{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7D7WCVAFNYXKSWSWAPLBH2YR6D","short_pith_number":"pith:7D7WCVAF","canonical_record":{"source":{"id":"1803.07710","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-21T01:09:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"08542c026f35410b805cc191665f1820477ca79188268b5669ff27399470f1b0","abstract_canon_sha256":"0ec2a875b0e0cc020fec318bf67d3e0932f956e9bd486688ace28be51b6b87a7"},"schema_version":"1.0"},"canonical_sha256":"f8ff6154056e2ea95a5603d613eb11f0c9fc2c00b6bed7607ede56e9d07f7dc0","source":{"kind":"arxiv","id":"1803.07710","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07710","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07710v5","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07710","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"7D7WCVAFNYXK","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7D7WCVAFNYXKSWSW","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7D7WCVAF","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7D7WCVAFNYXKSWSWAPLBH2YR6D","target":"record","payload":{"canonical_record":{"source":{"id":"1803.07710","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-21T01:09:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"08542c026f35410b805cc191665f1820477ca79188268b5669ff27399470f1b0","abstract_canon_sha256":"0ec2a875b0e0cc020fec318bf67d3e0932f956e9bd486688ace28be51b6b87a7"},"schema_version":"1.0"},"canonical_sha256":"f8ff6154056e2ea95a5603d613eb11f0c9fc2c00b6bed7607ede56e9d07f7dc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:08.819234Z","signature_b64":"mp38n4jB1BYu7pV5KBQ/wpq6eVciYMZHi98zI7BOKevKAG/AIkGoxxK7sYS/tPsOX16hFcZ2kPKvuHErTVLXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8ff6154056e2ea95a5603d613eb11f0c9fc2c00b6bed7607ede56e9d07f7dc0","last_reissued_at":"2026-05-17T23:42:08.818614Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:08.818614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.07710","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qdFJtig29kxyrUj/zZ5OQgojHV7VbWRpYFg0rTuPVPdhJINqABcSoy4+rbFqy2DDFlZ27N7ztvfAxU4aO/5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:05:18.718607Z"},"content_sha256":"b2dd0e213e4dde208e959f0613c785f36e4a43ac13229383f1aa9799ef2a2368","schema_version":"1.0","event_id":"sha256:b2dd0e213e4dde208e959f0613c785f36e4a43ac13229383f1aa9799ef2a2368"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7D7WCVAFNYXKSWSWAPLBH2YR6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference in Probabilistic Graphical Models by Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ethan Fetaya, KiJung Yoon, Lisa Zhang, Raquel Urtasun, Renjie Liao, Richard Zemel, Xaq Pitkow, Yuwen Xiong","submitted_at":"2018-03-21T01:09:07Z","abstract_excerpt":"A fundamental computation for statistical inference and accurate decision-making is to compute the marginal probabilities or most probable states of task-relevant variables. Probabilistic graphical models can efficiently represent the structure of such complex data, but performing these inferences is generally difficult. Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops. Here we use Graph Neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07710","kind":"arxiv","version":5},"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":"2026-05-17T23:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K6NytkmrW98Tyw2C5k0PEJoFg2qUe9VJNzLMQb3fKPNvE4J61mIRZRtaUhsv7ZGYn7kD64SkBx7YdZSq5JRzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:05:18.719294Z"},"content_sha256":"583fc81e2a3bd34d1a2141a1d6e0c0f4e237642422d7217406e7e01aff7e9c90","schema_version":"1.0","event_id":"sha256:583fc81e2a3bd34d1a2141a1d6e0c0f4e237642422d7217406e7e01aff7e9c90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D/bundle.json","state_url":"https://pith.science/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D/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":"2026-05-25T20:05:18Z","links":{"resolver":"https://pith.science/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D","bundle":"https://pith.science/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D/bundle.json","state":"https://pith.science/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7D7WCVAFNYXKSWSWAPLBH2YR6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7D7WCVAFNYXKSWSWAPLBH2YR6D","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":"0ec2a875b0e0cc020fec318bf67d3e0932f956e9bd486688ace28be51b6b87a7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-21T01:09:07Z","title_canon_sha256":"08542c026f35410b805cc191665f1820477ca79188268b5669ff27399470f1b0"},"schema_version":"1.0","source":{"id":"1803.07710","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07710","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07710v5","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07710","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"7D7WCVAFNYXK","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7D7WCVAFNYXKSWSW","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7D7WCVAF","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:583fc81e2a3bd34d1a2141a1d6e0c0f4e237642422d7217406e7e01aff7e9c90","target":"graph","created_at":"2026-05-17T23:42:08Z","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":"A fundamental computation for statistical inference and accurate decision-making is to compute the marginal probabilities or most probable states of task-relevant variables. Probabilistic graphical models can efficiently represent the structure of such complex data, but performing these inferences is generally difficult. Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops. Here we use Graph Neural","authors_text":"Ethan Fetaya, KiJung Yoon, Lisa Zhang, Raquel Urtasun, Renjie Liao, Richard Zemel, Xaq Pitkow, Yuwen Xiong","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-21T01:09:07Z","title":"Inference in Probabilistic Graphical Models by Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07710","kind":"arxiv","version":5},"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:b2dd0e213e4dde208e959f0613c785f36e4a43ac13229383f1aa9799ef2a2368","target":"record","created_at":"2026-05-17T23:42:08Z","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":"0ec2a875b0e0cc020fec318bf67d3e0932f956e9bd486688ace28be51b6b87a7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-21T01:09:07Z","title_canon_sha256":"08542c026f35410b805cc191665f1820477ca79188268b5669ff27399470f1b0"},"schema_version":"1.0","source":{"id":"1803.07710","kind":"arxiv","version":5}},"canonical_sha256":"f8ff6154056e2ea95a5603d613eb11f0c9fc2c00b6bed7607ede56e9d07f7dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8ff6154056e2ea95a5603d613eb11f0c9fc2c00b6bed7607ede56e9d07f7dc0","first_computed_at":"2026-05-17T23:42:08.818614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:08.818614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mp38n4jB1BYu7pV5KBQ/wpq6eVciYMZHi98zI7BOKevKAG/AIkGoxxK7sYS/tPsOX16hFcZ2kPKvuHErTVLXBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:08.819234Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.07710","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2dd0e213e4dde208e959f0613c785f36e4a43ac13229383f1aa9799ef2a2368","sha256:583fc81e2a3bd34d1a2141a1d6e0c0f4e237642422d7217406e7e01aff7e9c90"],"state_sha256":"b2a2a1cfd775ac6fdf829057b807cdb4af74d82258eae086e0896069e657bbfd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4zF9c4ZuuDvdTlDvFu+vzLbB66tXy4Iv4526Lv4Ltt1wWD9B7deswGxIv8hUwmlrvvVPBEwBfMENsw5+YWqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:05:18.723093Z","bundle_sha256":"ff2c5eebfc6a6afe585fa5c7d1ab46f82f33c824df35975c7a40b5b814264497"}}