{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5S7SPW3DI7VKZW26JTJUJ6I7QZ","short_pith_number":"pith:5S7SPW3D","canonical_record":{"source":{"id":"1602.01024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-02T17:51:43Z","cross_cats_sorted":[],"title_canon_sha256":"2319a66d2bcdbe039927eaad75f5ad1d7c1a23f062146b9ad3cf355e22c90eb3","abstract_canon_sha256":"0307d65c9f477f4aa1f44d97d241cd743c9fcd75f991b97798126a0bde86e265"},"schema_version":"1.0"},"canonical_sha256":"ecbf27db6347eaacdb5e4cd344f91f866b984154ac3bed24a5fd66c970a50044","source":{"kind":"arxiv","id":"1602.01024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.01024","created_at":"2026-05-18T01:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"1602.01024v1","created_at":"2026-05-18T01:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.01024","created_at":"2026-05-18T01:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"5S7SPW3DI7VK","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5S7SPW3DI7VKZW26","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5S7SPW3D","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5S7SPW3DI7VKZW26JTJUJ6I7QZ","target":"record","payload":{"canonical_record":{"source":{"id":"1602.01024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-02T17:51:43Z","cross_cats_sorted":[],"title_canon_sha256":"2319a66d2bcdbe039927eaad75f5ad1d7c1a23f062146b9ad3cf355e22c90eb3","abstract_canon_sha256":"0307d65c9f477f4aa1f44d97d241cd743c9fcd75f991b97798126a0bde86e265"},"schema_version":"1.0"},"canonical_sha256":"ecbf27db6347eaacdb5e4cd344f91f866b984154ac3bed24a5fd66c970a50044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:23.959108Z","signature_b64":"OLRpUL9V/+6Z6Zsc+lMNV8RbFa1RolSMhLCp0ChWbwsbw/9rxQJvPKlXi3GNfYz70nf23f+9b6tLI0folDl2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecbf27db6347eaacdb5e4cd344f91f866b984154ac3bed24a5fd66c970a50044","last_reissued_at":"2026-05-18T01:21:23.958539Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:23.958539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.01024","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":"2026-05-18T01:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86Cyza4lDBEjd9+8D3c+59aMYSuShHf00l7++NSWCxLhS9ckrd4ATeKezCpM5uCAg1Zj+/APb6TLwGA0x+6NAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:15:10.247545Z"},"content_sha256":"3b2ba807ef8d6fe1d21bfbf657e3c12a07b60a044ae8ebd352866fc3655c46ed","schema_version":"1.0","event_id":"sha256:3b2ba807ef8d6fe1d21bfbf657e3c12a07b60a044ae8ebd352866fc3655c46ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5S7SPW3DI7VKZW26JTJUJ6I7QZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Deep Multi-View Representation Learning: Objectives and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jeff Bilmes, Karen Livescu, Raman Arora, Weiran Wang","submitted_at":"2016-02-02T17:51:43Z","abstract_excerpt":"We consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for learning while only one view is available for downstream tasks. Previous work on this problem has proposed several techniques based on deep neural networks, typically involving either autoencoder-like networks with a reconstruction objective or paired feedforward networks with a batch-style correlation-based objective. We analyze several techniques based on prior work, as well as new variants, and compare them empirically on image, speech, and text tasks. We find a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.01024","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":"2026-05-18T01:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffnohfALI02PVCheZJuR5Ic6OsAyVGWbtaxEgdqvldkqpfKsyOXyd1TbcttTdP7aIfZAZGyshrNdbGJy16GaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:15:10.247887Z"},"content_sha256":"9e7050a694ea9f366177da6dcda2ea2e022d9f85be0cc8ea257c4b43502d99b0","schema_version":"1.0","event_id":"sha256:9e7050a694ea9f366177da6dcda2ea2e022d9f85be0cc8ea257c4b43502d99b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ/bundle.json","state_url":"https://pith.science/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ/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":"2026-06-01T15:15:10Z","links":{"resolver":"https://pith.science/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ","bundle":"https://pith.science/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ/bundle.json","state":"https://pith.science/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5S7SPW3DI7VKZW26JTJUJ6I7QZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5S7SPW3DI7VKZW26JTJUJ6I7QZ","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":"0307d65c9f477f4aa1f44d97d241cd743c9fcd75f991b97798126a0bde86e265","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-02T17:51:43Z","title_canon_sha256":"2319a66d2bcdbe039927eaad75f5ad1d7c1a23f062146b9ad3cf355e22c90eb3"},"schema_version":"1.0","source":{"id":"1602.01024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.01024","created_at":"2026-05-18T01:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"1602.01024v1","created_at":"2026-05-18T01:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.01024","created_at":"2026-05-18T01:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"5S7SPW3DI7VK","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5S7SPW3DI7VKZW26","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5S7SPW3D","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:9e7050a694ea9f366177da6dcda2ea2e022d9f85be0cc8ea257c4b43502d99b0","target":"graph","created_at":"2026-05-18T01:21:23Z","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 consider learning representations (features) in the setting in which we have access to multiple unlabeled views of the data for learning while only one view is available for downstream tasks. Previous work on this problem has proposed several techniques based on deep neural networks, typically involving either autoencoder-like networks with a reconstruction objective or paired feedforward networks with a batch-style correlation-based objective. We analyze several techniques based on prior work, as well as new variants, and compare them empirically on image, speech, and text tasks. We find a","authors_text":"Jeff Bilmes, Karen Livescu, Raman Arora, Weiran Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-02T17:51:43Z","title":"On Deep Multi-View Representation Learning: Objectives and Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.01024","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":"sha256:3b2ba807ef8d6fe1d21bfbf657e3c12a07b60a044ae8ebd352866fc3655c46ed","target":"record","created_at":"2026-05-18T01:21:23Z","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":"0307d65c9f477f4aa1f44d97d241cd743c9fcd75f991b97798126a0bde86e265","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-02T17:51:43Z","title_canon_sha256":"2319a66d2bcdbe039927eaad75f5ad1d7c1a23f062146b9ad3cf355e22c90eb3"},"schema_version":"1.0","source":{"id":"1602.01024","kind":"arxiv","version":1}},"canonical_sha256":"ecbf27db6347eaacdb5e4cd344f91f866b984154ac3bed24a5fd66c970a50044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecbf27db6347eaacdb5e4cd344f91f866b984154ac3bed24a5fd66c970a50044","first_computed_at":"2026-05-18T01:21:23.958539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:21:23.958539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OLRpUL9V/+6Z6Zsc+lMNV8RbFa1RolSMhLCp0ChWbwsbw/9rxQJvPKlXi3GNfYz70nf23f+9b6tLI0folDl2Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:21:23.959108Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.01024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b2ba807ef8d6fe1d21bfbf657e3c12a07b60a044ae8ebd352866fc3655c46ed","sha256:9e7050a694ea9f366177da6dcda2ea2e022d9f85be0cc8ea257c4b43502d99b0"],"state_sha256":"25e19bee0ac9b95e3400e87b8404d3d944713d3391911ec79a212a66110a53ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/V1XcDxfAh+Fih7yy9Qj7bXSIGdI31IUV0twaMHLotOimKj2WIKl8ODJVBNJDd/TlnQ7+RvL25Z00lJmpDRXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T15:15:10.249720Z","bundle_sha256":"09d672a8aef16ce172b8f71a0da05d2eb16395198b00675a43343e231afe1e98"}}