{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UGZJULBAZQBOBKGTDNJL7XQXJV","short_pith_number":"pith:UGZJULBA","schema_version":"1.0","canonical_sha256":"a1b29a2c20cc02e0a8d31b52bfde174d7f31f745ec52cbbea3b510b7109ee6a8","source":{"kind":"arxiv","id":"2401.11430","version":1},"attestation_state":"computed","paper":{"title":"Exploring Diffusion Time-steps for Unsupervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric I-Chao Chang, Hanwang Zhang, Jiankun Wang, Lei Ji, Qianru Sun, Zhongqi Yue","submitted_at":"2024-01-21T08:35:25Z","abstract_excerpt":"Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes. We build a theoretical framework that connects the diffusion time-steps and the hidden attributes, which serves as an effective inductive bias for unsupervised learning. Specifically, the forward diffusion process incrementally adds Gaussian noise to samples at each time-step, which essentially collapses different samples into similar ones by losing attribute"},"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":"2401.11430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-21T08:35:25Z","cross_cats_sorted":[],"title_canon_sha256":"73f8cb7374eacdd0fb508d508e3eac255517c37ce7ea289c3cb048bf0c1c76ff","abstract_canon_sha256":"b8747ebabc531789ba5bb9f2104748ebdb26a2c24c1fef18370eb8c236dce912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:50.696969Z","signature_b64":"D1RjzvvaX5DT3Eoz8jHvQ86v/AbRu9JtJwZAHFKZrGoE6NqiN8MHcXMYlD7U6d7emCLaZ4m8QcBIlHbX9uioDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1b29a2c20cc02e0a8d31b52bfde174d7f31f745ec52cbbea3b510b7109ee6a8","last_reissued_at":"2026-07-05T07:35:50.696443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:50.696443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Diffusion Time-steps for Unsupervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric I-Chao Chang, Hanwang Zhang, Jiankun Wang, Lei Ji, Qianru Sun, Zhongqi Yue","submitted_at":"2024-01-21T08:35:25Z","abstract_excerpt":"Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes. We build a theoretical framework that connects the diffusion time-steps and the hidden attributes, which serves as an effective inductive bias for unsupervised learning. Specifically, the forward diffusion process incrementally adds Gaussian noise to samples at each time-step, which essentially collapses different samples into similar ones by losing attribute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11430","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/2401.11430/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":"2401.11430","created_at":"2026-07-05T07:35:50.696508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11430v1","created_at":"2026-07-05T07:35:50.696508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11430","created_at":"2026-07-05T07:35:50.696508+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGZJULBAZQBO","created_at":"2026-07-05T07:35:50.696508+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGZJULBAZQBOBKGT","created_at":"2026-07-05T07:35:50.696508+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGZJULBA","created_at":"2026-07-05T07:35:50.696508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09250","citing_title":"LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13013","citing_title":"JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV","json":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV.json","graph_json":"https://pith.science/api/pith-number/UGZJULBAZQBOBKGTDNJL7XQXJV/graph.json","events_json":"https://pith.science/api/pith-number/UGZJULBAZQBOBKGTDNJL7XQXJV/events.json","paper":"https://pith.science/paper/UGZJULBA"},"agent_actions":{"view_html":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV","download_json":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV.json","view_paper":"https://pith.science/paper/UGZJULBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11430&json=true","fetch_graph":"https://pith.science/api/pith-number/UGZJULBAZQBOBKGTDNJL7XQXJV/graph.json","fetch_events":"https://pith.science/api/pith-number/UGZJULBAZQBOBKGTDNJL7XQXJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV/action/storage_attestation","attest_author":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV/action/author_attestation","sign_citation":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV/action/citation_signature","submit_replication":"https://pith.science/pith/UGZJULBAZQBOBKGTDNJL7XQXJV/action/replication_record"}},"created_at":"2026-07-05T07:35:50.696508+00:00","updated_at":"2026-07-05T07:35:50.696508+00:00"}