{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TT5HP4P2NZYFFYV4FS4LYEVVJP","short_pith_number":"pith:TT5HP4P2","schema_version":"1.0","canonical_sha256":"9cfa77f1fa6e7052e2bc2cb8bc12b54bd8d59188a0493ae1a6c02159b7d9b3be","source":{"kind":"arxiv","id":"2605.16088","version":1},"attestation_state":"computed","paper":{"title":"Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hou-Biao Li, Xiayu Liu, Zhengyi Lu","submitted_at":"2026-05-15T15:47:11Z","abstract_excerpt":"Self-supervised pretraining on molecular graphs has emerged as a promising approach for molecular property prediction, yet most existing methods operate at a single structural granularity and treat bond information as auxiliary edge attributes rather than as an independent semantic layer. In this work, we propose MolCHG, a multi-level self-supervised pretraining framework built upon a novel Compositional Hierarchical Graph that organizes molecular structure into four types of nodes across three semantic levels. By introducing a bond graph that operates in parallel with the atom graph, our arch"},"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":"2605.16088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T15:47:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ff634f42efc60a3a4cd2c929ee384b99aa7f47e5bab7662dc3fe24d4da1dbb6","abstract_canon_sha256":"33207c72977ae4c8c4be7c5a8813befc56e0c5d1c58301e0ac4d4cd7643eaf49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:52.129332Z","signature_b64":"eRq1sL1YLi4k/Wj5kfjSe3e89cXyFMIjNDr4cQorkKGrNYE0gslSh1ZOmfy0xll5krB6hluiUmy/7SLvTwWQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cfa77f1fa6e7052e2bc2cb8bc12b54bd8d59188a0493ae1a6c02159b7d9b3be","last_reissued_at":"2026-05-20T00:01:52.128236Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:52.128236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hou-Biao Li, Xiayu Liu, Zhengyi Lu","submitted_at":"2026-05-15T15:47:11Z","abstract_excerpt":"Self-supervised pretraining on molecular graphs has emerged as a promising approach for molecular property prediction, yet most existing methods operate at a single structural granularity and treat bond information as auxiliary edge attributes rather than as an independent semantic layer. In this work, we propose MolCHG, a multi-level self-supervised pretraining framework built upon a novel Compositional Hierarchical Graph that organizes molecular structure into four types of nodes across three semantic levels. By introducing a bond graph that operates in parallel with the atom graph, our arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16088","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/2605.16088/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:41.532181Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.499034Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"485e2337aec7410c9186a2f55be60b55af872eb646d517d65cdde78ce15e7f3f"},"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":"2605.16088","created_at":"2026-05-20T00:01:52.128343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16088v1","created_at":"2026-05-20T00:01:52.128343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16088","created_at":"2026-05-20T00:01:52.128343+00:00"},{"alias_kind":"pith_short_12","alias_value":"TT5HP4P2NZYF","created_at":"2026-05-20T00:01:52.128343+00:00"},{"alias_kind":"pith_short_16","alias_value":"TT5HP4P2NZYFFYV4","created_at":"2026-05-20T00:01:52.128343+00:00"},{"alias_kind":"pith_short_8","alias_value":"TT5HP4P2","created_at":"2026-05-20T00:01:52.128343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP","json":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP.json","graph_json":"https://pith.science/api/pith-number/TT5HP4P2NZYFFYV4FS4LYEVVJP/graph.json","events_json":"https://pith.science/api/pith-number/TT5HP4P2NZYFFYV4FS4LYEVVJP/events.json","paper":"https://pith.science/paper/TT5HP4P2"},"agent_actions":{"view_html":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP","download_json":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP.json","view_paper":"https://pith.science/paper/TT5HP4P2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16088&json=true","fetch_graph":"https://pith.science/api/pith-number/TT5HP4P2NZYFFYV4FS4LYEVVJP/graph.json","fetch_events":"https://pith.science/api/pith-number/TT5HP4P2NZYFFYV4FS4LYEVVJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP/action/storage_attestation","attest_author":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP/action/author_attestation","sign_citation":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP/action/citation_signature","submit_replication":"https://pith.science/pith/TT5HP4P2NZYFFYV4FS4LYEVVJP/action/replication_record"}},"created_at":"2026-05-20T00:01:52.128343+00:00","updated_at":"2026-05-20T00:01:52.128343+00:00"}