{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FNWFKH4Z2SYLGJ4MLWC3OOYFGA","short_pith_number":"pith:FNWFKH4Z","canonical_record":{"source":{"id":"2509.15267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-18T10:09:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6a77f01639146b88e7b33a68d0e72f5ccd8bfffeb755888a0b46bc90b4e1bd6c","abstract_canon_sha256":"054d833824f2b37984fb8383f85a4552ab8c435ca8e7119a1d14cbf344084a2d"},"schema_version":"1.0"},"canonical_sha256":"2b6c551f99d4b0b3278c5d85b73b05300318ce62ded1773ce1d307fb6dae4874","source":{"kind":"arxiv","id":"2509.15267","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.15267","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.15267v2","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15267","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"pith_short_12","alias_value":"FNWFKH4Z2SYL","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"pith_short_16","alias_value":"FNWFKH4Z2SYLGJ4M","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"pith_short_8","alias_value":"FNWFKH4Z","created_at":"2026-05-20T00:00:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FNWFKH4Z2SYLGJ4MLWC3OOYFGA","target":"record","payload":{"canonical_record":{"source":{"id":"2509.15267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-18T10:09:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6a77f01639146b88e7b33a68d0e72f5ccd8bfffeb755888a0b46bc90b4e1bd6c","abstract_canon_sha256":"054d833824f2b37984fb8383f85a4552ab8c435ca8e7119a1d14cbf344084a2d"},"schema_version":"1.0"},"canonical_sha256":"2b6c551f99d4b0b3278c5d85b73b05300318ce62ded1773ce1d307fb6dae4874","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:24.142352Z","signature_b64":"rwvHFMf4BpvsxUxvGQBe/m4ejmwA8yH6YXiouO4E2yzBp2KW6tTy7qcIdy2kjMUNZ/8RyIWwGb8oTvsd0R4iAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b6c551f99d4b0b3278c5d85b73b05300318ce62ded1773ce1d307fb6dae4874","last_reissued_at":"2026-05-20T00:00:24.141591Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:24.141591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.15267","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":"2026-05-20T00:00:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EyH8sjSPjIz+XjSEiN70GiiRtDnobCOoidoMGoImf7MlzWYZBRJ8VR3qMptHh8UeLVSHUrIuWac+dnl0OjcTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T10:49:31.252792Z"},"content_sha256":"16a4d8f202e6241e44697c7df3bcf63b6d8338cb8a64fd8a8eb4031544d62f05","schema_version":"1.0","event_id":"sha256:16a4d8f202e6241e44697c7df3bcf63b6d8338cb8a64fd8a8eb4031544d62f05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FNWFKH4Z2SYLGJ4MLWC3OOYFGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Autoguided Online Data Curation for Diffusion Model Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniele Faccio, Luis Oala, Marco Aversa, Valeria Pais","submitted_at":"2025-09-18T10:09:04Z","abstract_excerpt":"The costs of generative model compute rekindled promises and hopes for efficient data curation. In this work, we investigate whether recently developed autoguidance and online data selection methods can improve the time and sample efficiency of training generative diffusion models. We integrate joint example selection (JEST) and autoguidance into a unified code base for fast ablation and benchmarking. We evaluate combinations of data curation on a controlled 2-D synthetic data generation task as well as (3x64x64)-D image generation. Our comparisons are made at equal wall-clock time and equal n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15267","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/2509.15267/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":"2026-05-20T00:00:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJbHtzN79RTcBVHQE59rQzIRCqHcXitIUL+rFWe1f708eLyQFahJk9Cw5dZg8QPOHtaeidz1NrVAdULkfnRACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T10:49:31.253327Z"},"content_sha256":"7d422273dc3f5829524c7a44739622c017db7d6a274f7d80f13ebdf5b39d141c","schema_version":"1.0","event_id":"sha256:7d422273dc3f5829524c7a44739622c017db7d6a274f7d80f13ebdf5b39d141c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA/bundle.json","state_url":"https://pith.science