{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OTJDXGUIQOWOXABZGSMX4WVR5B","short_pith_number":"pith:OTJDXGUI","schema_version":"1.0","canonical_sha256":"74d23b9a8883aceb803934997e5ab1e84800f27aee2a0bb99757a3c74f1241c9","source":{"kind":"arxiv","id":"2310.02279","version":3},"attestation_state":"computed","paper":{"title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Wei-Hsiang Liao, Yuhta Takida, Yuki Mitsufuji, Yutong He","submitted_at":"2023-10-01T05:07:17Z","abstract_excerpt":"Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion pro"},"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":"2310.02279","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T05:07:17Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"7db72a01efbaa8f094beb84903b0741533eade5265cc1ef329bf7cd4ffcaf839","abstract_canon_sha256":"5c019c832956e7b302324e3a33c180889d560bc68bd34ae14a3548e76440a5fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:21.772748Z","signature_b64":"HW6Oiv56zGWrScig3L2vSflBPUdU640Y/tGSKTXKNULVkVTx+EL2n5xm5lTHfAhBX3c9e2AEsGjLAiOpSQbTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d23b9a8883aceb803934997e5ab1e84800f27aee2a0bb99757a3c74f1241c9","last_reissued_at":"2026-07-05T08:02:21.772187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:21.772187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Wei-Hsiang Liao, Yuhta Takida, Yuki Mitsufuji, Yutong He","submitted_at":"2023-10-01T05:07:17Z","abstract_excerpt":"Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02279","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.02279/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":"2310.02279","created_at":"2026-07-05T08:02:21.772238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02279v3","created_at":"2026-07-05T08:02:21.772238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02279","created_at":"2026-07-05T08:02:21.772238+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTJDXGUIQOWO","created_at":"2026-07-05T08:02:21.772238+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTJDXGUIQOWOXABZ","created_at":"2026-07-05T08:02:21.772238+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTJDXGUI","created_at":"2026-07-05T08:02:21.772238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25473","citing_title":"Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18478","citing_title":"Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10450","citing_title":"Few-step Generative Models as Lossy Compression","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08375","citing_title":"Few-step Cofolding with All-Atom Flow Maps","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05327","citing_title":"Multimarginal flow matching with optimal transport potentials","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19729","citing_title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04938","citing_title":"Improved DDIM Sampling with Moment Matching Gaussian Mixtures","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2412.15689","citing_title":"DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19729","citing_title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17042","citing_title":"Thermal-Only Crowd Counting with Deployment-Time Privacy Protection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18190","citing_title":"Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17834","citing_title":"Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19729","citing_title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08431","citing_title":"Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10764","citing_title":"Dual-End Consistency Model","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08511","citing_title":"Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22379","citing_title":"Efficient Diffusion Distillation via Embedding Loss","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05975","citing_title":"Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19238","citing_title":"Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07327","citing_title":"Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B","json":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B.json","graph_json":"https://pith.science/api/pith-number/OTJDXGUIQOWOXABZGSMX4WVR5B/graph.json","events_json":"https://pith.science/api/pith-number/OTJDXGUIQOWOXABZGSMX4WVR5B/events.json","paper":"https://pith.science/paper/OTJDXGUI"},"agent_actions":{"view_html":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B","download_json":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B.json","view_paper":"https://pith.science/paper/OTJDXGUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02279&json=true","fetch_graph":"https://pith.science/api/pith-number/OTJDXGUIQOWOXABZGSMX4WVR5B/graph.json","fetch_events":"https://pith.science/api/pith-number/OTJDXGUIQOWOXABZGSMX4WVR5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B/action/storage_attestation","attest_author":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B/action/author_attestation","sign_citation":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B/action/citation_signature","submit_replication":"https://pith.science/pith/OTJDXGUIQOWOXABZGSMX4WVR5B/action/replication_record"}},"created_at":"2026-07-05T08:02:21.772238+00:00","updated_at":"2026-07-05T08:02:21.772238+00:00"}