{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y5UK6PGGYRSFSBP4MO4HBI5NSE","short_pith_number":"pith:Y5UK6PGG","canonical_record":{"source":{"id":"2312.05757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T04:34:35Z","cross_cats_sorted":["cs.AI","cs.DL","cs.SI","stat.ME"],"title_canon_sha256":"54ec7cbed94b4dad67acf594f85d47049c1970f15f8ebe1a9840dd70819a46c5","abstract_canon_sha256":"5af52473565a90ffbf71e962d5159acffca832ac647dc7b0fd53112b9b513eae"},"schema_version":"1.0"},"canonical_sha256":"c768af3cc6c4645905fc63b870a3ad910ad9769e7603464c1291964526620b6a","source":{"kind":"arxiv","id":"2312.05757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05757","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05757v1","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05757","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"Y5UK6PGGYRSF","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"Y5UK6PGGYRSFSBP4","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"Y5UK6PGG","created_at":"2026-07-05T07:22:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y5UK6PGGYRSFSBP4MO4HBI5NSE","target":"record","payload":{"canonical_record":{"source":{"id":"2312.05757","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T04:34:35Z","cross_cats_sorted":["cs.AI","cs.DL","cs.SI","stat.ME"],"title_canon_sha256":"54ec7cbed94b4dad67acf594f85d47049c1970f15f8ebe1a9840dd70819a46c5","abstract_canon_sha256":"5af52473565a90ffbf71e962d5159acffca832ac647dc7b0fd53112b9b513eae"},"schema_version":"1.0"},"canonical_sha256":"c768af3cc6c4645905fc63b870a3ad910ad9769e7603464c1291964526620b6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:32.321368Z","signature_b64":"EtJh/Bj190j3u3sKj5nhxsVPeMoC1oi8EXZ15LPng3j/Ne+bAzx7VrcVsDulczHqOcA8nmCz3s5DC1kGWjoRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c768af3cc6c4645905fc63b870a3ad910ad9769e7603464c1291964526620b6a","last_reissued_at":"2026-07-05T07:22:32.320891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:32.320891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.05757","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":"2026-07-05T07:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xO/EQsqLaaNmw083Ta4v0wYirQIiWtBWrbA2cdXeknbnoHECg7LyX80bJ/HS4D1LVHejHH6h32T/Vx3aS45iBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:33:06.551146Z"},"content_sha256":"086162e5118bd012eddefb5a14231d7ef212bc80876e6f834afdbe27edc99b1d","schema_version":"1.0","event_id":"sha256:086162e5118bd012eddefb5a14231d7ef212bc80876e6f834afdbe27edc99b1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y5UK6PGGYRSFSBP4MO4HBI5NSE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.SI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Changlong Sun, Cui Huang, Kaisong Song, Tianqianjin Lin, Weikang Yuan, Xiaozhong Liu, Xurui Li, Yangyang Kang, Zhuoren Jiang","submitted_at":"2023-12-10T04:34:35Z","abstract_excerpt":"Heterogeneous graph neural networks have become popular in various domains. However, their generalizability and interpretability are limited due to the discrepancy between their inherent inference flows and human reasoning logic or underlying causal relationships for the learning problem. This study introduces a novel solution, HG-SCM (Heterogeneous Graph as Structural Causal Model). It can mimic the human perception and decision process through two key steps: constructing intelligible variables based on semantics derived from the graph schema and automatically learning task-level causal relat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05757","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/2312.05757/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":"2026-07-05T07:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zJ4iFt7nwdIpcJLq4pRnxhOeMrzIvnfhUYLETIDmOLzUzVpsoQcZK10iRntBSA4yKaWMRrgi6LGomhX7lBsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:33:06.551711Z"},"content_sha256":"af441a4578714c4135200ffee2acaedaa6749455377dbd475864715ce5754fcc","schema_version":"1.0","event_id":"sha256:af441a4578714c4135200ffee2acaedaa6749455377dbd475864715ce5754fcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE/bundle.json","state_url":"https://pith.science/