{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:TGT2LRLZYVDS6ZJS5XST6JWNYR","short_pith_number":"pith:TGT2LRLZ","canonical_record":{"source":{"id":"1506.03011","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-09T17:22:17Z","cross_cats_sorted":[],"title_canon_sha256":"d51faa13380b425954bdea8d7107d8c40269981eaaedaf0dd2d65e8a74a0dfa1","abstract_canon_sha256":"a030b6d80db2e61e50d01ca2c52a5a378d8972619ecc80f314045fc8a16ee248"},"schema_version":"1.0"},"canonical_sha256":"99a7a5c579c5472f6532ede53f26cdc44f57e51dcdb21d14baa7e8b23d0df9cc","source":{"kind":"arxiv","id":"1506.03011","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03011","created_at":"2026-05-18T01:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03011v2","created_at":"2026-05-18T01:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03011","created_at":"2026-05-18T01:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"TGT2LRLZYVDS","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TGT2LRLZYVDS6ZJS","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TGT2LRLZ","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:TGT2LRLZYVDS6ZJS5XST6JWNYR","target":"record","payload":{"canonical_record":{"source":{"id":"1506.03011","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-09T17:22:17Z","cross_cats_sorted":[],"title_canon_sha256":"d51faa13380b425954bdea8d7107d8c40269981eaaedaf0dd2d65e8a74a0dfa1","abstract_canon_sha256":"a030b6d80db2e61e50d01ca2c52a5a378d8972619ecc80f314045fc8a16ee248"},"schema_version":"1.0"},"canonical_sha256":"99a7a5c579c5472f6532ede53f26cdc44f57e51dcdb21d14baa7e8b23d0df9cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:33:32.016172Z","signature_b64":"GWHEXX09uVWqyIOioZNW7DZ1Gchh1M0G7p83rzGUQi7Jn7HMz6aNsX3RR0FhyZUtuAiN4rxoec0zwb9EhKa1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99a7a5c579c5472f6532ede53f26cdc44f57e51dcdb21d14baa7e8b23d0df9cc","last_reissued_at":"2026-05-18T01:33:32.015514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:33:32.015514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.03011","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0D+65R5J942lUfr+h6u1bmdNWk3v9zaG41H/BVcLXFnZYcENZtwTmiykZ2pDOuQMMlYJyvreCMH/cefECifZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:04:18.050631Z"},"content_sha256":"cabb468a8d523401c9ef06cd9bdccf9becfdf41823964ae4fb1c72a2f1e42daf","schema_version":"1.0","event_id":"sha256:cabb468a8d523401c9ef06cd9bdccf9becfdf41823964ae4fb1c72a2f1e42daf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:TGT2LRLZYVDS6ZJS5XST6JWNYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Linearize Under Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Mathieu, Ross Goroshin, Yann LeCun","submitted_at":"2015-06-09T17:22:17Z","abstract_excerpt":"Training deep feature hierarchies to solve supervised learning tasks has achieved state of the art performance on many problems in computer vision. However, a principled way in which to train such hierarchies in the unsupervised setting has remained elusive. In this work we suggest a new architecture and loss for training deep feature hierarchies that linearize the transformations observed in unlabeled natural video sequences. This is done by training a generative model to predict video frames. We also address the problem of inherent uncertainty in prediction by introducing latent variables th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03011","kind":"arxiv","version":2},"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":"2026-05-18T01:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"orqTb2EKH1k+hbw2uAoU+WlRhYCDp1H0FF74s6x/e4k6x4Ue9FlmD8ZJQqjzMVG0MMUZCbAi8QYlya6qxOMCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:04:18.050964Z"},"content_sha256":"fb7bebf8f4194f3c6c775f09208ec245cac0ebdac791c2675a631695f0282fe1","schema_version":"1.0","event_id":"sha256:fb7bebf8f4194f3c6c775f09208ec245cac0ebdac791c2675a631695f0282fe1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR/bundle.json","state_url":"https://pith.science/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR/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":"2026-06-30T11:04:18Z","links":{"resolver":"https://pith.science/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR","bundle":"https://pith.science/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR/bundle.json","state":"https://pith.science/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGT2LRLZYVDS6ZJS5XST6JWNYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:TGT2LRLZYVDS6ZJS5XST6JWNYR","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":"a030b6d80db2e61e50d01ca2c52a5a378d8972619ecc80f314045fc8a16ee248","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-09T17:22:17Z","title_canon_sha256":"d51faa13380b425954bdea8d7107d8c40269981eaaedaf0dd2d65e8a74a0dfa1"},"schema_version":"1.0","source":{"id":"1506.03011","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03011","created_at":"2026-05-18T01:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03011v2","created_at":"2026-05-18T01:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03011","created_at":"2026-05-18T01:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"TGT2LRLZYVDS","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TGT2LRLZYVDS6ZJS","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TGT2LRLZ","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:fb7bebf8f4194f3c6c775f09208ec245cac0ebdac791c2675a631695f0282fe1","target":"graph","created_at":"2026-05-18T01:33:32Z","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"},"paper":{"abstract_excerpt":"Training deep feature hierarchies to solve supervised learning tasks has achieved state of the art performance on many problems in computer vision. However, a principled way in which to train such hierarchies in the unsupervised setting has remained elusive. In this work we suggest a new architecture and loss for training deep feature hierarchies that linearize the transformations observed in unlabeled natural video sequences. This is done by training a generative model to predict video frames. We also address the problem of inherent uncertainty in prediction by introducing latent variables th","authors_text":"Michael Mathieu, Ross Goroshin, Yann LeCun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-09T17:22:17Z","title":"Learning to Linearize Under Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03011","kind":"arxiv","version":2},"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:cabb468a8d523401c9ef06cd9bdccf9becfdf41823964ae4fb1c72a2f1e42daf","target":"record","created_at":"2026-05-18T01:33:32Z","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":"a030b6d80db2e61e50d01ca2c52a5a378d8972619ecc80f314045fc8a16ee248","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-09T17:22:17Z","title_canon_sha256":"d51faa13380b425954bdea8d7107d8c40269981eaaedaf0dd2d65e8a74a0dfa1"},"schema_version":"1.0","source":{"id":"1506.03011","kind":"arxiv","version":2}},"canonical_sha256":"99a7a5c579c5472f6532ede53f26cdc44f57e51dcdb21d14baa7e8b23d0df9cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99a7a5c579c5472f6532ede53f26cdc44f57e51dcdb21d14baa7e8b23d0df9cc","first_computed_at":"2026-05-18T01:33:32.015514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:33:32.015514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GWHEXX09uVWqyIOioZNW7DZ1Gchh1M0G7p83rzGUQi7Jn7HMz6aNsX3RR0FhyZUtuAiN4rxoec0zwb9EhKa1BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:33:32.016172Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.03011","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cabb468a8d523401c9ef06cd9bdccf9becfdf41823964ae4fb1c72a2f1e42daf","sha256:fb7bebf8f4194f3c6c775f09208ec245cac0ebdac791c2675a631695f0282fe1"],"state_sha256":"c938fff5eb69446cb91ce1d4de0cae8b85db54c41569419d4a9947c764da01ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vx0h8UEFBSDWuP/qZs1eUulv4iWnL/1MngxuAlvojuJKvDQcOC80vcNVL4247f0hNoGIjhBMqvGCApwOThdPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T11:04:18.052794Z","bundle_sha256":"8a66004ea0a39aa1efe64c3e855fc3051d0d0075059821705e7b06df621d9661"}}