{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WYSIB36H2WHFK62KZGEEHFQHDI","short_pith_number":"pith:WYSIB36H","canonical_record":{"source":{"id":"1807.01985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:03:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"11e2e96fb8361cee5639090591dc88ad8ca17d63a21d57b5fb91302313f48550","abstract_canon_sha256":"a3c9ab92caf9315ee67feea7b8c7930882ce9324aa12ba0b01d1b055de51eff0"},"schema_version":"1.0"},"canonical_sha256":"b62480efc7d58e557b4ac9884396071a13978f531556beb3c5916a6bd43d7161","source":{"kind":"arxiv","id":"1807.01985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01985","created_at":"2026-05-18T00:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01985v1","created_at":"2026-05-18T00:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01985","created_at":"2026-05-18T00:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"WYSIB36H2WHF","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WYSIB36H2WHFK62K","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WYSIB36H","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WYSIB36H2WHFK62KZGEEHFQHDI","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01985","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:03:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"11e2e96fb8361cee5639090591dc88ad8ca17d63a21d57b5fb91302313f48550","abstract_canon_sha256":"a3c9ab92caf9315ee67feea7b8c7930882ce9324aa12ba0b01d1b055de51eff0"},"schema_version":"1.0"},"canonical_sha256":"b62480efc7d58e557b4ac9884396071a13978f531556beb3c5916a6bd43d7161","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:24.560391Z","signature_b64":"iTK9CZ2QXqMtnL16oS2FXaB1mjyI2UbawkDTVZiacg3ef5GQqG6rXHLHJtI8LXApoKdZYmRDXpCUTL4vijLeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b62480efc7d58e557b4ac9884396071a13978f531556beb3c5916a6bd43d7161","last_reissued_at":"2026-05-18T00:11:24.559776Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:24.559776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01985","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":"2026-05-18T00:11:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVndIJMWB2+yYjQr6U3Y6oxFtKrO9W64LT/dilF59R07A/YcSxst7SSFXBRBY5TF7Cd0ckDcsXXzgq/O/sIkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:03:00.097458Z"},"content_sha256":"2dbe679cc74bf1c8198275db7d9ee36d1aa0a3853dbe110b70985a63919cebe0","schema_version":"1.0","event_id":"sha256:2dbe679cc74bf1c8198275db7d9ee36d1aa0a3853dbe110b70985a63919cebe0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WYSIB36H2WHFK62KZGEEHFQHDI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BayesGrad: Explaining Predictions of Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hirotaka Akita, Hisashi Kashima, Kosuke Nakago, Shin-ichi Maeda, Tomoki Komatsu, Yohei Sugawara, Yukino Baba","submitted_at":"2018-07-04T14:03:37Z","abstract_excerpt":"Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: \"how do we explain the predictions of graph convolutional networks?\" A possible approach to answer this question is to visualize evidence substructures responsible for the predictions. For chemical property prediction tasks, the sample size of the training data is often small and/or a label imbalance problem occurs, where a few samples belong to a single class and the majority of samples belong to the other classes. This can lead to uncertainty r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01985","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":"2026-05-18T00:11:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50U9/co4Z0fHX4aUdXMAZCnikl5MT/Re1ei8aGi6auZ3Bbl84u0Dqoo5x5rlBlo6IkPUuyH+eglOm2PGyh6nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:03:00.098111Z"},"content_sha256":"c36c0aab06fa43cffae50fecf3ecd72f72a8487489bf889b129a9150fc45df3c","schema_version":"1.0","event_id":"sha256:c36c0aab06fa43cffae50fecf3ecd72f72a8487489bf889b129a9150fc45df3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WYSIB36H2WHFK62KZGEEHFQHDI/bundle.json","state_url":"https://pith.science/pith/WYSIB36H2WHFK62KZGEEHFQHDI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WYSIB36H2WHFK62KZGEEHFQHDI/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":"2026-05-25T21:03:00Z","links":{"resolver":"https://pith.science/pith/WYSIB36H2WHFK62KZGEEHFQHDI","bundle":"https://pith.science/pith/WYSIB36H2WHFK62KZGEEHFQHDI/bundle.json","state":"https://pith.science/pith/WYSIB36H2WHFK62KZGEEHFQHDI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WYSIB36H2WHFK62KZGEEHFQHDI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WYSIB36H2WHFK62KZGEEHFQHDI","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":"a3c9ab92caf9315ee67feea7b8c7930882ce9324aa12ba0b01d1b055de51eff0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:03:37Z","title_canon_sha256":"11e2e96fb8361cee5639090591dc88ad8ca17d63a21d57b5fb91302313f48550"},"schema_version":"1.0","source":{"id":"1807.01985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01985","created_at":"2026-05-18T00:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01985v1","created_at":"2026-05-18T00:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01985","created_at":"2026-05-18T00:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"WYSIB36H2WHF","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WYSIB36H2WHFK62K","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WYSIB36H","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:c36c0aab06fa43cffae50fecf3ecd72f72a8487489bf889b129a9150fc45df3c","target":"graph","created_at":"2026-05-18T00:11:24Z","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":"Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: \"how do we explain the predictions of graph convolutional networks?\" A possible approach to answer this question is to visualize evidence substructures responsible for the predictions. For chemical property prediction tasks, the sample size of the training data is often small and/or a label imbalance problem occurs, where a few samples belong to a single class and the majority of samples belong to the other classes. This can lead to uncertainty r","authors_text":"Hirotaka Akita, Hisashi Kashima, Kosuke Nakago, Shin-ichi Maeda, Tomoki Komatsu, Yohei Sugawara, Yukino Baba","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:03:37Z","title":"BayesGrad: Explaining Predictions of Graph Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01985","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":"sha256:2dbe679cc74bf1c8198275db7d9ee36d1aa0a3853dbe110b70985a63919cebe0","target":"record","created_at":"2026-05-18T00:11:24Z","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":"a3c9ab92caf9315ee67feea7b8c7930882ce9324aa12ba0b01d1b055de51eff0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T14:03:37Z","title_canon_sha256":"11e2e96fb8361cee5639090591dc88ad8ca17d63a21d57b5fb91302313f48550"},"schema_version":"1.0","source":{"id":"1807.01985","kind":"arxiv","version":1}},"canonical_sha256":"b62480efc7d58e557b4ac9884396071a13978f531556beb3c5916a6bd43d7161","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b62480efc7d58e557b4ac9884396071a13978f531556beb3c5916a6bd43d7161","first_computed_at":"2026-05-18T00:11:24.559776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:24.559776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iTK9CZ2QXqMtnL16oS2FXaB1mjyI2UbawkDTVZiacg3ef5GQqG6rXHLHJtI8LXApoKdZYmRDXpCUTL4vijLeBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:24.560391Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dbe679cc74bf1c8198275db7d9ee36d1aa0a3853dbe110b70985a63919cebe0","sha256:c36c0aab06fa43cffae50fecf3ecd72f72a8487489bf889b129a9150fc45df3c"],"state_sha256":"66da1f7b5aee7ab085286cb1700bbd497b01258e621ca39d59e5363ccd745790"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EvV9wL3m86pxxnDK80nnHa02FU38t8xY1UmWdiTQ+eOoE14uLzPnnZNbhwc01ARssXR2GBHwe1GrIi4Z3dXcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:03:00.101297Z","bundle_sha256":"fa12eee07139bf7b9c97153d0e7af12a1df5c7ad14ce1482af812a956d9366ca"}}