{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:Z7COYNLFWKZ5NV3R2VNOAEQF3V","short_pith_number":"pith:Z7COYNLF","canonical_record":{"source":{"id":"1505.05192","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-19T21:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"7b9af53b7564fcf2ba5050e02f5cff002cd8a5402c049d2ec30a9143f19f9f63","abstract_canon_sha256":"906dc29a2a56309980bc696b7de12c7ea1dbf498c78665eacb97c96e3d8e409e"},"schema_version":"1.0"},"canonical_sha256":"cfc4ec3565b2b3d6d771d55ae01205dd54f35d57b17e98ab68bc0997b0e084b7","source":{"kind":"arxiv","id":"1505.05192","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.05192","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1505.05192v3","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05192","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"Z7COYNLFWKZ5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"Z7COYNLFWKZ5NV3R","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"Z7COYNLF","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:Z7COYNLFWKZ5NV3R2VNOAEQF3V","target":"record","payload":{"canonical_record":{"source":{"id":"1505.05192","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-19T21:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"7b9af53b7564fcf2ba5050e02f5cff002cd8a5402c049d2ec30a9143f19f9f63","abstract_canon_sha256":"906dc29a2a56309980bc696b7de12c7ea1dbf498c78665eacb97c96e3d8e409e"},"schema_version":"1.0"},"canonical_sha256":"cfc4ec3565b2b3d6d771d55ae01205dd54f35d57b17e98ab68bc0997b0e084b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:48.448444Z","signature_b64":"NQdXwUcrU/t7X/L28F47oQCxUIkZovPPYnrbTtjDS5f9ODJaik8KxbHC+07UWcqpKQ+VWYVymZWElEXWPzTwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc4ec3565b2b3d6d771d55ae01205dd54f35d57b17e98ab68bc0997b0e084b7","last_reissued_at":"2026-05-18T01:22:48.447783Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:48.447783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.05192","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OsixLwltOYwRvroNHJkoDF3ujpj+BqcF4MEVyaI6ESviURbusPdHT3YRv9rYbWn4pHEU0Cych0ZV6Qw+a7DVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:14:08.412008Z"},"content_sha256":"4f7f23b22bb425288bfcd8f46d823f5ee249519214f2eea127abfced119198d8","schema_version":"1.0","event_id":"sha256:4f7f23b22bb425288bfcd8f46d823f5ee249519214f2eea127abfced119198d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:Z7COYNLFWKZ5NV3R2VNOAEQF3V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Visual Representation Learning by Context Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Alexei A. Efros, Carl Doersch","submitted_at":"2015-05-19T21:18:17Z","abstract_excerpt":"This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image and train a convolutional neural net to predict the position of the second patch relative to the first. We argue that doing well on this task requires the model to learn to recognize objects and their parts. We demonstrate that the feature representation learned using this within-image context indeed captures visual similarity across images. For example, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05192","kind":"arxiv","version":3},"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":"2026-05-18T01:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WBz4o39ZuNBLIRjSVECL1D8lQxu5qpHqKt5D8qCeHZobbdtBMxTpTxjBSBpsTVijUvVHuJHR+cvovt9mmZh0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:14:08.412731Z"},"content_sha256":"8957aa5e0b1e7b49d5ff1dc66ab19a526084769b373e2f0e67ead81baaeaf048","schema_version":"1.0","event_id":"sha256:8957aa5e0b1e7b49d5ff1dc66ab19a526084769b373e2f0e67ead81baaeaf048"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V/bundle.json","state_url":"https://pith.science/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V/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":"2026-06-06T18:14:08Z","links":{"resolver":"https://pith.science/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V","bundle":"https://pith.science/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V/bundle.json","state":"https://pith.science/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z7COYNLFWKZ5NV3R2VNOAEQF3V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:Z7COYNLFWKZ5NV3R2VNOAEQF3V","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":"906dc29a2a56309980bc696b7de12c7ea1dbf498c78665eacb97c96e3d8e409e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-19T21:18:17Z","title_canon_sha256":"7b9af53b7564fcf2ba5050e02f5cff002cd8a5402c049d2ec30a9143f19f9f63"},"schema_version":"1.0","source":{"id":"1505.05192","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.05192","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1505.05192v3","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05192","created_at":"2026-05-18T01:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"Z7COYNLFWKZ5","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"Z7COYNLFWKZ5NV3R","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"Z7COYNLF","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:8957aa5e0b1e7b49d5ff1dc66ab19a526084769b373e2f0e67ead81baaeaf048","target":"graph","created_at":"2026-05-18T01:22:48Z","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":"This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image and train a convolutional neural net to predict the position of the second patch relative to the first. We argue that doing well on this task requires the model to learn to recognize objects and their parts. We demonstrate that the feature representation learned using this within-image context indeed captures visual similarity across images. For example, th","authors_text":"Abhinav Gupta, Alexei A. Efros, Carl Doersch","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-19T21:18:17Z","title":"Unsupervised Visual Representation Learning by Context Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05192","kind":"arxiv","version":3},"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":"sha256:4f7f23b22bb425288bfcd8f46d823f5ee249519214f2eea127abfced119198d8","target":"record","created_at":"2026-05-18T01:22:48Z","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":"906dc29a2a56309980bc696b7de12c7ea1dbf498c78665eacb97c96e3d8e409e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-19T21:18:17Z","title_canon_sha256":"7b9af53b7564fcf2ba5050e02f5cff002cd8a5402c049d2ec30a9143f19f9f63"},"schema_version":"1.0","source":{"id":"1505.05192","kind":"arxiv","version":3}},"canonical_sha256":"cfc4ec3565b2b3d6d771d55ae01205dd54f35d57b17e98ab68bc0997b0e084b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfc4ec3565b2b3d6d771d55ae01205dd54f35d57b17e98ab68bc0997b0e084b7","first_computed_at":"2026-05-18T01:22:48.447783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:22:48.447783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NQdXwUcrU/t7X/L28F47oQCxUIkZovPPYnrbTtjDS5f9ODJaik8KxbHC+07UWcqpKQ+VWYVymZWElEXWPzTwBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:22:48.448444Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.05192","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f7f23b22bb425288bfcd8f46d823f5ee249519214f2eea127abfced119198d8","sha256:8957aa5e0b1e7b49d5ff1dc66ab19a526084769b373e2f0e67ead81baaeaf048"],"state_sha256":"e6ab19c985063babfa1fded5d6763baa9ee5443a8fc9f7e5d3555760a22a481a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuiNmOAW0V/pCEn+N+ZBwCWS7bzdC73ZZ9ntVKyiL4PLuEWWlod6+Sx3EpMgVJfxvwUrNeZuDB8ZXZ62pC98DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:14:08.416663Z","bundle_sha256":"5e7915ac2e9b13d0631c8dcdeb2d6ac59d04244788be4f9eac08c279f6bc27d1"}}