{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XKJAOVPR6NKE56B4RCRV7W73B5","short_pith_number":"pith:XKJAOVPR","schema_version":"1.0","canonical_sha256":"ba920755f1f3544ef83c88a35fdbfb0f5ce33174cfe00c8c9b4ca72190ffa8fe","source":{"kind":"arxiv","id":"2502.00382","version":1},"attestation_state":"computed","paper":{"title":"Masked Generative Nested Transformers with Decode Time Scaling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain, Sahil Goyal, Sujoy Paul","submitted_at":"2025-02-01T09:41:01Z","abstract_excerpt":"Recent advances in visual generation have made significant strides in producing content of exceptional quality. However, most methods suffer from a fundamental problem - a bottleneck of inference computational efficiency. Most of these algorithms involve multiple passes over a transformer model to generate tokens or denoise inputs. However, the model size is kept consistent throughout all iterations, which makes it computationally expensive. In this work, we aim to address this issue primarily through two key ideas - (a) not all parts of the generation process need equal compute, and we design"},"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":"2502.00382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T09:41:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9bd752a9debcc6bd4d9cd1eca736f8f8b6948f3ccd39a9d64807c5357f1bdf3d","abstract_canon_sha256":"08ff968dca41769efe23e1c1f4be1ed73e89411057b441f7a7852691adb81a1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:32.959560Z","signature_b64":"ed5LfZ8xhXA/7Lf/xJ2KfZnAFkSC8NNSJIzjqArVAiXUGXAx7MuWkLEMz1e+IE8JJI44iIhU1IpQohLSwZ6EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba920755f1f3544ef83c88a35fdbfb0f5ce33174cfe00c8c9b4ca72190ffa8fe","last_reissued_at":"2026-07-05T10:08:32.959149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:32.959149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Generative Nested Transformers with Decode Time Scaling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Debapriya Tula, Gagan Jain, Pradeep Shenoy, Prateek Jain, Sahil Goyal, Sujoy Paul","submitted_at":"2025-02-01T09:41:01Z","abstract_excerpt":"Recent advances in visual generation have made significant strides in producing content of exceptional quality. However, most methods suffer from a fundamental problem - a bottleneck of inference computational efficiency. Most of these algorithms involve multiple passes over a transformer model to generate tokens or denoise inputs. However, the model size is kept consistent throughout all iterations, which makes it computationally expensive. In this work, we aim to address this issue primarily through two key ideas - (a) not all parts of the generation process need equal compute, and we design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00382","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/2502.00382/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":"2502.00382","created_at":"2026-07-05T10:08:32.959204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00382v1","created_at":"2026-07-05T10:08:32.959204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00382","created_at":"2026-07-05T10:08:32.959204+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKJAOVPR6NKE","created_at":"2026-07-05T10:08:32.959204+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKJAOVPR6NKE56B4","created_at":"2026-07-05T10:08:32.959204+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKJAOVPR","created_at":"2026-07-05T10:08:32.959204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5","json":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5.json","graph_json":"https://pith.science/api/pith-number/XKJAOVPR6NKE56B4RCRV7W73B5/graph.json","events_json":"https://pith.science/api/pith-number/XKJAOVPR6NKE56B4RCRV7W73B5/events.json","paper":"https://pith.science/paper/XKJAOVPR"},"agent_actions":{"view_html":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5","download_json":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5.json","view_paper":"https://pith.science/paper/XKJAOVPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00382&json=true","fetch_graph":"https://pith.science/api/pith-number/XKJAOVPR6NKE56B4RCRV7W73B5/graph.json","fetch_events":"https://pith.science/api/pith-number/XKJAOVPR6NKE56B4RCRV7W73B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5/action/storage_attestation","attest_author":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5/action/author_attestation","sign_citation":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5/action/citation_signature","submit_replication":"https://pith.science/pith/XKJAOVPR6NKE56B4RCRV7W73B5/action/replication_record"}},"created_at":"2026-07-05T10:08:32.959204+00:00","updated_at":"2026-07-05T10:08:32.959204+00:00"}