{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:V4ZL4HSPVARNVUPH5IG774LQRG","short_pith_number":"pith:V4ZL4HSP","canonical_record":{"source":{"id":"1603.08575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-28T21:59:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1755bdce83d1eed2a86e260bafa9e3a785a26f2f859bc4b83984072d15b4716","abstract_canon_sha256":"45477a898377255fdb2db9246e2f171e1027a10de47677ef49217ef36a6a46b7"},"schema_version":"1.0"},"canonical_sha256":"af32be1e4fa822dad1e7ea0dfff17089a3a765b534ba4c09a97d821bd4e525da","source":{"kind":"arxiv","id":"1603.08575","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.08575","created_at":"2026-05-18T01:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"1603.08575v3","created_at":"2026-05-18T01:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08575","created_at":"2026-05-18T01:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"V4ZL4HSPVARN","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"V4ZL4HSPVARNVUPH","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"V4ZL4HSP","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:V4ZL4HSPVARNVUPH5IG774LQRG","target":"record","payload":{"canonical_record":{"source":{"id":"1603.08575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-28T21:59:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1755bdce83d1eed2a86e260bafa9e3a785a26f2f859bc4b83984072d15b4716","abstract_canon_sha256":"45477a898377255fdb2db9246e2f171e1027a10de47677ef49217ef36a6a46b7"},"schema_version":"1.0"},"canonical_sha256":"af32be1e4fa822dad1e7ea0dfff17089a3a765b534ba4c09a97d821bd4e525da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:11.711491Z","signature_b64":"vwRKV1tJicAJ/WWeXrcw2Ln16TV5naDtaTzO5qXA4pEcgekg6mRYAo9BcslO/YbuWDRu9WzY0Zk7KmdNYyitCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af32be1e4fa822dad1e7ea0dfff17089a3a765b534ba4c09a97d821bd4e525da","last_reissued_at":"2026-05-18T01:09:11.710792Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:11.710792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.08575","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+jSXbkI969apBj7z+OHeFZHm58e9APqMZs7uYMDcSDbb+XByY48P2OqOb9mNgEwKDDI+y3CGI67PF7FzKuyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:44:31.662383Z"},"content_sha256":"70ad1de72b6964c584029cc2c52b9356217f96d2e8ef8504ef90d7217d495a26","schema_version":"1.0","event_id":"sha256:70ad1de72b6964c584029cc2c52b9356217f96d2e8ef8504ef90d7217d495a26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:V4ZL4HSPVARNVUPH5IG774LQRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Szepesvari, Geoffrey E. Hinton, Koray Kavukcuoglu, Nicolas Heess, S. M. Ali Eslami, Theophane Weber, Yuval Tassa","submitted_at":"2016-03-28T21:59:08Z","abstract_excerpt":"We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D models (probabilistic renderers). We show that such models learn to identify multiple objects - coun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08575","kind":"arxiv","version":3},"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":"2026-05-18T01:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dt3HbVC8ILYLkbk7ZBKy+GJho11+/sB4jtpP1Pa5Y53km8He0wCORqWvyPQ50yUZgg44i96syJ6XP/IhwBB+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T09:44:31.662923Z"},"content_sha256":"365614d96e82de03f3e3d6c99017516a797456e57a599406cae8e467aeccfb09","schema_version":"1.0","event_id":"sha256:365614d96e82de03f3e3d6c99017516a797456e57a599406cae8e467aeccfb09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4ZL4HSPVARNVUPH5IG774LQRG/bundle.json","state_url":"https://pith.science/pith/V4ZL4HSPVARNVUPH5IG774LQRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4ZL4HSPVARNVUPH5IG774LQRG/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":"2026-06-01T09:44:31Z","links":{"resolver":"https://pith.science/pith/V4ZL4HSPVARNVUPH5IG774LQRG","bundle":"https://pith.science/pith/V4ZL4HSPVARNVUPH5IG774LQRG/bundle.json","state":"https://pith.science/pith/V4ZL4HSPVARNVUPH5IG774LQRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4ZL4HSPVARNVUPH5IG774LQRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:V4ZL4HSPVARNVUPH5IG774LQRG","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":"45477a898377255fdb2db9246e2f171e1027a10de47677ef49217ef36a6a46b7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-28T21:59:08Z","title_canon_sha256":"f1755bdce83d1eed2a86e260bafa9e3a785a26f2f859bc4b83984072d15b4716"},"schema_version":"1.0","source":{"id":"1603.08575","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.08575","created_at":"2026-05-18T01:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"1603.08575v3","created_at":"2026-05-18T01:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.08575","created_at":"2026-05-18T01:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"V4ZL4HSPVARN","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"V4ZL4HSPVARNVUPH","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"V4ZL4HSP","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:365614d96e82de03f3e3d6c99017516a797456e57a599406cae8e467aeccfb09","target":"graph","created_at":"2026-05-18T01:09:11Z","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":"We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns to choose the appropriate number of inference steps. We use this scheme to learn to perform inference in partially specified 2D models (variable-sized variational auto-encoders) and fully specified 3D models (probabilistic renderers). We show that such models learn to identify multiple objects - coun","authors_text":"David Szepesvari, Geoffrey E. Hinton, Koray Kavukcuoglu, Nicolas Heess, S. M. Ali Eslami, Theophane Weber, Yuval Tassa","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-28T21:59:08Z","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.08575","kind":"arxiv","version":3},"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":"sha256:70ad1de72b6964c584029cc2c52b9356217f96d2e8ef8504ef90d7217d495a26","target":"record","created_at":"2026-05-18T01:09:11Z","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":"45477a898377255fdb2db9246e2f171e1027a10de47677ef49217ef36a6a46b7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-28T21:59:08Z","title_canon_sha256":"f1755bdce83d1eed2a86e260bafa9e3a785a26f2f859bc4b83984072d15b4716"},"schema_version":"1.0","source":{"id":"1603.08575","kind":"arxiv","version":3}},"canonical_sha256":"af32be1e4fa822dad1e7ea0dfff17089a3a765b534ba4c09a97d821bd4e525da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af32be1e4fa822dad1e7ea0dfff17089a3a765b534ba4c09a97d821bd4e525da","first_computed_at":"2026-05-18T01:09:11.710792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:11.710792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vwRKV1tJicAJ/WWeXrcw2Ln16TV5naDtaTzO5qXA4pEcgekg6mRYAo9BcslO/YbuWDRu9WzY0Zk7KmdNYyitCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:11.711491Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.08575","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70ad1de72b6964c584029cc2c52b9356217f96d2e8ef8504ef90d7217d495a26","sha256:365614d96e82de03f3e3d6c99017516a797456e57a599406cae8e467aeccfb09"],"state_sha256":"8a5f6cc8227c20a3ce940e1eae91907c83d5900ee9911505d2704c96c620083b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSNZbKGr4WAAHSJc5rmhg1V2WgoDdDqvGB0t9BcbNE3Z22b3tQoGnN8FY46O5kNYkrG17nzV693IMM1mlX3BBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T09:44:31.665707Z","bundle_sha256":"2ef722d41698116ce60eb383f4291280619ac1f4e4913c9e45fe9369cfdb255a"}}