{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RNVCDRURG2VZI6M6AXZXJW2OXO","short_pith_number":"pith:RNVCDRUR","schema_version":"1.0","canonical_sha256":"8b6a21c69136ab94799e05f374db4ebba6ba80e34e69bb07bbb051bb9b5b89f0","source":{"kind":"arxiv","id":"2006.02598","version":2},"attestation_state":"computed","paper":{"title":"Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aditya Sanghi","submitted_at":"2020-06-04T00:30:26Z","abstract_excerpt":"A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use datasets that are aligned, require objects to be reconstructed and suffer from deteriorated performance on downstream tasks. To solve these issues, we propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the mutual information between 3D objects and their \"chunks\" to improve the representations in aligned da"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.02598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-04T00:30:26Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"ba4b784a935407cbbd7c2142adc87869762de2b5fc9b0b124f2daa2f656e98c0","abstract_canon_sha256":"7738d259bdb161ebe12e65854b13a77880450ef34bf87dd5efc72bb25c970539"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:12.654375Z","signature_b64":"XdXM2rL87a/jsQbjSZ8DmV03LWofWn2Hav33/lzrpuWE66YQpGCziv6C/3RDIb3E4TEmevvRhsWRxKSHiGZqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6a21c69136ab94799e05f374db4ebba6ba80e34e69bb07bbb051bb9b5b89f0","last_reissued_at":"2026-07-05T01:29:12.653975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:12.653975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aditya Sanghi","submitted_at":"2020-06-04T00:30:26Z","abstract_excerpt":"A major endeavor of computer vision is to represent, understand and extract structure from 3D data. Towards this goal, unsupervised learning is a powerful and necessary tool. Most current unsupervised methods for 3D shape analysis use datasets that are aligned, require objects to be reconstructed and suffer from deteriorated performance on downstream tasks. To solve these issues, we propose to extend the InfoMax and contrastive learning principles on 3D shapes. We show that we can maximize the mutual information between 3D objects and their \"chunks\" to improve the representations in aligned da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02598","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/2006.02598/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.02598","created_at":"2026-07-05T01:29:12.654029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.02598v2","created_at":"2026-07-05T01:29:12.654029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02598","created_at":"2026-07-05T01:29:12.654029+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNVCDRURG2VZ","created_at":"2026-07-05T01:29:12.654029+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNVCDRURG2VZI6M6","created_at":"2026-07-05T01:29:12.654029+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNVCDRUR","created_at":"2026-07-05T01:29:12.654029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24641","citing_title":"A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO","json":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO.json","graph_json":"https://pith.science/api/pith-number/RNVCDRURG2VZI6M6AXZXJW2OXO/graph.json","events_json":"https://pith.science/api/pith-number/RNVCDRURG2VZI6M6AXZXJW2OXO/events.json","paper":"https://pith.science/paper/RNVCDRUR"},"agent_actions":{"view_html":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO","download_json":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO.json","view_paper":"https://pith.science/paper/RNVCDRUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.02598&json=true","fetch_graph":"https://pith.science/api/pith-number/RNVCDRURG2VZI6M6AXZXJW2OXO/graph.json","fetch_events":"https://pith.science/api/pith-number/RNVCDRURG2VZI6M6AXZXJW2OXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO/action/storage_attestation","attest_author":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO/action/author_attestation","sign_citation":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO/action/citation_signature","submit_replication":"https://pith.science/pith/RNVCDRURG2VZI6M6AXZXJW2OXO/action/replication_record"}},"created_at":"2026-07-05T01:29:12.654029+00:00","updated_at":"2026-07-05T01:29:12.654029+00:00"}