{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EQPQOEMGUBX7BGVPEMFHSUXS3T","short_pith_number":"pith:EQPQOEMG","canonical_record":{"source":{"id":"2103.12983","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-24T04:38:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5501cb5d762b1279c7583c14e866feed053f4ce28aeb0847dcfaf41bef2dde6d","abstract_canon_sha256":"e1a378f9309e4b8bdb2f31c9b811080fa29de7de592c4a347f3493a6ad014c29"},"schema_version":"1.0"},"canonical_sha256":"241f071186a06ff09aaf230a7952f2dcd2aa6083a94e77109f59994fcb3078d1","source":{"kind":"arxiv","id":"2103.12983","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12983","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12983v2","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12983","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"pith_short_12","alias_value":"EQPQOEMGUBX7","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"pith_short_16","alias_value":"EQPQOEMGUBX7BGVP","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"pith_short_8","alias_value":"EQPQOEMG","created_at":"2026-07-05T02:45:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EQPQOEMGUBX7BGVPEMFHSUXS3T","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12983","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-24T04:38:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5501cb5d762b1279c7583c14e866feed053f4ce28aeb0847dcfaf41bef2dde6d","abstract_canon_sha256":"e1a378f9309e4b8bdb2f31c9b811080fa29de7de592c4a347f3493a6ad014c29"},"schema_version":"1.0"},"canonical_sha256":"241f071186a06ff09aaf230a7952f2dcd2aa6083a94e77109f59994fcb3078d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:37.157004Z","signature_b64":"7deGi8YoX8TpfcltqiRa4zSMUgB0awWqCC/P0/t6w86wB40m6vCSjPdHRvnwYWknFyEhvvCAKJMbr//IZsnEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241f071186a06ff09aaf230a7952f2dcd2aa6083a94e77109f59994fcb3078d1","last_reissued_at":"2026-07-05T02:45:37.156521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:37.156521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12983","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":"2026-07-05T02:45:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efyo+PWluiifD1GSMog1FCLOHpDm9IiSPtmxL1kP5fXjCZUXDQpNQJbn1kIOe9/WUDGVM0OA4vvAQM0k81wgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:45:27.574956Z"},"content_sha256":"6c8c142d86311845b293c31ca53a0259d7668f13367889a4eefa1e02316b33db","schema_version":"1.0","event_id":"sha256:6c8c142d86311845b293c31ca53a0259d7668f13367889a4eefa1e02316b33db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EQPQOEMGUBX7BGVPEMFHSUXS3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Thin Nguyen, Thomas P Quinn, Tri Minh Nguyen, Truyen Tran","submitted_at":"2021-03-24T04:38:38Z","abstract_excerpt":"Motivation: Many high-performance DTA models have been proposed, but they are mostly black-box and thus lack human interpretability. Explainable AI (XAI) can make DTA models more trustworthy, and can also enable scientists to distill biological knowledge from the models. Counterfactual explanation is one popular approach to explaining the behaviour of a deep neural network, which works by systematically answering the question \"How would the model output change if the inputs were changed in this way?\". Most counterfactual explanation methods only operate on single input data. It remains an open"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12983","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/2103.12983/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":"2026-07-05T02:45:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49hGhCYVlDDHYs3rPo9Jk3JnGub8FjJ6uGa+zhW5TLQKb9DNSB3Y+nlZXd7pRV0poyXM0ehT9ZdWbZWU3ie6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:45:27.575537Z"},"content_sha256":"916d7a5a1eb3bbee3cbc3fc7022546ef217135deb9a19ea9139a91fb797df3b3","schema_version":"1.0","event_id":"sha256:916d7a5a1eb3bbee3cbc3fc7022546ef217135deb9a19ea9139a91fb797df3b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T/bundle.json","state_url":"https://pith.science/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T/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":"2026-08-03T15:45:27Z","links":{"resolver":"https://pith.science/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T","bundle":"https://pith.science/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T/bundle.json","state":"https://pith.science/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQPQOEMGUBX7BGVPEMFHSUXS3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EQPQOEMGUBX7BGVPEMFHSUXS3T","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":"e1a378f9309e4b8bdb2f31c9b811080fa29de7de592c4a347f3493a6ad014c29","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-24T04:38:38Z","title_canon_sha256":"5501cb5d762b1279c7583c14e866feed053f4ce28aeb0847dcfaf41bef2dde6d"},"schema_version":"1.0","source":{"id":"2103.12983","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12983","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12983v2","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12983","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"pith_short_12","alias_value":"EQPQOEMGUBX7","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"pith_short_16","alias_value":"EQPQOEMGUBX7BGVP","created_at":"2026-07-05T02:45:37Z"},{"alias_kind":"pith_short_8","alias_value":"EQPQOEMG","created_at":"2026-07-05T02:45:37Z"}],"graph_snapshots":[{"event_id":"sha256:916d7a5a1eb3bbee3cbc3fc7022546ef217135deb9a19ea9139a91fb797df3b3","target":"graph","created_at":"2026-07-05T02:45:37Z","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/2103.12983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivation: Many high-performance DTA models have been proposed, but they are mostly black-box and thus lack human interpretability. Explainable AI (XAI) can make DTA models more trustworthy, and can also enable scientists to distill biological knowledge from the models. Counterfactual explanation is one popular approach to explaining the behaviour of a deep neural network, which works by systematically answering the question \"How would the model output change if the inputs were changed in this way?\". Most counterfactual explanation methods only operate on single input data. It remains an open","authors_text":"Thin Nguyen, Thomas P Quinn, Tri Minh Nguyen, Truyen Tran","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-24T04:38:38Z","title":"Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12983","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":"sha256:6c8c142d86311845b293c31ca53a0259d7668f13367889a4eefa1e02316b33db","target":"record","created_at":"2026-07-05T02:45:37Z","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":"e1a378f9309e4b8bdb2f31c9b811080fa29de7de592c4a347f3493a6ad014c29","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-24T04:38:38Z","title_canon_sha256":"5501cb5d762b1279c7583c14e866feed053f4ce28aeb0847dcfaf41bef2dde6d"},"schema_version":"1.0","source":{"id":"2103.12983","kind":"arxiv","version":2}},"canonical_sha256":"241f071186a06ff09aaf230a7952f2dcd2aa6083a94e77109f59994fcb3078d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"241f071186a06ff09aaf230a7952f2dcd2aa6083a94e77109f59994fcb3078d1","first_computed_at":"2026-07-05T02:45:37.156521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:37.156521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7deGi8YoX8TpfcltqiRa4zSMUgB0awWqCC/P0/t6w86wB40m6vCSjPdHRvnwYWknFyEhvvCAKJMbr//IZsnEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:37.157004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12983","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c8c142d86311845b293c31ca53a0259d7668f13367889a4eefa1e02316b33db","sha256:916d7a5a1eb3bbee3cbc3fc7022546ef217135deb9a19ea9139a91fb797df3b3"],"state_sha256":"6ee7593bf5d253899ea5584705c9d34368ab7e840b71890135f1a05e75255f72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfoETyyCIxI57CcWMNVAichfx+W3Qx+nOPDOgT4Eu02HkRZVKxTyM2D/35fL773CG1WzVJw+pWCKECCdqe0aAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:45:27.579655Z","bundle_sha256":"a8d673d134bb90294b5c97c6b030a3a82ff156af549e3944474e701e498c7604"}}