{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MFCLUFMQTKP4TIJ3ZQPH7646OY","short_pith_number":"pith:MFCLUFMQ","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"},"canonical_sha256":"6144ba15909a9fc9a13bcc1e7ffb9e7631143ec17e49e64569b2a5008d639407","source":{"kind":"arxiv","id":"2409.01081","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01081","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01081v1","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01081","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"MFCLUFMQTKP4","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"MFCLUFMQTKP4TIJ3","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"MFCLUFMQ","created_at":"2026-07-05T09:01:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MFCLUFMQTKP4TIJ3ZQPH7646OY","target":"record","payload":{"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"},"canonical_sha256":"6144ba15909a9fc9a13bcc1e7ffb9e7631143ec17e49e64569b2a5008d639407","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"},"source_kind":"arxiv","source_id":"2409.01081","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmpHYNRdg8Opom05x2zZMtrlclrOCMuCJhw7vzNpl1gs0HgUOREXZ9HfUPArBVXVhUtjU1H9/200Oj5B4/y6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:21:59.633443Z"},"content_sha256":"140d7791bf8b1a723db0ce915110e049a3a08e56f684179c09f64d0148f13c24","schema_version":"1.0","event_id":"sha256:140d7791bf8b1a723db0ce915110e049a3a08e56f684179c09f64d0148f13c24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MFCLUFMQTKP4TIJ3ZQPH7646OY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wd0VeAA2PZYc9p6PARVtEtqhcToKtCEETpxzt3sZ1ZrpfxVh28c63JErYmY0wupHSH9k1a/v2lMYRw0yq3zODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:21:59.633950Z"},"content_sha256":"3831483f7286ab4a6562cdbffa36c67154fea85f338235ba4e76331bb7921650","schema_version":"1.0","event_id":"sha256:3831483f7286ab4a6562cdbffa36c67154fea85f338235ba4e76331bb7921650"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/bundle.json","state_url":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T09:21:59Z","links":{"resolver":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY","bundle":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/bundle.json","state":"https://pith.science/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFCLUFMQTKP4TIJ3ZQPH7646OY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MFCLUFMQTKP4TIJ3ZQPH7646OY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"de4a8cc79cfe8705d87b0f9d49681a476de7683489f66bb79dd8b8dee82e5b86","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T09:06:04Z","title_canon_sha256":"88963098b816a701bbf390719d172f0e99e3fcd20eda6d0e6f46f87f0f7b5e2e"},"schema_version":"1.0","source":{"id":"2409.01081","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01081","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01081v1","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01081","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"MFCLUFMQTKP4","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"MFCLUFMQTKP4TIJ3","created_at":"2026-07-05T09:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"MFCLUFMQ","created_at":"2026-07-05T09:01:58Z"}],"graph_snapshots":[{"event_id":"sha256:3831483f7286ab4a6562cdbffa36c67154fea85f338235ba4e76331bb7921650","target":"graph","created_at":"2026-07-05T09:01:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.01081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dingshuo Chen, Ding Wang, Guibin Zhang, Jeffrey Xu Yu, Liang Wang, Qiang Liu, Shu Wu, Yuyan Ni, Zhixun Li","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T09:06:04Z","title":"Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01081","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:140d7791bf8b1a723db0ce915110e049a3a08e56f684179c09f64d0148f13c24","target":"record","created_at":"2026-07-05T09:01:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"de4a8cc79cfe8705d87b0f9d49681a476de7683489f66bb79dd8b8dee82e5b86","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T09:06:04Z","title_canon_sha256":"88963098b816a701bbf390719d172f0e99e3fcd20eda6d0e6f46f87f0f7b5e2e"},"schema_version":"1.0","source":{"id":"2409.01081","kind":"arxiv","version":1}},"canonical_sha256":"6144ba15909a9fc9a13bcc1e7ffb9e7631143ec17e49e64569b2a5008d639407","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6144ba15909a9fc9a13bcc1e7ffb9e7631143ec17e49e64569b2a5008d639407","first_computed_at":"2026-07-05T09:01:58.824812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:58.824812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0w1thkuCW0f4H5CTF+kGNCclAfnPmoM7mSa5aoTS2/cM3JsdV+iMoNIEXE3PJrT0xH+Zizx0a5VJKpwAsqedBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:58.825167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01081","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:140d7791bf8b1a723db0ce915110e049a3a08e56f684179c09f64d0148f13c24","sha256:3831483f7286ab4a6562cdbffa36c67154fea85f338235ba4e76331bb7921650"],"state_sha256":"8cefe076ef1c6786b267c19628d558f8273fced4e9e614ea56664911250b7079"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALh4K3AYDMS7N6Q27wQEBhJY/ZB1BMidHSCk2HloS07mJPB25VLlCzuHalougptGNiLZ8adVQhsjp5OIfPFZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:21:59.638873Z","bundle_sha256":"fab11ad9a2f432088a54f85af7a31903e616bb89b8f50615f0d03c8087d5efad"}}