{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W","short_pith_number":"pith:Z3QQKJ6G","canonical_record":{"source":{"id":"2503.12271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-15T21:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"8fe9e0b7904785d63e348eaae23fe49e4c255c784237706165a90a7655126efb","abstract_canon_sha256":"ed3a43f1d8c71b7e0db882d5e99f0254d854547f4eb0c416d5df155450684e38"},"schema_version":"1.0"},"canonical_sha256":"cee10527c6534332fce9f8c6b5dd19edb763a70e930d2a19174df6725f4d7aaf","source":{"kind":"arxiv","id":"2503.12271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12271","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12271v1","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12271","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z3QQKJ6GKNBT","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z3QQKJ6GKNBTF7HJ","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z3QQKJ6G","created_at":"2026-07-05T10:32:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-15T21:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"8fe9e0b7904785d63e348eaae23fe49e4c255c784237706165a90a7655126efb","abstract_canon_sha256":"ed3a43f1d8c71b7e0db882d5e99f0254d854547f4eb0c416d5df155450684e38"},"schema_version":"1.0"},"canonical_sha256":"cee10527c6534332fce9f8c6b5dd19edb763a70e930d2a19174df6725f4d7aaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:09.108021Z","signature_b64":"uLjzcvZ2mi2I06qozUlnS9VgG20Afo7AtACcbR4TmoVOEePRZpqStEYVimA8P4ELqijWsdvtt/JlVP5aBYmHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cee10527c6534332fce9f8c6b5dd19edb763a70e930d2a19174df6725f4d7aaf","last_reissued_at":"2026-07-05T10:32:09.107399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:09.107399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12271","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1yBsnHY8eWVFthCb28BJpu0v/Qsos+IkYIcSg3bX7MFeWkUL4rwc8wN4fDnmKXTz/V0WGZXhoFECJNbyPArACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:31:52.932145Z"},"content_sha256":"43b578bf98ae88e63027b3b13a878a5495df2e3bc0672f7bed28897f2b04e3ee","schema_version":"1.0","event_id":"sha256:43b578bf98ae88e63027b3b13a878a5495df2e3bc0672f7bed28897f2b04e3ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Akash Gokul, Arsh Koneru, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato","submitted_at":"2025-03-15T21:58:12Z","abstract_excerpt":"The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive, leading to growing interest in inference-time scaling to improve performance. Currently, inference-time scaling for text-to-image diffusion models is largely limited to best-of-N sampling, where multiple images are generated per prompt and a selection model chooses the best output. Inspired by the recent success of reasoning models like DeepSeek-R1 in the la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12271","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/2503.12271/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":"2026-07-05T10:32:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hynTxibSeORqiBk2dwGy1pDag2guy3gUkOKObdLcv2Az/Lg1aNl7H9UbIAWqgiYmuohMialifi6LHk8LErD1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:31:52.932759Z"},"content_sha256":"fbfc115840f2aa5f8274c83d01a24dded707846f4d51981bd70fbfbd1e7fe781","schema_version":"1.0","event_id":"sha256:fbfc115840f2aa5f8274c83d01a24dded707846f4d51981bd70fbfbd1e7fe781"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W/bundle.json","state_url":"https://pith.science/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W/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":"2026-08-07T01:31:52Z","links":{"resolver":"https://pith.science/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W","bundle":"https://pith.science/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W/bundle.json","state":"https://pith.science/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z3QQKJ6GKNBTF7HJ7DDLLXIZ5W","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":"ed3a43f1d8c71b7e0db882d5e99f0254d854547f4eb0c416d5df155450684e38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-15T21:58:12Z","title_canon_sha256":"8fe9e0b7904785d63e348eaae23fe49e4c255c784237706165a90a7655126efb"},"schema_version":"1.0","source":{"id":"2503.12271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12271","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12271v1","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12271","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z3QQKJ6GKNBT","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z3QQKJ6GKNBTF7HJ","created_at":"2026-07-05T10:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z3QQKJ6G","created_at":"2026-07-05T10:32:09Z"}],"graph_snapshots":[{"event_id":"sha256:fbfc115840f2aa5f8274c83d01a24dded707846f4d51981bd70fbfbd1e7fe781","target":"graph","created_at":"2026-07-05T10:32:09Z","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/2503.12271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive, leading to growing interest in inference-time scaling to improve performance. Currently, inference-time scaling for text-to-image diffusion models is largely limited to best-of-N sampling, where multiple images are generated per prompt and a selection model chooses the best output. Inspired by the recent success of reasoning models like DeepSeek-R1 in the la","authors_text":"Aditya Grover, Akash Gokul, Arsh Koneru, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-15T21:58:12Z","title":"Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12271","kind":"arxiv","version":1},"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":"sha256:43b578bf98ae88e63027b3b13a878a5495df2e3bc0672f7bed28897f2b04e3ee","target":"record","created_at":"2026-07-05T10:32:09Z","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":"ed3a43f1d8c71b7e0db882d5e99f0254d854547f4eb0c416d5df155450684e38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-15T21:58:12Z","title_canon_sha256":"8fe9e0b7904785d63e348eaae23fe49e4c255c784237706165a90a7655126efb"},"schema_version":"1.0","source":{"id":"2503.12271","kind":"arxiv","version":1}},"canonical_sha256":"cee10527c6534332fce9f8c6b5dd19edb763a70e930d2a19174df6725f4d7aaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cee10527c6534332fce9f8c6b5dd19edb763a70e930d2a19174df6725f4d7aaf","first_computed_at":"2026-07-05T10:32:09.107399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:09.107399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLjzcvZ2mi2I06qozUlnS9VgG20Afo7AtACcbR4TmoVOEePRZpqStEYVimA8P4ELqijWsdvtt/JlVP5aBYmHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:09.108021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43b578bf98ae88e63027b3b13a878a5495df2e3bc0672f7bed28897f2b04e3ee","sha256:fbfc115840f2aa5f8274c83d01a24dded707846f4d51981bd70fbfbd1e7fe781"],"state_sha256":"178216d6c26ba0bedb939c154f2cbffbad5b6667c28e89137e04ad61b1034713"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UruAKnGmj+iuf4VyTB7XOL5AluEmcAv/V+gi+P/pccfCXszIfnOS/HxsV1SyQAI9j9PythguFeYDfO7pK5aoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:31:52.938049Z","bundle_sha256":"622934f6441e12e1cd3d46643c82e6182da74107a4b83060f1e308740db88f0c"}}