{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZHWAMYYZVLBXMGPSN6RPFZBQIM","short_pith_number":"pith:ZHWAMYYZ","canonical_record":{"source":{"id":"2410.16122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-10-21T15:50:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9e9e8f98ee58b8bfa9911a097cccdf8484f131b6f4133c55bebb6e819ad44177","abstract_canon_sha256":"73d31db69231560e1ef0e724ab01aca8ff96e8923b828cd66b9b1bde92933b6b"},"schema_version":"1.0"},"canonical_sha256":"c9ec066319aac37619f26fa2f2e4304304afb86ec5b25aec96a0fab362ad9a49","source":{"kind":"arxiv","id":"2410.16122","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16122","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16122v2","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16122","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZHWAMYYZVLBX","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZHWAMYYZVLBXMGPS","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZHWAMYYZ","created_at":"2026-07-05T10:57:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZHWAMYYZVLBXMGPSN6RPFZBQIM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-10-21T15:50:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9e9e8f98ee58b8bfa9911a097cccdf8484f131b6f4133c55bebb6e819ad44177","abstract_canon_sha256":"73d31db69231560e1ef0e724ab01aca8ff96e8923b828cd66b9b1bde92933b6b"},"schema_version":"1.0"},"canonical_sha256":"c9ec066319aac37619f26fa2f2e4304304afb86ec5b25aec96a0fab362ad9a49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:20.505160Z","signature_b64":"85DAiASW3ySShH9zWYgPN/GIuHcHDY9YOcjMVBrJIdvn2Q3ecm5WsYmtqbhLqgoZPLfdViZrBlry/IZecvqRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9ec066319aac37619f26fa2f2e4304304afb86ec5b25aec96a0fab362ad9a49","last_reissued_at":"2026-07-05T10:57:20.504648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:20.504648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8a8vaU3e9JbOdD96BPy5aXfJHBDUTZAvaUOz9lLI/ZB9PcRM3TZ9L/TAM35VPiS5vJ7tx2fruiiSWUGy7Pb/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:24:18.224627Z"},"content_sha256":"4a85a534c226aa243bb2a6ec7b69daf64cb471e609b87983067c76972f500684","schema_version":"1.0","event_id":"sha256:4a85a534c226aa243bb2a6ec7b69daf64cb471e609b87983067c76972f500684"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZHWAMYYZVLBXMGPSN6RPFZBQIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integer linear programming for unsupervised training set selection in molecular machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Clemence Corminboeuf, Friedrich Eisenbrand, Jan Weinreich, Ksenia R. Briling, Matthieu Haeberle, Puck van Gerwen, Ruben Laplaza","submitted_at":"2024-10-21T15:50:04Z","abstract_excerpt":"Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning applied to chemistry, we demonstrate the relevance of an ILP formulation to select molecular training sets for predictions of size-extensive properties. We show that our algorithm outperforms existing unsupervised training set selection approaches, especially when predicting properties of molecules larger than those present in the training set. We argue that the reason for the improved perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16122","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/2410.16122/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":"2026-07-05T10:57:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KVM71J01/mJ3GRROoUswbBg1v1QAVk7EWx+evzsDcepX4En+BYeKR2v1GEGQ+Q77DRgN59z2FtgSRaGLbkYUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T19:24:18.224997Z"},"content_sha256":"4044e618b59a53e927fee1d862d51d7a769a401697a131feb22671471fbdc263","schema_version":"1.0","event_id":"sha256:4044e618b59a53e927fee1d862d51d7a769a401697a131feb22671471fbdc263"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM/bundle.json","state_url":"https://pith.science/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM/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":"2026-07-13T19:24:18Z","links":{"resolver":"https://pith.science/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM","bundle":"https://pith.science/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM/bundle.json","state":"https://pith.science/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHWAMYYZVLBXMGPSN6RPFZBQIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZHWAMYYZVLBXMGPSN6RPFZBQIM","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":"73d31db69231560e1ef0e724ab01aca8ff96e8923b828cd66b9b1bde92933b6b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-10-21T15:50:04Z","title_canon_sha256":"9e9e8f98ee58b8bfa9911a097cccdf8484f131b6f4133c55bebb6e819ad44177"},"schema_version":"1.0","source":{"id":"2410.16122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16122","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16122v2","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16122","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZHWAMYYZVLBX","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZHWAMYYZVLBXMGPS","created_at":"2026-07-05T10:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZHWAMYYZ","created_at":"2026-07-05T10:57:20Z"}],"graph_snapshots":[{"event_id":"sha256:4044e618b59a53e927fee1d862d51d7a769a401697a131feb22671471fbdc263","target":"graph","created_at":"2026-07-05T10:57:20Z","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/2410.16122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning applied to chemistry, we demonstrate the relevance of an ILP formulation to select molecular training sets for predictions of size-extensive properties. We show that our algorithm outperforms existing unsupervised training set selection approaches, especially when predicting properties of molecules larger than those present in the training set. We argue that the reason for the improved perfor","authors_text":"Clemence Corminboeuf, Friedrich Eisenbrand, Jan Weinreich, Ksenia R. Briling, Matthieu Haeberle, Puck van Gerwen, Ruben Laplaza","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-10-21T15:50:04Z","title":"Integer linear programming for unsupervised training set selection in molecular machine learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16122","kind":"arxiv","version":2},"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":"sha256:4a85a534c226aa243bb2a6ec7b69daf64cb471e609b87983067c76972f500684","target":"record","created_at":"2026-07-05T10:57:20Z","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":"73d31db69231560e1ef0e724ab01aca8ff96e8923b828cd66b9b1bde92933b6b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2024-10-21T15:50:04Z","title_canon_sha256":"9e9e8f98ee58b8bfa9911a097cccdf8484f131b6f4133c55bebb6e819ad44177"},"schema_version":"1.0","source":{"id":"2410.16122","kind":"arxiv","version":2}},"canonical_sha256":"c9ec066319aac37619f26fa2f2e4304304afb86ec5b25aec96a0fab362ad9a49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9ec066319aac37619f26fa2f2e4304304afb86ec5b25aec96a0fab362ad9a49","first_computed_at":"2026-07-05T10:57:20.504648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:20.504648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"85DAiASW3ySShH9zWYgPN/GIuHcHDY9YOcjMVBrJIdvn2Q3ecm5WsYmtqbhLqgoZPLfdViZrBlry/IZecvqRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:20.505160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a85a534c226aa243bb2a6ec7b69daf64cb471e609b87983067c76972f500684","sha256:4044e618b59a53e927fee1d862d51d7a769a401697a131feb22671471fbdc263"],"state_sha256":"c7d2a4bdbdfff4cfe0fe4c2626a10ba9102bbaf1e9222a975de1e41185b4a575"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Il6YRL34UQXqsKPiuuEGvxOldig6wd1O3WOafrHJ9d8My3rgTAPAdj8mDQOlnsqf4UY8FxJ7SDzME7oDWUDcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T19:24:18.227175Z","bundle_sha256":"d30619df87650f1b6d975f477704f1856cee85b0a17bffb153bc0982406a1b41"}}