{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4FDCT5P4P5SLR4TMZAONGDXQRG","short_pith_number":"pith:4FDCT5P4","canonical_record":{"source":{"id":"2601.22495","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T03:07:47Z","cross_cats_sorted":[],"title_canon_sha256":"ae4e3cfd15528f06c0a08ed1529dccdc4eae23bd42852ebc5c99c85ef46ad05b","abstract_canon_sha256":"2c371aca1ec87bcb83e230b997d94d337a590d6a1f70666f046a30ada64ebe93"},"schema_version":"1.0"},"canonical_sha256":"e14629f5fc7f64b8f26cc81cd30ef0899d1f8f7398f9440832c3792465e71a92","source":{"kind":"arxiv","id":"2601.22495","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22495","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22495v2","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22495","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"4FDCT5P4P5SL","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"4FDCT5P4P5SLR4TM","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"4FDCT5P4","created_at":"2026-06-19T16:09:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4FDCT5P4P5SLR4TMZAONGDXQRG","target":"record","payload":{"canonical_record":{"source":{"id":"2601.22495","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T03:07:47Z","cross_cats_sorted":[],"title_canon_sha256":"ae4e3cfd15528f06c0a08ed1529dccdc4eae23bd42852ebc5c99c85ef46ad05b","abstract_canon_sha256":"2c371aca1ec87bcb83e230b997d94d337a590d6a1f70666f046a30ada64ebe93"},"schema_version":"1.0"},"canonical_sha256":"e14629f5fc7f64b8f26cc81cd30ef0899d1f8f7398f9440832c3792465e71a92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:54.227434Z","signature_b64":"qH0T93QHgwHo3H9jP6N3Gz/7OnbY5HKwvsditeD1QdXt1Uk38nUwN7OPKwmrW6TEQMyo4g++s/l8kj9Nm6XZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14629f5fc7f64b8f26cc81cd30ef0899d1f8f7398f9440832c3792465e71a92","last_reissued_at":"2026-06-19T16:09:54.227009Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:54.227009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.22495","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":"2026-06-19T16:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lNA6lC7ox00/r/xNiL1inihH1df3Xlvrb4MHF6SNuaQEn8eDcBHFMjaPgLi9SJ/z1B/LWh+9Q5F/GzaPEqRgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:25:03.734422Z"},"content_sha256":"effd32feac2ee6935b8c86b352ec413bca69e1675ed071550d76956991c57927","schema_version":"1.0","event_id":"sha256:effd32feac2ee6935b8c86b352ec413bca69e1675ed071550d76956991c57927"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4FDCT5P4P5SLR4TMZAONGDXQRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradual Fine-Tuning for Flow Matching Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arindam Banerjee, Gudrun Thorkelsdottir","submitted_at":"2026-01-30T03:07:47Z","abstract_excerpt":"Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints. While recent work has produced significant advances, particularly in the area of reward-based fine-tuning, current methods fail to demonstrate both theoretical correctness as well as strong empirical results in terms of stability, efficiency, and diversity preservation. In this work, we propose Gradual Fine-Tuning (GFT), a simple yet principled annealing-based framework for fine-tuning flow generative models when only samples from the target distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22495","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/2601.22495/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":"2026-06-19T16:09:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wlx7bm34TCOCxhde87IyM+HVguQ5CL1QNeQf6fR5KIViZrcPiIYK4MP+BrK2MBb8W2gEdw+wc744F1NASSvnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:25:03.734941Z"},"content_sha256":"333e9ef3fa944ada679a2362e17d6974d8fa7eee10a5a91c0dc68207b7cebcfc","schema_version":"1.0","event_id":"sha256:333e9ef3fa944ada679a2362e17d6974d8fa7eee10a5a91c0dc68207b7cebcfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FDCT5P4P5SLR4TMZAONGDXQRG/bundle.json","state_url":"https://pith.science/pith