science/pith/KUC7UFUFKRW73XTYRLCHBXT73T/action/replication_record"}},"created_at":"2026-07-05T07:56:58.858205+00:00","updated_at":"2026-07-05T07:56:58.858205+00:00"}