{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RZXD5ZY7WY7MJXP2RA7H4INWAT","short_pith_number":"pith:RZXD5ZY7","canonical_record":{"source":{"id":"2103.00787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-01T06:24:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25bf3f258cadfc7addcee0def286916b77b3e5308c7d730d5a08c63395f8e4aa","abstract_canon_sha256":"df85c074b9b6209f6fd31e25ab969e89f34f8db0822bb1f3b2a790611470f09c"},"schema_version":"1.0"},"canonical_sha256":"8e6e3ee71fb63ec4ddfa883e7e21b604ca7eec141a8ce1683bc7c58430f207b6","source":{"kind":"arxiv","id":"2103.00787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00787","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00787v1","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00787","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"RZXD5ZY7WY7M","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"RZXD5ZY7WY7MJXP2","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"RZXD5ZY7","created_at":"2026-07-05T02:19:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RZXD5ZY7WY7MJXP2RA7H4INWAT","target":"record","payload":{"canonical_record":{"source":{"id":"2103.00787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-01T06:24:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25bf3f258cadfc7addcee0def286916b77b3e5308c7d730d5a08c63395f8e4aa","abstract_canon_sha256":"df85c074b9b6209f6fd31e25ab969e89f34f8db0822bb1f3b2a790611470f09c"},"schema_version":"1.0"},"canonical_sha256":"8e6e3ee71fb63ec4ddfa883e7e21b604ca7eec141a8ce1683bc7c58430f207b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:09.543968Z","signature_b64":"2GhWJ3lgvce08Owyz2tximPGGrWZMs4h0BdN/Db2bh2VMbqbKlLArllekkOT9FfgjWPvW07zb5dxmwFkyE/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e6e3ee71fb63ec4ddfa883e7e21b604ca7eec141a8ce1683bc7c58430f207b6","last_reissued_at":"2026-07-05T02:19:09.543533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:09.543533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.00787","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":"2026-07-05T02:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCuRoRWpHgawkOyjfz6+KH4lokGkWUdHwxkRPgVWpe1ZxSnttkxaiBAZvEXIi6MQSOtSMWjznaPRpDr/AnBdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:44:01.524168Z"},"content_sha256":"abd5ab0fe1c4e9b39eab148ed80dd89da65acdebf154a54f344cc4f53a367cc2","schema_version":"1.0","event_id":"sha256:abd5ab0fe1c4e9b39eab148ed80dd89da65acdebf154a54f344cc4f53a367cc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RZXD5ZY7WY7MJXP2RA7H4INWAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Wei Hu, Xiang Gao","submitted_at":"2021-03-01T06:24:17Z","abstract_excerpt":"3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have performed best so far. However, feature learning of multiple views in existing methods is mostly performed in a supervised fashion, which often requires a large amount of data labels with high costs. In contrast, self-supervised learning aims to learn multi-view feature representations without involving labeled data. To this end, we propose a novel self-supervised p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00787","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.00787/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":"2026-07-05T02:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CePBF3H6Jtf/wX5RzNfBP10YxwHu7i0M7250N9MQhrHkHOwLfCrJSYg7gw92F2Nvl11ZUtKKYXl9SpOUcdoQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:44:01.524738Z"},"content_sha256":"7ea55749f5fe4c066e81b7c3d6aecf91bcc587be9b2fdff80c18e7f779750f53","schema_version":"1.0","event_id":"sha256:7ea55749f5fe4c066e81b7c3d6aecf91bcc587be9b2fdff80c18e7f779750f53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT/bundle.json","state_url":"https://pith.science/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT/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":"2026-08-03T20:44:01Z","links":{"resolver":"https://pith.science/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT","bundle":"https://pith.science/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT/bundle.json","state":"https://pith.science/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZXD5ZY7WY7MJXP2RA7H4INWAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RZXD5ZY7WY7MJXP2RA7H4INWAT","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":"df85c074b9b6209f6fd31e25ab969e89f34f8db0822bb1f3b2a790611470f09c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-01T06:24:17Z","title_canon_sha256":"25bf3f258cadfc7addcee0def286916b77b3e5308c7d730d5a08c63395f8e4aa"},"schema_version":"1.0","source":{"id":"2103.00787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00787","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00787v1","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00787","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"RZXD5ZY7WY7M","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"RZXD5ZY7WY7MJXP2","created_at":"2026-07-05T02:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"RZXD5ZY7","created_at":"2026-07-05T02:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:7ea55749f5fe4c066e81b7c3d6aecf91bcc587be9b2fdff80c18e7f779750f53","target":"graph","created_at":"2026-07-05T02:19:09Z","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/2103.00787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have performed best so far. However, feature learning of multiple views in existing methods is mostly performed in a supervised fashion, which often requires a large amount of data labels with high costs. In contrast, self-supervised learning aims to learn multi-view feature representations without involving labeled data. To this end, we propose a novel self-supervised p","authors_text":"Guo-jun Qi, Wei Hu, Xiang Gao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-01T06:24:17Z","title":"Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00787","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:abd5ab0fe1c4e9b39eab148ed80dd89da65acdebf154a54f344cc4f53a367cc2","target":"record","created_at":"2026-07-05T02:19:09Z","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":"df85c074b9b6209f6fd31e25ab969e89f34f8db0822bb1f3b2a790611470f09c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-01T06:24:17Z","title_canon_sha256":"25bf3f258cadfc7addcee0def286916b77b3e5308c7d730d5a08c63395f8e4aa"},"schema_version":"1.0","source":{"id":"2103.00787","kind":"arxiv","version":1}},"canonical_sha256":"8e6e3ee71fb63ec4ddfa883e7e21b604ca7eec141a8ce1683bc7c58430f207b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e6e3ee71fb63ec4ddfa883e7e21b604ca7eec141a8ce1683bc7c58430f207b6","first_computed_at":"2026-07-05T02:19:09.543533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:19:09.543533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GhWJ3lgvce08Owyz2tximPGGrWZMs4h0BdN/Db2bh2VMbqbKlLArllekkOT9FfgjWPvW07zb5dxmwFkyE/uDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:19:09.543968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.00787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abd5ab0fe1c4e9b39eab148ed80dd89da65acdebf154a54f344cc4f53a367cc2","sha256:7ea55749f5fe4c066e81b7c3d6aecf91bcc587be9b2fdff80c18e7f779750f53"],"state_sha256":"9dc348c0e429df941d1b4184f6cfe824b9ad6605f8263c23d2c9030f575884ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMtqydDRaOGqgHnd6yNL+Y6sayQLBlD3ONx7loKY7lHa1rM97kvtdRH9xh0wUfOxzKmdO9b5pNwrfaOL8sR9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:44:01.531007Z","bundle_sha256":"5301272713079280982dc21630b1b9ccd1107632e000ad8eb54077a48b622b4c"}}