{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:A6NMETRTPD377BXBVYWW66FK7P","short_pith_number":"pith:A6NMETRT","canonical_record":{"source":{"id":"1710.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T16:31:24Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"93e2b253e34667bd97984268c7b8f8f7cb4b9be15ecd757fa3bebd4a04341787","abstract_canon_sha256":"080e56c7f6455f654c88d5e112b1617b1883c46c75d7433f4f868ed0456e1bc6"},"schema_version":"1.0"},"canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","source":{"kind":"arxiv","id":"1710.11052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11052","created_at":"2026-05-18T00:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11052v1","created_at":"2026-05-18T00:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11052","created_at":"2026-05-18T00:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"A6NMETRTPD37","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"A6NMETRTPD377BXB","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"A6NMETRT","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:A6NMETRTPD377BXBVYWW66FK7P","target":"record","payload":{"canonical_record":{"source":{"id":"1710.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T16:31:24Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"93e2b253e34667bd97984268c7b8f8f7cb4b9be15ecd757fa3bebd4a04341787","abstract_canon_sha256":"080e56c7f6455f654c88d5e112b1617b1883c46c75d7433f4f868ed0456e1bc6"},"schema_version":"1.0"},"canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:45.745557Z","signature_b64":"q6DkEdpO0Nc7pcGS0hHxi2zxYveo1WrhSwwfINs5Yld78y5svzdpQ4PHIoV3Oi3pW++jF2XlI/7qWCXkx8+DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","last_reissued_at":"2026-05-18T00:31:45.745023Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:45.745023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.11052","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":"2026-05-18T00:31:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uf1UVKNPVpTDXMlN4Hpbfdnke/ayFJ2XPrhnjxyKIaN51YZ2HwTg5YazlxnQ1tE4T2yNrBZV9VBfahpbHnb0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:08:30.888634Z"},"content_sha256":"38b982671eeedeec4f804c872c93da49a79f5db041b52598f7903a56d37be553","schema_version":"1.0","event_id":"sha256:38b982671eeedeec4f804c872c93da49a79f5db041b52598f7903a56d37be553"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:A6NMETRTPD377BXBVYWW66FK7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Connection between Feed-Forward Neural Networks and Probabilistic Graphical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dmitrij Schlesinger","submitted_at":"2017-10-30T16:31:24Z","abstract_excerpt":"Two of the most popular modelling paradigms in computer vision are feed-forward neural networks (FFNs) and probabilistic graphical models (GMs). Various connections between the two have been studied in recent works, such as e.g. expressing mean-field based inference in a GM as an FFN. This paper establishes a new connection between FFNs and GMs. Our key observation is that any FFN implements a certain approximation of a corresponding Bayesian network (BN). We characterize various benefits of having this connection. In particular, it results in a new learning algorithm for BNs. We validate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11052","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":"2026-05-18T00:31:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9fq6Aa/AdIHKTO6Stdw+SVC1nFPDoTnDkxhcq8Sk7aG+BKGynvmeAfgpRQnih9cH+2lZj5xiTUvhB6Qo4d/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T07:08:30.888978Z"},"content_sha256":"bc4a363c572a96c60e51144c5b735a1024280fd2e88bf2c05efb4dae6cb7e5ff","schema_version":"1.0","event_id":"sha256:bc4a363c572a96c60e51144c5b735a1024280fd2e88bf2c05efb4dae6cb7e5ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/bundle.json","state_url":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6NMETRTPD377BXBVYWW66FK7P/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":"2026-06-30T07:08:30Z","links":{"resolver":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P","bundle":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/bundle.json","state":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6NMETRTPD377BXBVYWW66FK7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:A6NMETRTPD377BXBVYWW66FK7P","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":"080e56c7f6455f654c88d5e112b1617b1883c46c75d7433f4f868ed0456e1bc6","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T16:31:24Z","title_canon_sha256":"93e2b253e34667bd97984268c7b8f8f7cb4b9be15ecd757fa3bebd4a04341787"},"schema_version":"1.0","source":{"id":"1710.11052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11052","created_at":"2026-05-18T00:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11052v1","created_at":"2026-05-18T00:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11052","created_at":"2026-05-18T00:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"A6NMETRTPD37","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"A6NMETRTPD377BXB","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"A6NMETRT","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:bc4a363c572a96c60e51144c5b735a1024280fd2e88bf2c05efb4dae6cb7e5ff","target":"graph","created_at":"2026-05-18T00:31:45Z","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":"Two of the most popular modelling paradigms in computer vision are feed-forward neural networks (FFNs) and probabilistic graphical models (GMs). Various connections between the two have been studied in recent works, such as e.g. expressing mean-field based inference in a GM as an FFN. This paper establishes a new connection between FFNs and GMs. Our key observation is that any FFN implements a certain approximation of a corresponding Bayesian network (BN). We characterize various benefits of having this connection. In particular, it results in a new learning algorithm for BNs. We validate the ","authors_text":"Dmitrij Schlesinger","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T16:31:24Z","title":"A Connection between Feed-Forward Neural Networks and Probabilistic Graphical Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11052","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":"sha256:38b982671eeedeec4f804c872c93da49a79f5db041b52598f7903a56d37be553","target":"record","created_at":"2026-05-18T00:31:45Z","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":"080e56c7f6455f654c88d5e112b1617b1883c46c75d7433f4f868ed0456e1bc6","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T16:31:24Z","title_canon_sha256":"93e2b253e34667bd97984268c7b8f8f7cb4b9be15ecd757fa3bebd4a04341787"},"schema_version":"1.0","source":{"id":"1710.11052","kind":"arxiv","version":1}},"canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","first_computed_at":"2026-05-18T00:31:45.745023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:45.745023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q6DkEdpO0Nc7pcGS0hHxi2zxYveo1WrhSwwfINs5Yld78y5svzdpQ4PHIoV3Oi3pW++jF2XlI/7qWCXkx8+DCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:45.745557Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.11052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38b982671eeedeec4f804c872c93da49a79f5db041b52598f7903a56d37be553","sha256:bc4a363c572a96c60e51144c5b735a1024280fd2e88bf2c05efb4dae6cb7e5ff"],"state_sha256":"36ae46e14400b41150ca17008ec346c7a968eeba9746345d46d185354855d165"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APcGdJ8vvh7/dwpMQNXhVDH3SbFbLogE9SJyl6oUZtjZedehMGY/1ByHz+UBzO1ctN4cdDBuZml0uV1qJiAJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T07:08:30.890828Z","bundle_sha256":"a64d6b6b22a4daf9719907d270a67ed0bc37c585c74d62b50d58527c2b64bcc4"}}