/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA/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":"2026-05-22T10:49:31Z","links":{"resolver":"https://pith.science/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA","bundle":"https://pith.science/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA/bundle.json","state":"https://pith.science/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FNWFKH4Z2SYLGJ4MLWC3OOYFGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FNWFKH4Z2SYLGJ4MLWC3OOYFGA","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":"054d833824f2b37984fb8383f85a4552ab8c435ca8e7119a1d14cbf344084a2d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-18T10:09:04Z","title_canon_sha256":"6a77f01639146b88e7b33a68d0e72f5ccd8bfffeb755888a0b46bc90b4e1bd6c"},"schema_version":"1.0","source":{"id":"2509.15267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.15267","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"arxiv_version","alias_value":"2509.15267v2","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15267","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"pith_short_12","alias_value":"FNWFKH4Z2SYL","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"pith_short_16","alias_value":"FNWFKH4Z2SYLGJ4M","created_at":"2026-05-20T00:00:24Z"},{"alias_kind":"pith_short_8","alias_value":"FNWFKH4Z","created_at":"2026-05-20T00:00:24Z"}],"graph_snapshots":[{"event_id":"sha256:7d422273dc3f5829524c7a44739622c017db7d6a274f7d80f13ebdf5b39d141c","target":"graph","created_at":"2026-05-20T00:00:24Z","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/2509.15267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The costs of generative model compute rekindled promises and hopes for efficient data curation. In this work, we investigate whether recently developed autoguidance and online data selection methods can improve the time and sample efficiency of training generative diffusion models. We integrate joint example selection (JEST) and autoguidance into a unified code base for fast ablation and benchmarking. We evaluate combinations of data curation on a controlled 2-D synthetic data generation task as well as (3x64x64)-D image generation. Our comparisons are made at equal wall-clock time and equal n","authors_text":"Daniele Faccio, Luis Oala, Marco Aversa, Valeria Pais","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-18T10:09:04Z","title":"Autoguided Online Data Curation for Diffusion Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15267","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":"sha256:16a4d8f202e6241e44697c7df3bcf63b6d8338cb8a64fd8a8eb4031544d62f05","target":"record","created_at":"2026-05-20T00:00:24Z","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":"054d833824f2b37984fb8383f85a4552ab8c435ca8e7119a1d14cbf344084a2d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-18T10:09:04Z","title_canon_sha256":"6a77f01639146b88e7b33a68d0e72f5ccd8bfffeb755888a0b46bc90b4e1bd6c"},"schema_version":"1.0","source":{"id":"2509.15267","kind":"arxiv","version":2}},"canonical_sha256":"2b6c551f99d4b0b3278c5d85b73b05300318ce62ded1773ce1d307fb6dae4874","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b6c551f99d4b0b3278c5d85b73b05300318ce62ded1773ce1d307fb6dae4874","first_computed_at":"2026-05-20T00:00:24.141591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:24.141591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rwvHFMf4BpvsxUxvGQBe/m4ejmwA8yH6YXiouO4E2yzBp2KW6tTy7qcIdy2kjMUNZ/8RyIWwGb8oTvsd0R4iAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:24.142352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.15267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16a4d8f202e6241e44697c7df3bcf63b6d8338cb8a64fd8a8eb4031544d62f05","sha256:7d422273dc3f5829524c7a44739622c017db7d6a274f7d80f13ebdf5b39d141c"],"state_sha256":"e9e827fa5dd28b373e110310ebe7ecc30d30b215ac22a17b13d1f9230a5fa672"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLjnN3Bm+7aeb8Q3TzwmzxE2dfczR8mgna0KdfrR5ZYeKuV5g2abVxEopW3ftCEIWn4UoeuA59AnB7oQQbajAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T10:49:31.256563Z","bundle_sha256":"4fef788bc1b4fdede8ad2d3733d980f131cadba53b17265eda50f62c952cd592"}}