{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ERCSMM3UOELS25DI4FHDY7SRDB","short_pith_number":"pith:ERCSMM3U","schema_version":"1.0","canonical_sha256":"244526337471172d7468e14e3c7e511856f78126fe057309c5fbc3b2a041bffb","source":{"kind":"arxiv","id":"2012.03044","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Visual Representation Learning from Hierarchical Grouping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Maire, Xiao Zhang","submitted_at":"2020-12-05T14:54:08Z","abstract_excerpt":"We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partitions an image into regions, followed by merging of those regions into a tree hierarchy. A small supervised dataset suffices for training this grouping primitive. Across a large unlabeled dataset, we apply this learned primitive to automatically predict hierarchical region structure. These predictions serve as guidance for self-supervised contrastive feature learning: we task a deep network with producing per-pixel embed"},"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":"2012.03044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-05T14:54:08Z","cross_cats_sorted":[],"title_canon_sha256":"56f81abecec6c7075299c2692e54e8fca90d24ad038ea09856b2fa05cd57b464","abstract_canon_sha256":"f179c22a6024820c363f0c59ba69b4d1c4de78da6528c0f710cb4d3d680e1df4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:25.247986Z","signature_b64":"SKSmXM2OcxgqMJmS+bPQd8eJHCgyyTGsrg/dvEdcC9exkN4vj09FEz4crIu+uRzrhVtRrjYF4m4ALFzOmnUOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244526337471172d7468e14e3c7e511856f78126fe057309c5fbc3b2a041bffb","last_reissued_at":"2026-07-05T01:57:25.247624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:25.247624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Visual Representation Learning from Hierarchical Grouping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Maire, Xiao Zhang","submitted_at":"2020-12-05T14:54:08Z","abstract_excerpt":"We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partitions an image into regions, followed by merging of those regions into a tree hierarchy. A small supervised dataset suffices for training this grouping primitive. Across a large unlabeled dataset, we apply this learned primitive to automatically predict hierarchical region structure. These predictions serve as guidance for self-supervised contrastive feature learning: we task a deep network with producing per-pixel embed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03044","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/2012.03044/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":"2012.03044","created_at":"2026-07-05T01:57:25.247679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.03044v1","created_at":"2026-07-05T01:57:25.247679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03044","created_at":"2026-07-05T01:57:25.247679+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERCSMM3UOELS","created_at":"2026-07-05T01:57:25.247679+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERCSMM3UOELS25DI","created_at":"2026-07-05T01:57:25.247679+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERCSMM3U","created_at":"2026-07-05T01:57:25.247679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB","json":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB.json","graph_json":"https://pith.science/api/pith-number/ERCSMM3UOELS25DI4FHDY7SRDB/graph.json","events_json":"https://pith.science/api/pith-number/ERCSMM3UOELS25DI4FHDY7SRDB/events.json","paper":"https://pith.science/paper/ERCSMM3U"},"agent_actions":{"view_html":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB","download_json":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB.json","view_paper":"https://pith.science/paper/ERCSMM3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.03044&json=true","fetch_graph":"https://pith.science/api/pith-number/ERCSMM3UOELS25DI4FHDY7SRDB/graph.json","fetch_events":"https://pith.science/api/pith-number/ERCSMM3UOELS25DI4FHDY7SRDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB/action/storage_attestation","attest_author":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB/action/author_attestation","sign_citation":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB/action/citation_signature","submit_replication":"https://pith.science/pith/ERCSMM3UOELS25DI4FHDY7SRDB/action/replication_record"}},"created_at":"2026-07-05T01:57:25.247679+00:00","updated_at":"2026-07-05T01:57:25.247679+00:00"}