{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XPUIAWJYKDCL3VZ7AEJVG6BF7F","short_pith_number":"pith:XPUIAWJY","canonical_record":{"source":{"id":"2011.05499","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-11T01:28:11Z","cross_cats_sorted":[],"title_canon_sha256":"410d9fcf95fe8881eac4a8175f988d21cbe882c9fff9374164c79df9249778c2","abstract_canon_sha256":"4cd62ba39c04c2411788abbeb8afeca7e3112ad7213babd9a26e952ec2b452cd"},"schema_version":"1.0"},"canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","source":{"kind":"arxiv","id":"2011.05499","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05499","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05499v2","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05499","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"XPUIAWJYKDCL","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"XPUIAWJYKDCL3VZ7","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"XPUIAWJY","created_at":"2026-07-05T01:57:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XPUIAWJYKDCL3VZ7AEJVG6BF7F","target":"record","payload":{"canonical_record":{"source":{"id":"2011.05499","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-11T01:28:11Z","cross_cats_sorted":[],"title_canon_sha256":"410d9fcf95fe8881eac4a8175f988d21cbe882c9fff9374164c79df9249778c2","abstract_canon_sha256":"4cd62ba39c04c2411788abbeb8afeca7e3112ad7213babd9a26e952ec2b452cd"},"schema_version":"1.0"},"canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:36.586560Z","signature_b64":"ljO3DnCtP3YGr3GdzNRhKFOf3rFLvdPQvVvRCxkEh8PGjNptDwRvFXPYtPFG46L8jE8wPv76t+MJAxttpnnaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","last_reissued_at":"2026-07-05T01:57:36.586081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:36.586081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.05499","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yP2zsP9zC9Y+WurIt5ndYkWm9XFJ2CJO0iS0AKedl9WcvoXR46l5EQu5luBkOm+lhwmPuYzT8FrZPg4OpUgMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:21.747018Z"},"content_sha256":"573e0a8f11164df2a85f59d602632b75cf5a2bf8d4f1c7b8385d7f4cbd3386ef","schema_version":"1.0","event_id":"sha256:573e0a8f11164df2a85f59d602632b75cf5a2bf8d4f1c7b8385d7f4cbd3386ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XPUIAWJYKDCL3VZ7AEJVG6BF7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Learning of Dense Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Amjad Almahairi, Florian Golemo, Pedro O. Pinheiro, Ryan Y. Benmalek","submitted_at":"2020-11-11T01:28:11Z","abstract_excerpt":"Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05499","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.05499/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPkzhOBE7eK3ThVzjyE82Lon0zvAy325FfLWxVUTfWh8lk52HMKCaG1mQ7A5k/cuELYiztDGB/ufRcHzUBN/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:21.747526Z"},"content_sha256":"c6ac3a6e2f59dbb719e515d120a1c2784b4a1ed414d355cb389ae340077752ac","schema_version":"1.0","event_id":"sha256:c6ac3a6e2f59dbb719e515d120a1c2784b4a1ed414d355cb389ae340077752ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/bundle.json","state_url":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/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":"2026-08-08T13:12:21Z","links":{"resolver":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F","bundle":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/bundle.json","state":"https://pith.science/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPUIAWJYKDCL3VZ7AEJVG6BF7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XPUIAWJYKDCL3VZ7AEJVG6BF7F","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":"4cd62ba39c04c2411788abbeb8afeca7e3112ad7213babd9a26e952ec2b452cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-11T01:28:11Z","title_canon_sha256":"410d9fcf95fe8881eac4a8175f988d21cbe882c9fff9374164c79df9249778c2"},"schema_version":"1.0","source":{"id":"2011.05499","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05499","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05499v2","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05499","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"XPUIAWJYKDCL","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_16","alias_value":"XPUIAWJYKDCL3VZ7","created_at":"2026-07-05T01:57:36Z"},{"alias_kind":"pith_short_8","alias_value":"XPUIAWJY","created_at":"2026-07-05T01:57:36Z"}],"graph_snapshots":[{"event_id":"sha256:c6ac3a6e2f59dbb719e515d120a1c2784b4a1ed414d355cb389ae340077752ac","target":"graph","created_at":"2026-07-05T01:57:36Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.05499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewi","authors_text":"Aaron Courville, Amjad Almahairi, Florian Golemo, Pedro O. Pinheiro, Ryan Y. Benmalek","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-11T01:28:11Z","title":"Unsupervised Learning of Dense Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05499","kind":"arxiv","version":2},"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":"sha256:573e0a8f11164df2a85f59d602632b75cf5a2bf8d4f1c7b8385d7f4cbd3386ef","target":"record","created_at":"2026-07-05T01:57:36Z","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":"4cd62ba39c04c2411788abbeb8afeca7e3112ad7213babd9a26e952ec2b452cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-11T01:28:11Z","title_canon_sha256":"410d9fcf95fe8881eac4a8175f988d21cbe882c9fff9374164c79df9249778c2"},"schema_version":"1.0","source":{"id":"2011.05499","kind":"arxiv","version":2}},"canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbe880593850c4bdd73f0113537825f96dd09e59be41aaba75562bf66c2a41d9","first_computed_at":"2026-07-05T01:57:36.586081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:36.586081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ljO3DnCtP3YGr3GdzNRhKFOf3rFLvdPQvVvRCxkEh8PGjNptDwRvFXPYtPFG46L8jE8wPv76t+MJAxttpnnaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:36.586560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05499","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:573e0a8f11164df2a85f59d602632b75cf5a2bf8d4f1c7b8385d7f4cbd3386ef","sha256:c6ac3a6e2f59dbb719e515d120a1c2784b4a1ed414d355cb389ae340077752ac"],"state_sha256":"c9b9ef089e9904959d6b9124ed572d7f06296156b31097deeb06f4f4b9342e6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fgM9A2nCL0cmnwu8OjMbBjqUwzP6a7ahmk1GJIQZT9tW1qKpl0rym3vzUW5hJ1it4Lvkuoy9cTrOn7eMF2c4DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:12:21.752455Z","bundle_sha256":"d4e5c5d97ad8522735507f8980cbb80d98fe19a7eca52bf7fbf96d317bfc4834"}}