{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3LWRQL5DBSYKJ2UA2JJUY5GDX6","short_pith_number":"pith:3LWRQL5D","canonical_record":{"source":{"id":"2412.16822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T02:04:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ee574f5ea35818ff7790dfaaa2c89116fb904d985e9dbdfa8d1a52a0297ee859","abstract_canon_sha256":"2e3ba5e2f7d99f839bf5679183a14d2858d22b984866c96704ba0be4a893b0b1"},"schema_version":"1.0"},"canonical_sha256":"daed182fa30cb0a4ea80d2534c74c3bf915d322674dbc61d2206c790fd5963d7","source":{"kind":"arxiv","id":"2412.16822","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16822","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16822v2","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16822","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"3LWRQL5DBSYK","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"3LWRQL5DBSYKJ2UA","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"3LWRQL5D","created_at":"2026-07-05T10:40:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3LWRQL5DBSYKJ2UA2JJUY5GDX6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T02:04:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ee574f5ea35818ff7790dfaaa2c89116fb904d985e9dbdfa8d1a52a0297ee859","abstract_canon_sha256":"2e3ba5e2f7d99f839bf5679183a14d2858d22b984866c96704ba0be4a893b0b1"},"schema_version":"1.0"},"canonical_sha256":"daed182fa30cb0a4ea80d2534c74c3bf915d322674dbc61d2206c790fd5963d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:15.766950Z","signature_b64":"EdtlQ6sakhoy5Yd6NN0tYesj0j5YxmGmdgX399OFGp9dD5ETpjy8Ul1adY3CFeUVmGSimQw1GWl5kKB+teA/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daed182fa30cb0a4ea80d2534c74c3bf915d322674dbc61d2206c790fd5963d7","last_reissued_at":"2026-07-05T10:40:15.765854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:15.765854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16822","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zKwCwLFzb2kP0XUg11q1THuERxqwyQCLWEAsaktTl4pgdtSnUW/05l9Vzifg8stofZXWnf10zVzYrKUaMt5sBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:56:05.601698Z"},"content_sha256":"cc5a173a54a5baa6e8a9bc9f002a583c05471bac3d3341030a4610b0f8a20f57","schema_version":"1.0","event_id":"sha256:cc5a173a54a5baa6e8a9bc9f002a583c05471bac3d3341030a4610b0f8a20f57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3LWRQL5DBSYKJ2UA2JJUY5GDX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Connelly Barnes, Eli Shechtman, Haoran You, Lingzhi Zhang, Sohrab Amirghodsi, Wei Zhou, Xiaoyang Liu, Yan Kang, Yingyan Celine Lin, Yotam Nitzan, Yuqian Zhou, Zhe Lin, Zhenbang Du","submitted_at":"2024-12-22T02:04:17Z","abstract_excerpt":"Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency bottleneck is that existing DiTs apply equal computation across all regions of an image. However, not all image tokens are equally important, and certain localized areas require more computation, such as objects. To address this, we propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16822","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/2412.16822/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQO0wr06WYqeV7LCPnvRmZ15L/RVpP3nw6Xwe4oqwSEWQ1o9KTf7tb3T7sjaD+hV223NCW2rXcMLlan9gxhnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:56:05.602066Z"},"content_sha256":"cb98db496bafc40c552660f377690493990f02e6eb1ece622e2afa9029e4fc7c","schema_version":"1.0","event_id":"sha256:cb98db496bafc40c552660f377690493990f02e6eb1ece622e2afa9029e4fc7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6/bundle.json","state_url":"https://pith.science/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T15:56:05Z","links":{"resolver":"https://pith.science/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6","bundle":"https://pith.science/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6/bundle.json","state":"https://pith.science/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LWRQL5DBSYKJ2UA2JJUY5GDX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3LWRQL5DBSYKJ2UA2JJUY5GDX6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e3ba5e2f7d99f839bf5679183a14d2858d22b984866c96704ba0be4a893b0b1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T02:04:17Z","title_canon_sha256":"ee574f5ea35818ff7790dfaaa2c89116fb904d985e9dbdfa8d1a52a0297ee859"},"schema_version":"1.0","source":{"id":"2412.16822","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16822","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16822v2","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16822","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"3LWRQL5DBSYK","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"3LWRQL5DBSYKJ2UA","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"3LWRQL5D","created_at":"2026-07-05T10:40:15Z"}],"graph_snapshots":[{"event_id":"sha256:cb98db496bafc40c552660f377690493990f02e6eb1ece622e2afa9029e4fc7c","target":"graph","created_at":"2026-07-05T10:40:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.16822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency bottleneck is that existing DiTs apply equal computation across all regions of an image. However, not all image tokens are equally important, and certain localized areas require more computation, such as objects. To address this, we propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically ro","authors_text":"Connelly Barnes, Eli Shechtman, Haoran You, Lingzhi Zhang, Sohrab Amirghodsi, Wei Zhou, Xiaoyang Liu, Yan Kang, Yingyan Celine Lin, Yotam Nitzan, Yuqian Zhou, Zhe Lin, Zhenbang Du","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T02:04:17Z","title":"Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16822","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc5a173a54a5baa6e8a9bc9f002a583c05471bac3d3341030a4610b0f8a20f57","target":"record","created_at":"2026-07-05T10:40:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2e3ba5e2f7d99f839bf5679183a14d2858d22b984866c96704ba0be4a893b0b1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T02:04:17Z","title_canon_sha256":"ee574f5ea35818ff7790dfaaa2c89116fb904d985e9dbdfa8d1a52a0297ee859"},"schema_version":"1.0","source":{"id":"2412.16822","kind":"arxiv","version":2}},"canonical_sha256":"daed182fa30cb0a4ea80d2534c74c3bf915d322674dbc61d2206c790fd5963d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daed182fa30cb0a4ea80d2534c74c3bf915d322674dbc61d2206c790fd5963d7","first_computed_at":"2026-07-05T10:40:15.765854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:15.765854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EdtlQ6sakhoy5Yd6NN0tYesj0j5YxmGmdgX399OFGp9dD5ETpjy8Ul1adY3CFeUVmGSimQw1GWl5kKB+teA/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:15.766950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16822","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc5a173a54a5baa6e8a9bc9f002a583c05471bac3d3341030a4610b0f8a20f57","sha256:cb98db496bafc40c552660f377690493990f02e6eb1ece622e2afa9029e4fc7c"],"state_sha256":"42c1fe20b87c42ecb839ad3cfe801920ad759a6e33ab85742e098d5956f37fe3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MuuqxlxSHEgq3QxREhX9Kpy4hPrvVPo8rBhzjhRKVG+yVJlfn9HRCSBvGSYX64g51QP1hWO3P5i1QFnMQ2kEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:56:05.604029Z","bundle_sha256":"c8f8932afadc6d2ddeb011f26aac8783d41b66f47d8e1e0983ed309c3e16bc2c"}}