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE/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":"2026-08-15T14:33:06Z","links":{"resolver":"https://pith.science/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE","bundle":"https://pith.science/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE/bundle.json","state":"https://pith.science/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5UK6PGGYRSFSBP4MO4HBI5NSE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y5UK6PGGYRSFSBP4MO4HBI5NSE","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":"5af52473565a90ffbf71e962d5159acffca832ac647dc7b0fd53112b9b513eae","cross_cats_sorted":["cs.AI","cs.DL","cs.SI","stat.ME"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T04:34:35Z","title_canon_sha256":"54ec7cbed94b4dad67acf594f85d47049c1970f15f8ebe1a9840dd70819a46c5"},"schema_version":"1.0","source":{"id":"2312.05757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05757","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05757v1","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05757","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"Y5UK6PGGYRSF","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"Y5UK6PGGYRSFSBP4","created_at":"2026-07-05T07:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"Y5UK6PGG","created_at":"2026-07-05T07:22:32Z"}],"graph_snapshots":[{"event_id":"sha256:af441a4578714c4135200ffee2acaedaa6749455377dbd475864715ce5754fcc","target":"graph","created_at":"2026-07-05T07:22:32Z","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/2312.05757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneous graph neural networks have become popular in various domains. However, their generalizability and interpretability are limited due to the discrepancy between their inherent inference flows and human reasoning logic or underlying causal relationships for the learning problem. This study introduces a novel solution, HG-SCM (Heterogeneous Graph as Structural Causal Model). It can mimic the human perception and decision process through two key steps: constructing intelligible variables based on semantics derived from the graph schema and automatically learning task-level causal relat","authors_text":"Changlong Sun, Cui Huang, Kaisong Song, Tianqianjin Lin, Weikang Yuan, Xiaozhong Liu, Xurui Li, Yangyang Kang, Zhuoren Jiang","cross_cats":["cs.AI","cs.DL","cs.SI","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T04:34:35Z","title":"Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05757","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":"sha256:086162e5118bd012eddefb5a14231d7ef212bc80876e6f834afdbe27edc99b1d","target":"record","created_at":"2026-07-05T07:22:32Z","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":"5af52473565a90ffbf71e962d5159acffca832ac647dc7b0fd53112b9b513eae","cross_cats_sorted":["cs.AI","cs.DL","cs.SI","stat.ME"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-10T04:34:35Z","title_canon_sha256":"54ec7cbed94b4dad67acf594f85d47049c1970f15f8ebe1a9840dd70819a46c5"},"schema_version":"1.0","source":{"id":"2312.05757","kind":"arxiv","version":1}},"canonical_sha256":"c768af3cc6c4645905fc63b870a3ad910ad9769e7603464c1291964526620b6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c768af3cc6c4645905fc63b870a3ad910ad9769e7603464c1291964526620b6a","first_computed_at":"2026-07-05T07:22:32.320891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:32.320891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EtJh/Bj190j3u3sKj5nhxsVPeMoC1oi8EXZ15LPng3j/Ne+bAzx7VrcVsDulczHqOcA8nmCz3s5DC1kGWjoRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:32.321368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:086162e5118bd012eddefb5a14231d7ef212bc80876e6f834afdbe27edc99b1d","sha256:af441a4578714c4135200ffee2acaedaa6749455377dbd475864715ce5754fcc"],"state_sha256":"979d0d065050bc8c7b6684871ec74f573946d75837673d6ada8ffd2a2c478222"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AaNlJdflOiud5IodRWlG02Pi6gC9OWA+AlMe2ASNiIi9dUoTUcyWQ1SwDORuwXPELN3zx1wTWClimoo6VPt5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:33:06.554963Z","bundle_sha256":"94063cb2b48a90580cc8d257525192260bde00c9bc8939628ac77d8a22874d5b"}}