{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:N5RB3X4AOZ4T4QM2ZYKMEUITVO","short_pith_number":"pith:N5RB3X4A","canonical_record":{"source":{"id":"1809.06334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2018-09-17T17:06:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4de29d1963139c78a068c00575ced85913cfc30ba9c12152de0b1a38d83e65d9","abstract_canon_sha256":"e12fdaee28302d0d3b6b927c27e257a03af73a1b63b2837a1cdf4ec21db0fc6f"},"schema_version":"1.0"},"canonical_sha256":"6f621ddf8076793e419ace14c25113ab9fd6e25f0d9254ebf86373611d001d61","source":{"kind":"arxiv","id":"1809.06334","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06334","created_at":"2026-05-18T00:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06334v1","created_at":"2026-05-18T00:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06334","created_at":"2026-05-18T00:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"N5RB3X4AOZ4T","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"N5RB3X4AOZ4T4QM2","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"N5RB3X4A","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:N5RB3X4AOZ4T4QM2ZYKMEUITVO","target":"record","payload":{"canonical_record":{"source":{"id":"1809.06334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2018-09-17T17:06:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4de29d1963139c78a068c00575ced85913cfc30ba9c12152de0b1a38d83e65d9","abstract_canon_sha256":"e12fdaee28302d0d3b6b927c27e257a03af73a1b63b2837a1cdf4ec21db0fc6f"},"schema_version":"1.0"},"canonical_sha256":"6f621ddf8076793e419ace14c25113ab9fd6e25f0d9254ebf86373611d001d61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:34.991821Z","signature_b64":"Ap/xJPuG2WTEgld+JWQAfwMN8rxJ2b5OwQrPpPi7/+WvNrwArl4aecH4/oQEZwNaiyrchjEuP0dDgvMp2AWEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f621ddf8076793e419ace14c25113ab9fd6e25f0d9254ebf86373611d001d61","last_reissued_at":"2026-05-18T00:05:34.991330Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:34.991330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.06334","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":"2026-05-18T00:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDjM9CJqokZki2kyo4Q06oh+F+MPTgeD7yDW9s0+yMKy/Ost29Rd2dTsR9gYpHTWZ+fRe10EoGXxbDKShjrVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T14:26:48.432393Z"},"content_sha256":"1b2e75c4b6024ef534cb908da805005de9dd027a8604ce0a203fa7588675bb58","schema_version":"1.0","event_id":"sha256:1b2e75c4b6024ef534cb908da805005de9dd027a8604ce0a203fa7588675bb58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:N5RB3X4AOZ4T4QM2ZYKMEUITVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"physics.chem-ph","authors_text":"Clyde Fare, Edward O. Pyzer-Knapp, Lukas Turcani","submitted_at":"2018-09-17T17:06:06Z","abstract_excerpt":"Chemical representations derived from deep learning are emerging as a powerful tool in areas such as drug discovery and materials innovation. Currently, this methodology has three major limitations - the cost of representation generation, risk of inherited bias, and the requirement for large amounts of data. We propose the use of multi-task learning in tandem with transfer learning to address these limitations directly. In order to avoid introducing unknown bias into multi-task learning through the task selection itself, we calculate task similarity through pairwise task affinity, and use this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06334","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":""},"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":"2026-05-18T00:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1H1nZe5utCXEmyHbq3eScMJLrNW90ESl6SsGpOuo9hXcn4RfmqmACYUvYPO7PJc7iGNSsZyG+a48S9ZXPW1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T14:26:48.432743Z"},"content_sha256":"998b6bf878e1f16bfcb8915e4b4b7786cda0452c1c4c23b94fef3f11306fe2e7","schema_version":"1.0","event_id":"sha256:998b6bf878e1f16bfcb8915e4b4b7786cda0452c1c4c23b94fef3f11306fe2e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO/bundle.json","state_url":"https://pith.science/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO/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":"2026-06-22T14:26:48Z","links":{"resolver":"https://pith.science/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO","bundle":"https://pith.science/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO/bundle.json","state":"https://pith.science/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5RB3X4AOZ4T4QM2ZYKMEUITVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:N5RB3X4AOZ4T4QM2ZYKMEUITVO","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":"e12fdaee28302d0d3b6b927c27e257a03af73a1b63b2837a1cdf4ec21db0fc6f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2018-09-17T17:06:06Z","title_canon_sha256":"4de29d1963139c78a068c00575ced85913cfc30ba9c12152de0b1a38d83e65d9"},"schema_version":"1.0","source":{"id":"1809.06334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06334","created_at":"2026-05-18T00:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06334v1","created_at":"2026-05-18T00:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06334","created_at":"2026-05-18T00:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"N5RB3X4AOZ4T","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"N5RB3X4AOZ4T4QM2","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"N5RB3X4A","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:998b6bf878e1f16bfcb8915e4b4b7786cda0452c1c4c23b94fef3f11306fe2e7","target":"graph","created_at":"2026-05-18T00:05:34Z","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"},"paper":{"abstract_excerpt":"Chemical representations derived from deep learning are emerging as a powerful tool in areas such as drug discovery and materials innovation. Currently, this methodology has three major limitations - the cost of representation generation, risk of inherited bias, and the requirement for large amounts of data. We propose the use of multi-task learning in tandem with transfer learning to address these limitations directly. In order to avoid introducing unknown bias into multi-task learning through the task selection itself, we calculate task similarity through pairwise task affinity, and use this","authors_text":"Clyde Fare, Edward O. Pyzer-Knapp, Lukas Turcani","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2018-09-17T17:06:06Z","title":"Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06334","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":"sha256:1b2e75c4b6024ef534cb908da805005de9dd027a8604ce0a203fa7588675bb58","target":"record","created_at":"2026-05-18T00:05:34Z","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":"e12fdaee28302d0d3b6b927c27e257a03af73a1b63b2837a1cdf4ec21db0fc6f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2018-09-17T17:06:06Z","title_canon_sha256":"4de29d1963139c78a068c00575ced85913cfc30ba9c12152de0b1a38d83e65d9"},"schema_version":"1.0","source":{"id":"1809.06334","kind":"arxiv","version":1}},"canonical_sha256":"6f621ddf8076793e419ace14c25113ab9fd6e25f0d9254ebf86373611d001d61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f621ddf8076793e419ace14c25113ab9fd6e25f0d9254ebf86373611d001d61","first_computed_at":"2026-05-18T00:05:34.991330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:34.991330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ap/xJPuG2WTEgld+JWQAfwMN8rxJ2b5OwQrPpPi7/+WvNrwArl4aecH4/oQEZwNaiyrchjEuP0dDgvMp2AWEAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:34.991821Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.06334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b2e75c4b6024ef534cb908da805005de9dd027a8604ce0a203fa7588675bb58","sha256:998b6bf878e1f16bfcb8915e4b4b7786cda0452c1c4c23b94fef3f11306fe2e7"],"state_sha256":"aa3ce77f8d2b0caeaaa8f0769a9f4252f2a8b0ce09f4a95f32ec8569a5cf4240"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C+oLwCItYTu2wIfHSrj65/+jXGp+Ziin2RZ4xlzQtEd5bURZs5yCIlonSxzmDvUcLMD45x8vEuu3xAdn0o2mDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T14:26:48.434773Z","bundle_sha256":"afcfffe1118644e938a9ff8616028437806ce20ffe4a700ffe8d0bbf6e509015"}}