{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GO4SHUAKFZR5347I3M3GYT7ZEB","short_pith_number":"pith:GO4SHUAK","canonical_record":{"source":{"id":"1611.03125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T22:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"93b3e9b2a9f286215c2cfddc4a6b9370a55d9d7f57b12d97bc6b4b3f05107cf3","abstract_canon_sha256":"83bf2fc8e7219ee9501562002c9ea939d3e5e978d160d1c811abe1e858f14cbf"},"schema_version":"1.0"},"canonical_sha256":"33b923d00a2e63ddf3e8db366c4ff9204b7a9f87faca86919f772d9e214f8192","source":{"kind":"arxiv","id":"1611.03125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03125","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03125v1","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03125","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"GO4SHUAKFZR5","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GO4SHUAKFZR5347I","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GO4SHUAK","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GO4SHUAKFZR5347I3M3GYT7ZEB","target":"record","payload":{"canonical_record":{"source":{"id":"1611.03125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T22:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"93b3e9b2a9f286215c2cfddc4a6b9370a55d9d7f57b12d97bc6b4b3f05107cf3","abstract_canon_sha256":"83bf2fc8e7219ee9501562002c9ea939d3e5e978d160d1c811abe1e858f14cbf"},"schema_version":"1.0"},"canonical_sha256":"33b923d00a2e63ddf3e8db366c4ff9204b7a9f87faca86919f772d9e214f8192","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:41.270699Z","signature_b64":"w3yg2qfjJGl9bWyEljKHbWe10r5rSgSXOMaouvJaKgGt2pU73xSvXlwEMRA8+R2dLncHt6JQAqex6QOv98qVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33b923d00a2e63ddf3e8db366c4ff9204b7a9f87faca86919f772d9e214f8192","last_reissued_at":"2026-05-18T00:59:41.269908Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:41.269908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.03125","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":"2026-05-18T00:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OA4NCwUzJJ7WTfNepBovKhKo9/ZN+CsLtie3pFVZ7d2XDZnp3Yv0j+XQwFJqingAakBCV0S40P6LNm0WHTqKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:34:52.129023Z"},"content_sha256":"b37f963c7009cbfa61f5051d9473e987144338755313cb26d37010f8ce474eb8","schema_version":"1.0","event_id":"sha256:b37f963c7009cbfa61f5051d9473e987144338755313cb26d37010f8ce474eb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GO4SHUAKFZR5347I3M3GYT7ZEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Modular Theory of Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Soon Ong, Daniel McNamara, Robert C. Williamson","submitted_at":"2016-11-09T22:40:15Z","abstract_excerpt":"Learning representations of data, and in particular learning features for a subsequent prediction task, has been a fruitful area of research delivering impressive empirical results in recent years. However, relatively little is understood about what makes a representation `good'. We propose the idea of a risk gap induced by representation learning for a given prediction context, which measures the difference in the risk of some learner using the learned features as compared to the original inputs. We describe a set of sufficient conditions for unsupervised representation learning to provide a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03125","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":"2026-05-18T00:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d48sR9HITuLFOZcWypwkyMj61lJZTg9r7g8ghs8+2Xg1Jyd28wXZixTvpidmLPQROxTdO0Lz4W4NgFyIMNgRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:34:52.129384Z"},"content_sha256":"92539ad8e493ba693b761c775b6efef26baf8dad9e7503ec454d7a0614319ce4","schema_version":"1.0","event_id":"sha256:92539ad8e493ba693b761c775b6efef26baf8dad9e7503ec454d7a0614319ce4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GO4SHUAKFZR5347I3M3GYT7ZEB/bundle.json","state_url":"https://pith.science/pith/GO4SHUAKFZR5347I3M3GYT7ZEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GO4SHUAKFZR5347I3M3GYT7ZEB/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":"2026-05-27T10:34:52Z","links":{"resolver":"https://pith.science/pith/GO4SHUAKFZR5347I3M3GYT7ZEB","bundle":"https://pith.science/pith/GO4SHUAKFZR5347I3M3GYT7ZEB/bundle.json","state":"https://pith.science/pith/GO4SHUAKFZR5347I3M3GYT7ZEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GO4SHUAKFZR5347I3M3GYT7ZEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GO4SHUAKFZR5347I3M3GYT7ZEB","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":"83bf2fc8e7219ee9501562002c9ea939d3e5e978d160d1c811abe1e858f14cbf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T22:40:15Z","title_canon_sha256":"93b3e9b2a9f286215c2cfddc4a6b9370a55d9d7f57b12d97bc6b4b3f05107cf3"},"schema_version":"1.0","source":{"id":"1611.03125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03125","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03125v1","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03125","created_at":"2026-05-18T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"GO4SHUAKFZR5","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GO4SHUAKFZR5347I","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GO4SHUAK","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:92539ad8e493ba693b761c775b6efef26baf8dad9e7503ec454d7a0614319ce4","target":"graph","created_at":"2026-05-18T00:59:41Z","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":"Learning representations of data, and in particular learning features for a subsequent prediction task, has been a fruitful area of research delivering impressive empirical results in recent years. However, relatively little is understood about what makes a representation `good'. We propose the idea of a risk gap induced by representation learning for a given prediction context, which measures the difference in the risk of some learner using the learned features as compared to the original inputs. We describe a set of sufficient conditions for unsupervised representation learning to provide a ","authors_text":"Cheng Soon Ong, Daniel McNamara, Robert C. Williamson","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T22:40:15Z","title":"A Modular Theory of Feature Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03125","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:b37f963c7009cbfa61f5051d9473e987144338755313cb26d37010f8ce474eb8","target":"record","created_at":"2026-05-18T00:59:41Z","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":"83bf2fc8e7219ee9501562002c9ea939d3e5e978d160d1c811abe1e858f14cbf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T22:40:15Z","title_canon_sha256":"93b3e9b2a9f286215c2cfddc4a6b9370a55d9d7f57b12d97bc6b4b3f05107cf3"},"schema_version":"1.0","source":{"id":"1611.03125","kind":"arxiv","version":1}},"canonical_sha256":"33b923d00a2e63ddf3e8db366c4ff9204b7a9f87faca86919f772d9e214f8192","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33b923d00a2e63ddf3e8db366c4ff9204b7a9f87faca86919f772d9e214f8192","first_computed_at":"2026-05-18T00:59:41.269908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:59:41.269908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w3yg2qfjJGl9bWyEljKHbWe10r5rSgSXOMaouvJaKgGt2pU73xSvXlwEMRA8+R2dLncHt6JQAqex6QOv98qVCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:59:41.270699Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.03125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b37f963c7009cbfa61f5051d9473e987144338755313cb26d37010f8ce474eb8","sha256:92539ad8e493ba693b761c775b6efef26baf8dad9e7503ec454d7a0614319ce4"],"state_sha256":"affd5c5e15aa247fb8b5b8ada9e5824d036c51c98f1728f762e6e85adc9f3fe9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gil4LMMgUprKYjxqyUquyHsJgB2j8ZNVGEhXYEs+UM8m9FUN07l/N6R74X0jlUJ3lKxXl2ZAKKojmnwXX+bVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:34:52.131940Z","bundle_sha256":"ba51e2dc0f58ffdda9116b95899855a131fd2a958a0127ea219dc6bf222fb1b5"}}