{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CJTXKFUNYLJ2T6VZCQ55DIK54","short_pith_number":"pith:2CJTXKFU","schema_version":"1.0","canonical_sha256":"d0933ba8b46e169d4fd5c8a1de8d0aef2651796eac0d0c0701fbceb8d4f05519","source":{"kind":"arxiv","id":"2402.19159","version":2},"attestation_state":"computed","paper":{"title":"Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Chaoyue Wang, Dacheng Tao, Jianbin Zheng, Minghui Hu, Tat-Jen Cham, Zhongyi Fan","submitted_at":"2024-02-29T13:44:14Z","abstract_excerpt":"Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the parameterisation and distillation errors by broadening the scope of the self-"},"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":"2402.19159","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T13:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"7b26ab45215c3d6e3e2c98076dcc5d17fb373e9c310c7602e35f65494431dc00","abstract_canon_sha256":"a72a418bdb93729364359890a16c55573ebffcf41479ff95761bfe899db33f4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:02.056912Z","signature_b64":"82whZCkR060xhQdH3vQcfY6EjaAFZfiXp/DsaIQ2uN4iE7RcLy1HBudPZ0bQeSc7aZnQuJPZKY/raatAIvN3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0933ba8b46e169d4fd5c8a1de8d0aef2651796eac0d0c0701fbceb8d4f05519","last_reissued_at":"2026-07-05T08:08:02.056444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:02.056444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Chaoyue Wang, Dacheng Tao, Jianbin Zheng, Minghui Hu, Tat-Jen Cham, Zhongyi Fan","submitted_at":"2024-02-29T13:44:14Z","abstract_excerpt":"Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the parameterisation and distillation errors by broadening the scope of the self-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19159","kind":"arxiv","version":2},"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/2402.19159/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":"2402.19159","created_at":"2026-07-05T08:08:02.056503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19159v2","created_at":"2026-07-05T08:08:02.056503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19159","created_at":"2026-07-05T08:08:02.056503+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CJTXKFUNYLJ","created_at":"2026-07-05T08:08:02.056503+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CJTXKFUNYLJ2T6V","created_at":"2026-07-05T08:08:02.056503+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CJTXKFU","created_at":"2026-07-05T08:08:02.056503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06609","citing_title":"D2PO: Optimizing Diffusion Samplers via Dynamic Preference","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22394","citing_title":"Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05327","citing_title":"Multimarginal flow matching with optimal transport potentials","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01651","citing_title":"Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28226","citing_title":"Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15190","citing_title":"RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32020","citing_title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2505.02242","citing_title":"Sampling-Aware Quantization for Diffusion Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06376","citing_title":"Continuous-Time Distribution Matching for Few-Step Diffusion Distillation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08837","citing_title":"Discrete Meanflow Training Curriculum","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08828","citing_title":"Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54","json":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54.json","graph_json":"https://pith.science/api/pith-number/2CJTXKFUNYLJ2T6VZCQ55DIK54/graph.json","events_json":"https://pith.science/api/pith-number/2CJTXKFUNYLJ2T6VZCQ55DIK54/events.json","paper":"https://pith.science/paper/2CJTXKFU"},"agent_actions":{"view_html":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54","download_json":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54.json","view_paper":"https://pith.science/paper/2CJTXKFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19159&json=true","fetch_graph":"https://pith.science/api/pith-number/2CJTXKFUNYLJ2T6VZCQ55DIK54/graph.json","fetch_events":"https://pith.science/api/pith-number/2CJTXKFUNYLJ2T6VZCQ55DIK54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54/action/storage_attestation","attest_author":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54/action/author_attestation","sign_citation":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54/action/citation_signature","submit_replication":"https://pith.science/pith/2CJTXKFUNYLJ2T6VZCQ55DIK54/action/replication_record"}},"created_at":"2026-07-05T08:08:02.056503+00:00","updated_at":"2026-07-05T08:08:02.056503+00:00"}