{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CSAY3ZENOWUHF2HMT4IKPPAXP7","short_pith_number":"pith:CSAY3ZEN","canonical_record":{"source":{"id":"1706.04601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-14T17:35:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"053ba5cdec201e97c9629621c5f9aa2afba7f489b8749e8ae7d2e1e6a7b9ddaa","abstract_canon_sha256":"2678e8300b21c31e9d8d66f013e21ce5900020d7272efd6d24766e38e43ad365"},"schema_version":"1.0"},"canonical_sha256":"14818de48d75a872e8ec9f10a7bc177fe5834f2a52e594c2892f187cdb0dd968","source":{"kind":"arxiv","id":"1706.04601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04601","created_at":"2026-05-18T00:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04601v1","created_at":"2026-05-18T00:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04601","created_at":"2026-05-18T00:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"CSAY3ZENOWUH","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CSAY3ZENOWUHF2HM","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CSAY3ZEN","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CSAY3ZENOWUHF2HMT4IKPPAXP7","target":"record","payload":{"canonical_record":{"source":{"id":"1706.04601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-14T17:35:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"053ba5cdec201e97c9629621c5f9aa2afba7f489b8749e8ae7d2e1e6a7b9ddaa","abstract_canon_sha256":"2678e8300b21c31e9d8d66f013e21ce5900020d7272efd6d24766e38e43ad365"},"schema_version":"1.0"},"canonical_sha256":"14818de48d75a872e8ec9f10a7bc177fe5834f2a52e594c2892f187cdb0dd968","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:22.224769Z","signature_b64":"yumESGT0o0IwRBFeWzxL3/kjfSMT7HRcSZI2RMFNgZwZ/gwllTCx+pn82aPHVhx2HN3hkSxTEPS9/m5lYLfPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14818de48d75a872e8ec9f10a7bc177fe5834f2a52e594c2892f187cdb0dd968","last_reissued_at":"2026-05-18T00:42:22.224225Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:22.224225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.04601","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":"2026-05-18T00:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+EzjddgBzk++F0LtxbqnH95Px8/N4eH48gsx872WGfxdZaeInv1pbvFozOS2VR7hwGr8g+W37KJlpLoBk1yAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:59:49.435943Z"},"content_sha256":"3b1f97496fda5e811dc10355274a38a43fa281c4c1bcb5cc7b26c7804491af66","schema_version":"1.0","event_id":"sha256:3b1f97496fda5e811dc10355274a38a43fa281c4c1bcb5cc7b26c7804491af66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CSAY3ZENOWUHF2HMT4IKPPAXP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provable benefits of representation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrej Risteski, Sanjeev Arora","submitted_at":"2017-06-14T17:35:21Z","abstract_excerpt":"There is general consensus that learning representations is useful for a variety of reasons, e.g. efficient use of labeled data (semi-supervised learning), transfer learning and understanding hidden structure of data. Popular techniques for representation learning include clustering, manifold learning, kernel-learning, autoencoders, Boltzmann machines, etc.\n  To study the relative merits of these techniques, it's essential to formalize the definition and goals of representation learning, so that they are all become instances of the same definition. This paper introduces such a formal framework"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04601","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":"2026-05-18T00:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ccakxizPING4k0Yn3WS6rSEFKttjkETnfwiP5SIWL/ydHn/wDsH+mcw5BSARLZZD5qE2WcuhuCbc7rTHgOMoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:59:49.436281Z"},"content_sha256":"f57bf2c791bdf59353ca794c10b091819d89791b34a72204fd04e857c5a7e80a","schema_version":"1.0","event_id":"sha256:f57bf2c791bdf59353ca794c10b091819d89791b34a72204fd04e857c5a7e80a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7/bundle.json","state_url":"https://pith.science/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7/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":"2026-06-27T16:59:49Z","links":{"resolver":"https://pith.science/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7","bundle":"https://pith.science/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7/bundle.json","state":"https://pith.science/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CSAY3ZENOWUHF2HMT4IKPPAXP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CSAY3ZENOWUHF2HMT4IKPPAXP7","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":"2678e8300b21c31e9d8d66f013e21ce5900020d7272efd6d24766e38e43ad365","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-14T17:35:21Z","title_canon_sha256":"053ba5cdec201e97c9629621c5f9aa2afba7f489b8749e8ae7d2e1e6a7b9ddaa"},"schema_version":"1.0","source":{"id":"1706.04601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04601","created_at":"2026-05-18T00:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04601v1","created_at":"2026-05-18T00:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04601","created_at":"2026-05-18T00:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"CSAY3ZENOWUH","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CSAY3ZENOWUHF2HM","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CSAY3ZEN","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:f57bf2c791bdf59353ca794c10b091819d89791b34a72204fd04e857c5a7e80a","target":"graph","created_at":"2026-05-18T00:42:22Z","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":"There is general consensus that learning representations is useful for a variety of reasons, e.g. efficient use of labeled data (semi-supervised learning), transfer learning and understanding hidden structure of data. Popular techniques for representation learning include clustering, manifold learning, kernel-learning, autoencoders, Boltzmann machines, etc.\n  To study the relative merits of these techniques, it's essential to formalize the definition and goals of representation learning, so that they are all become instances of the same definition. This paper introduces such a formal framework","authors_text":"Andrej Risteski, Sanjeev Arora","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-14T17:35:21Z","title":"Provable benefits of representation learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04601","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":"sha256:3b1f97496fda5e811dc10355274a38a43fa281c4c1bcb5cc7b26c7804491af66","target":"record","created_at":"2026-05-18T00:42:22Z","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":"2678e8300b21c31e9d8d66f013e21ce5900020d7272efd6d24766e38e43ad365","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-14T17:35:21Z","title_canon_sha256":"053ba5cdec201e97c9629621c5f9aa2afba7f489b8749e8ae7d2e1e6a7b9ddaa"},"schema_version":"1.0","source":{"id":"1706.04601","kind":"arxiv","version":1}},"canonical_sha256":"14818de48d75a872e8ec9f10a7bc177fe5834f2a52e594c2892f187cdb0dd968","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14818de48d75a872e8ec9f10a7bc177fe5834f2a52e594c2892f187cdb0dd968","first_computed_at":"2026-05-18T00:42:22.224225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:22.224225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yumESGT0o0IwRBFeWzxL3/kjfSMT7HRcSZI2RMFNgZwZ/gwllTCx+pn82aPHVhx2HN3hkSxTEPS9/m5lYLfPCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:22.224769Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b1f97496fda5e811dc10355274a38a43fa281c4c1bcb5cc7b26c7804491af66","sha256:f57bf2c791bdf59353ca794c10b091819d89791b34a72204fd04e857c5a7e80a"],"state_sha256":"c116b53f43d8845b6b0a3e05008a2f66b35eb325086e6832bc505517166f01ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KULm7CPsbNsMO+Sof0MVgsJ09ft4kMsuNZXxB/l81aVgIRhWG0SW7d17gZUmc3cll279XHoohVPYxKqCr+FzDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T16:59:49.438169Z","bundle_sha256":"1e96825a34cfa0c0f28e7f41d0464d6221c7580f1be3948862cc4a7c36cb3f73"}}