{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BB5UJXXKWECG66D7E5EVE5BGV2","short_pith_number":"pith:BB5UJXXK","schema_version":"1.0","canonical_sha256":"087b44deeab1046f787f2749527426ae816a67da3fab9e342ba11ec32f2eefff","source":{"kind":"arxiv","id":"1604.03628","version":3},"attestation_state":"computed","paper":{"title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jianwei Yang","submitted_at":"2016-04-13T01:24:59Z","abstract_excerpt":"In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent process, stacked on top of representations output by a Convolutional Neural Network (CNN). During training, image clusters and representations are updated jointly: image clustering is conducted in the forward pass, while representation learning in the backward pass. Our key idea behind this framework is that good representations are beneficial to image clustering"},"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":"1604.03628","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-13T01:24:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e7be90c9973d055075c511423ccf9af91bc00df840f6ae168532929073408f37","abstract_canon_sha256":"0bed3d6e67ab4c96d6faa66b2c0851dc2784656e790025fa6c148d6cc7bfba1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:16.636956Z","signature_b64":"Emc7xb6rRinAIvdAExpv3dWe1URKZA2C12zD9WOE47ou2rTYMQoTsr7i1ycXS3MCkqFEc0wl30DS+7x6lEp1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"087b44deeab1046f787f2749527426ae816a67da3fab9e342ba11ec32f2eefff","last_reissued_at":"2026-05-18T01:12:16.636560Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:16.636560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jianwei Yang","submitted_at":"2016-04-13T01:24:59Z","abstract_excerpt":"In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent process, stacked on top of representations output by a Convolutional Neural Network (CNN). During training, image clusters and representations are updated jointly: image clustering is conducted in the forward pass, while representation learning in the backward pass. Our key idea behind this framework is that good representations are beneficial to image clustering"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03628","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1604.03628","created_at":"2026-05-18T01:12:16.636615+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.03628v3","created_at":"2026-05-18T01:12:16.636615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03628","created_at":"2026-05-18T01:12:16.636615+00:00"},{"alias_kind":"pith_short_12","alias_value":"BB5UJXXKWECG","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BB5UJXXKWECG66D7","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BB5UJXXK","created_at":"2026-05-18T12:30:07.202191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.21743","citing_title":"Cohort Organized Learning: Clustering Through Agreement","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2","json":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2.json","graph_json":"https://pith.science/api/pith-number/BB5UJXXKWECG66D7E5EVE5BGV2/graph.json","events_json":"https://pith.science/api/pith-number/BB5UJXXKWECG66D7E5EVE5BGV2/events.json","paper":"https://pith.science/paper/BB5UJXXK"},"agent_actions":{"view_html":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2","download_json":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2.json","view_paper":"https://pith.science/paper/BB5UJXXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.03628&json=true","fetch_graph":"https://pith.science/api/pith-number/BB5UJXXKWECG66D7E5EVE5BGV2/graph.json","fetch_events":"https://pith.science/api/pith-number/BB5UJXXKWECG66D7E5EVE5BGV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2/action/storage_attestation","attest_author":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2/action/author_attestation","sign_citation":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2/action/citation_signature","submit_replication":"https://pith.science/pith/BB5UJXXKWECG66D7E5EVE5BGV2/action/replication_record"}},"created_at":"2026-05-18T01:12:16.636615+00:00","updated_at":"2026-05-18T01:12:16.636615+00:00"}