/4FDCT5P4P5SLR4TMZAONGDXQRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FDCT5P4P5SLR4TMZAONGDXQRG/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":"2026-08-05T23:25:03Z","links":{"resolver":"https://pith.science/pith/4FDCT5P4P5SLR4TMZAONGDXQRG","bundle":"https://pith.science/pith/4FDCT5P4P5SLR4TMZAONGDXQRG/bundle.json","state":"https://pith.science/pith/4FDCT5P4P5SLR4TMZAONGDXQRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FDCT5P4P5SLR4TMZAONGDXQRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4FDCT5P4P5SLR4TMZAONGDXQRG","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":"2c371aca1ec87bcb83e230b997d94d337a590d6a1f70666f046a30ada64ebe93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T03:07:47Z","title_canon_sha256":"ae4e3cfd15528f06c0a08ed1529dccdc4eae23bd42852ebc5c99c85ef46ad05b"},"schema_version":"1.0","source":{"id":"2601.22495","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22495","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22495v2","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22495","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_12","alias_value":"4FDCT5P4P5SL","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_16","alias_value":"4FDCT5P4P5SLR4TM","created_at":"2026-06-19T16:09:54Z"},{"alias_kind":"pith_short_8","alias_value":"4FDCT5P4","created_at":"2026-06-19T16:09:54Z"}],"graph_snapshots":[{"event_id":"sha256:333e9ef3fa944ada679a2362e17d6974d8fa7eee10a5a91c0dc68207b7cebcfc","target":"graph","created_at":"2026-06-19T16:09:54Z","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/2601.22495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints. While recent work has produced significant advances, particularly in the area of reward-based fine-tuning, current methods fail to demonstrate both theoretical correctness as well as strong empirical results in terms of stability, efficiency, and diversity preservation. In this work, we propose Gradual Fine-Tuning (GFT), a simple yet principled annealing-based framework for fine-tuning flow generative models when only samples from the target distribution ","authors_text":"Arindam Banerjee, Gudrun Thorkelsdottir","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T03:07:47Z","title":"Gradual Fine-Tuning for Flow Matching Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22495","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:effd32feac2ee6935b8c86b352ec413bca69e1675ed071550d76956991c57927","target":"record","created_at":"2026-06-19T16:09:54Z","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":"2c371aca1ec87bcb83e230b997d94d337a590d6a1f70666f046a30ada64ebe93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T03:07:47Z","title_canon_sha256":"ae4e3cfd15528f06c0a08ed1529dccdc4eae23bd42852ebc5c99c85ef46ad05b"},"schema_version":"1.0","source":{"id":"2601.22495","kind":"arxiv","version":2}},"canonical_sha256":"e14629f5fc7f64b8f26cc81cd30ef0899d1f8f7398f9440832c3792465e71a92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e14629f5fc7f64b8f26cc81cd30ef0899d1f8f7398f9440832c3792465e71a92","first_computed_at":"2026-06-19T16:09:54.227009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:09:54.227009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qH0T93QHgwHo3H9jP6N3Gz/7OnbY5HKwvsditeD1QdXt1Uk38nUwN7OPKwmrW6TEQMyo4g++s/l8kj9Nm6XZAA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:09:54.227434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22495","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:effd32feac2ee6935b8c86b352ec413bca69e1675ed071550d76956991c57927","sha256:333e9ef3fa944ada679a2362e17d6974d8fa7eee10a5a91c0dc68207b7cebcfc"],"state_sha256":"cdbaa0456ba09b5fec2a9baf6aae2226049424c7c033b52604a59b40e0f3bfcc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SuEejUxsbIY9XPFHj3Mhx4NA2ba9eviD2vfFzPYE29xqZx0AXtVRXFV6tJ82i6tjVkwK7gB7NN+/s48cSCi9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:25:03.740295Z","bundle_sha256":"3cc4387fc98711bbaa89e9d2eabc5cda44aa000a9cfd42f469a4448b03ac0da0"}}