{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VHNZRC53HSPIPLX7TJXVBXZ27J","short_pith_number":"pith:VHNZRC53","schema_version":"1.0","canonical_sha256":"a9db988bbb3c9e87aeff9a6f50df3afa7a877ea9a4dc1b6c91aa66983a5c1dec","source":{"kind":"arxiv","id":"2510.27497","version":2},"attestation_state":"computed","paper":{"title":"InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haorui Li, Hongyu Guo, Shengchao Liu, Weitao Du, Yuqiang Li","submitted_at":"2025-10-31T14:19:50Z","abstract_excerpt":"Transformer-based autoregressive models have emerged as a unifying paradigm across modalities such as text and images, but their extension to 3D molecule generation remains underexplored. The gap stems from two fundamental challenges: (1) how to tokenize molecules into a canonical 1D sequence of tokens that is invariant to both SE(3) transformations and atom index permutations, and (2) how to design an architecture capable of modeling hybrid atom-based tokens that couple discrete atom types with continuous 3D coordinates. To address these challenges, we introduce InertialAR. It first performs "},"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":"2510.27497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-31T14:19:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2032fec32b594614d72e5841dfaef68d245f27d2e8058e842fc470d0b7ea141","abstract_canon_sha256":"b5acb843bfc6601cef9f47d23046c856dbc5985fa331be0cc356787f9eb4d2c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:38.956737Z","signature_b64":"DNuO226W1XKEXdIvAq/EvbMtr/XrACNolYjzLFD4qSNOpUHl29VSVXJZPmYYXTbGDn30YppHhWYCG31HxmSJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9db988bbb3c9e87aeff9a6f50df3afa7a877ea9a4dc1b6c91aa66983a5c1dec","last_reissued_at":"2026-07-21T01:20:38.955705Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:38.955705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haorui Li, Hongyu Guo, Shengchao Liu, Weitao Du, Yuqiang Li","submitted_at":"2025-10-31T14:19:50Z","abstract_excerpt":"Transformer-based autoregressive models have emerged as a unifying paradigm across modalities such as text and images, but their extension to 3D molecule generation remains underexplored. The gap stems from two fundamental challenges: (1) how to tokenize molecules into a canonical 1D sequence of tokens that is invariant to both SE(3) transformations and atom index permutations, and (2) how to design an architecture capable of modeling hybrid atom-based tokens that couple discrete atom types with continuous 3D coordinates. To address these challenges, we introduce InertialAR. It first performs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.27497","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/2510.27497/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":"2510.27497","created_at":"2026-07-21T01:20:38.956198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.27497v2","created_at":"2026-07-21T01:20:38.956198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27497","created_at":"2026-07-21T01:20:38.956198+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHNZRC53HSPI","created_at":"2026-07-21T01:20:38.956198+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHNZRC53HSPIPLX7","created_at":"2026-07-21T01:20:38.956198+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHNZRC53","created_at":"2026-07-21T01:20:38.956198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.05844","citing_title":"NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J","json":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J.json","graph_json":"https://pith.science/api/pith-number/VHNZRC53HSPIPLX7TJXVBXZ27J/graph.json","events_json":"https://pith.science/api/pith-number/VHNZRC53HSPIPLX7TJXVBXZ27J/events.json","paper":"https://pith.science/paper/VHNZRC53"},"agent_actions":{"view_html":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J","download_json":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J.json","view_paper":"https://pith.science/paper/VHNZRC53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.27497&json=true","fetch_graph":"https://pith.science/api/pith-number/VHNZRC53HSPIPLX7TJXVBXZ27J/graph.json","fetch_events":"https://pith.science/api/pith-number/VHNZRC53HSPIPLX7TJXVBXZ27J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J/action/storage_attestation","attest_author":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J/action/author_attestation","sign_citation":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J/action/citation_signature","submit_replication":"https://pith.science/pith/VHNZRC53HSPIPLX7TJXVBXZ27J/action/replication_record"}},"created_at":"2026-07-21T01:20:38.956198+00:00","updated_at":"2026-07-21T01:20:38.956198+00:00"}