{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MFCLUFMQTKP4TIJ3ZQPH7646OY","short_pith_number":"pith:MFCLUFMQ","schema_version":"1.0","canonical_sha256":"6144ba15909a9fc9a13bcc1e7ffb9e7631143ec17e49e64569b2a5008d639407","source":{"kind":"arxiv","id":"2409.01081","version":1},"attestation_state":"computed","paper":{"title":"Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Dingshuo Chen, Ding Wang, Guibin Zhang, Jeffrey Xu Yu, Liang Wang, Qiang Liu, Shu Wu, Yuyan Ni, Zhixun Li","submitted_at":"2024-09-02T09:06:04Z","abstract_excerpt":"With the emergence of various molecular tasks and massive datasets, how to perform efficient training has become an urgent yet under-explored issue in the area. Data pruning (DP), as an oft-stated approach to saving training burdens, filters out less influential samples to form a coreset for training. However, the increasing reliance on pretrained models for molecular tasks renders traditional in-domain DP methods incompatible. Therefore, we propose a Molecular data Pruning framework for enhanced Generalization (MolPeg), which focuses on the source-free data pruning scenario, where data prunin"},"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":"2409.01081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T09:06:04Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"88963098b816a701bbf390719d172f0e99e3fcd20eda6d0e6f46f87f0f7b5e2e","abstract_canon_sha256":"de4a8cc79cfe8705d87b0f9d49681a476de7683489f66bb79dd8b8dee82e5b86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:58.825167Z","signature_b64":"0w1thkuCW0f4H5CTF+kGNCclAfnPmoM7mSa5aoTS2/cM3JsdV+iMoNIEXE3PJrT0xH+Zizx0a5VJKpwAsqedBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6144ba15909a9fc9a13bcc1e7ffb9e7631143ec17e49e64569b2a5008d639407","last_reissued_at":"2026-07-05T09:01:58.824812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:58.824812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Dingshuo Chen, Ding Wang, Guibin Zhang, Jeffrey Xu Yu, Liang Wang, Qiang Liu, Shu Wu, Yuyan Ni, Zhixun Li","submitted_at":"2024-09-02T09:06:04Z","abstract_excerpt":"With the emergence of various molecular tasks and massive datasets, how to perform efficient training has become an urgent yet under-explored issue in the area. Data pruning (DP), as an oft-stated approach to saving training burdens, filters out less influential samples to form a coreset for training. However, the increasing reliance on pretrained models for molecular tasks renders traditional in-domain DP methods incompatible. Therefore, we propose a Molecular data Pruning framework for enhanced Generalization (MolPeg), which focuses on the source-free data pruning scenario, where data prunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01081","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/2409.01081/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":"2409.01081","created_at":"2026-07-05T09:01:58.824868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01081v1","created_at":"2026-07-05T09:01:58.824868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01081","created_at":"2026-07-05T09:01:58.824868+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFCLUFMQTKP4","created_at":"2026-07-05T09:01:58.824868+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFCLUFMQTKP4TIJ3","created_at":"2026-07-05T09:01:58.824868+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFCLUFMQ","created_at":"2026-07-05T09:01:58.824868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20903","citing_title":"Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY","json":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY.json","graph_json":"https://pith.science/api/pith-number/MFCLUFMQTKP4TIJ3ZQPH7646OY/graph.json","events_json":"https://pith.science/api/pith-number/MFCLUFMQTKP4TIJ3ZQPH7646OY/events.json","paper":"https://pith.science/paper/MFCLUFMQ"},"agent_actions":{"view_html":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY","download_json":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY.json","view_paper":"https://pith.science/paper/MFCLUFMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01081&json=true","fetch_graph":"https://pith.science/api/pith-number/MFCLUFMQTKP4TIJ3ZQPH7646OY/graph.json","fetch_events":"https://pith.science/api/pith-number/MFCLUFMQTKP4TIJ3ZQPH7646OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/action/storage_attestation","attest_author":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/action/author_attestation","sign_citation":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/action/citation_signature","submit_replication":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/action/replication_record"}},"created_at":"2026-07-05T09:01:58.824868+00:00","updated_at":"2026-07-05T09:01:58.824868+00:00"}