{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:7WTBXPEHDJAYYCUDKKOUEGZB7U","short_pith_number":"pith:7WTBXPEH","canonical_record":{"source":{"id":"1402.2333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-10T23:53:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"adef18a482c48ea4edac02da545fa4a8520eec1ffce45b940a358b5f5113ebd0","abstract_canon_sha256":"c63fbdfe3412533fb86e89b8a28911f8c1d2f912a60bdf97fc3854d8c9288d37"},"schema_version":"1.0"},"canonical_sha256":"fda61bbc871a418c0a83529d421b21fd17581a389fc22ae53e98cfa6b976f10b","source":{"kind":"arxiv","id":"1402.2333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.2333","created_at":"2026-05-18T02:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"1402.2333v1","created_at":"2026-05-18T02:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.2333","created_at":"2026-05-18T02:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"7WTBXPEHDJAY","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7WTBXPEHDJAYYCUD","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7WTBXPEH","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:7WTBXPEHDJAYYCUDKKOUEGZB7U","target":"record","payload":{"canonical_record":{"source":{"id":"1402.2333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-10T23:53:29Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"adef18a482c48ea4edac02da545fa4a8520eec1ffce45b940a358b5f5113ebd0","abstract_canon_sha256":"c63fbdfe3412533fb86e89b8a28911f8c1d2f912a60bdf97fc3854d8c9288d37"},"schema_version":"1.0"},"canonical_sha256":"fda61bbc871a418c0a83529d421b21fd17581a389fc22ae53e98cfa6b976f10b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:59:31.111058Z","signature_b64":"gO+y1EA/TaxyzMUcqnokRI9se8T2u9OeWNUmpyXczrYCgeaaAAe2P26CtxAq+kbjCmKySdA6zP1Y5XFxcMFQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda61bbc871a418c0a83529d421b21fd17581a389fc22ae53e98cfa6b976f10b","last_reissued_at":"2026-05-18T02:59:31.110258Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:59:31.110258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.2333","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":"2026-05-18T02:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H5C3B+VVSSolQwtAqMzfqnI3PvmW1oLy2oqwHPQV8bKmMYXxGF1h3xbJ3EilzKHuarz8DK08XIaZ1dLDKm+oBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:46:00.682145Z"},"content_sha256":"e88db42b979eba96e48f591e10c445154753e44a9bbcb24124a3217b181bbb09","schema_version":"1.0","event_id":"sha256:e88db42b979eba96e48f591e10c445154753e44a9bbcb24124a3217b181bbb09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:7WTBXPEHDJAYYCUDKKOUEGZB7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling sequential data using higher-order relational features and predictive training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kishore Konda, Roland Memisevic, Vincent Michalski","submitted_at":"2014-02-10T23:53:29Z","abstract_excerpt":"Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one frame, given the previous frame, these models learn \"mapping units\" that encode the transformations inherent in a sequence, and thereby learn to encode motion. In this work we extend bi-linear models by introducing \"higher-order mapping units\" that allow us to encode transformations between frames and transformations between transformations.\n  We show that this makes it possible to encode temporal structure that is mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.2333","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":"2026-05-18T02:59:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X38D+DaHh//FtEKq7B/1Up5moKcJr7vUIU4ET7lX/+ryeqwQw5OhY20vLAFUt4jvGnnxqBXn6ZgB/1V9VhGNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:46:00.682539Z"},"content_sha256":"f8dd7b77da0d95833ac08923a94b538f69e55aaa159417a9323e731198eb3ea7","schema_version":"1.0","event_id":"sha256:f8dd7b77da0d95833ac08923a94b538f69e55aaa159417a9323e731198eb3ea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U/bundle.json","state_url":"https://pith.science/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U/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":"2026-05-30T22:46:00Z","links":{"resolver":"https://pith.science/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U","bundle":"https://pith.science/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U/bundle.json","state":"https://pith.science/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WTBXPEHDJAYYCUDKKOUEGZB7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:7WTBXPEHDJAYYCUDKKOUEGZB7U","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":"c63fbdfe3412533fb86e89b8a28911f8c1d2f912a60bdf97fc3854d8c9288d37","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-10T23:53:29Z","title_canon_sha256":"adef18a482c48ea4edac02da545fa4a8520eec1ffce45b940a358b5f5113ebd0"},"schema_version":"1.0","source":{"id":"1402.2333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.2333","created_at":"2026-05-18T02:59:31Z"},{"alias_kind":"arxiv_version","alias_value":"1402.2333v1","created_at":"2026-05-18T02:59:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.2333","created_at":"2026-05-18T02:59:31Z"},{"alias_kind":"pith_short_12","alias_value":"7WTBXPEHDJAY","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"7WTBXPEHDJAYYCUD","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"7WTBXPEH","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:f8dd7b77da0d95833ac08923a94b538f69e55aaa159417a9323e731198eb3ea7","target":"graph","created_at":"2026-05-18T02:59:31Z","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":"Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one frame, given the previous frame, these models learn \"mapping units\" that encode the transformations inherent in a sequence, and thereby learn to encode motion. In this work we extend bi-linear models by introducing \"higher-order mapping units\" that allow us to encode transformations between frames and transformations between transformations.\n  We show that this makes it possible to encode temporal structure that is mor","authors_text":"Kishore Konda, Roland Memisevic, Vincent Michalski","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-10T23:53:29Z","title":"Modeling sequential data using higher-order relational features and predictive training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.2333","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:e88db42b979eba96e48f591e10c445154753e44a9bbcb24124a3217b181bbb09","target":"record","created_at":"2026-05-18T02:59:31Z","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":"c63fbdfe3412533fb86e89b8a28911f8c1d2f912a60bdf97fc3854d8c9288d37","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-10T23:53:29Z","title_canon_sha256":"adef18a482c48ea4edac02da545fa4a8520eec1ffce45b940a358b5f5113ebd0"},"schema_version":"1.0","source":{"id":"1402.2333","kind":"arxiv","version":1}},"canonical_sha256":"fda61bbc871a418c0a83529d421b21fd17581a389fc22ae53e98cfa6b976f10b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fda61bbc871a418c0a83529d421b21fd17581a389fc22ae53e98cfa6b976f10b","first_computed_at":"2026-05-18T02:59:31.110258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:59:31.110258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gO+y1EA/TaxyzMUcqnokRI9se8T2u9OeWNUmpyXczrYCgeaaAAe2P26CtxAq+kbjCmKySdA6zP1Y5XFxcMFQBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:59:31.111058Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.2333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e88db42b979eba96e48f591e10c445154753e44a9bbcb24124a3217b181bbb09","sha256:f8dd7b77da0d95833ac08923a94b538f69e55aaa159417a9323e731198eb3ea7"],"state_sha256":"774afa9835830e127fb5ddd43570f4c0ae42fff7c34d7c4e4ad82ca968cc1f76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0oJ65868gvgKKZcpM0p0Y+G/reDTcTtjhkJdBDoT47aXlptjfm9y8o9QZEtHQhVBE0QwkTv8AvoQqdOCWsNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T22:46:00.684816Z","bundle_sha256":"07d5a1223dfcdda53dbe2c892194da68f0087d6ea1052cf2e93c488af05c43b2"}}