{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B4XLADPS5CO242S5QBXMEKZLZE","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":"94eef402f88e16cb36cbd61968c9ca79c4afc07effe0e99736212df483656de0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T04:14:16Z","title_canon_sha256":"5e9764c61bc478385f70d204c6b7c9aabb9f5e1b1cbb1a8a3253d17e9d894990"},"schema_version":"1.0","source":{"id":"2605.15599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15599","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15599v1","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15599","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"B4XLADPS5CO2","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"B4XLADPS5CO242S5","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"B4XLADPS","created_at":"2026-05-20T00:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:8467b53e35ac5eced521a059be74f303a7ce9043bc17357f800dfae22ea702bf","target":"graph","created_at":"2026-05-20T00:01:07Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.898221Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.056186Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15599/integrity.json","findings":[],"snapshot_sha256":"fa8a60ae4fda41038af1d2f755189c110fd3da289127ad3f137abcb2f8cdc446","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extreme low-data fine-grained classification is common in expert domains where labeling is expensive, yet practitioners still need principled guidance for selecting pretrained encoders. We study emerald inclusion grading with a custom dataset of labeled images across three classes and ask: under matched backbone capacity, how does pretraining objective affect downstream representation quality? We compare four frozen ViT-B/16 encoders trained with supervised classification, contrastive learning (SigLIP2), masked reconstruction (MAE), and self-distillation (DINOv3), and evaluate them with leave-","authors_text":"Aisha Sartaj, Alexander Hackett, Ginny Fisher, Jason Fisher, Mahule Roy, Srikanth Thudumu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T04:14:16Z","title":"Pretraining Objective Matters in Extreme Low-Data FGVC: A Backbone-Controlled Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15599","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":"sha256:0389e4babc6c8274473f6a8368f1a2f136dcdb3030bf10e6a398ddd56c76c2de","target":"record","created_at":"2026-05-20T00:01:07Z","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":"94eef402f88e16cb36cbd61968c9ca79c4afc07effe0e99736212df483656de0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T04:14:16Z","title_canon_sha256":"5e9764c61bc478385f70d204c6b7c9aabb9f5e1b1cbb1a8a3253d17e9d894990"},"schema_version":"1.0","source":{"id":"2605.15599","kind":"arxiv","version":1}},"canonical_sha256":"0f2eb00df2e89dae6a5d806ec22b2bc913d4e475a92f0556ca8af3d590440bb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f2eb00df2e89dae6a5d806ec22b2bc913d4e475a92f0556ca8af3d590440bb8","first_computed_at":"2026-05-20T00:01:07.462579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:07.462579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pklCPvwkLr6pw19vs8gSgcleI4eLTdCTGyVUA540f1cWLXj+z/nviNqciiWMat73Q+AVy4yh+HHdV0JXnhHDCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:07.463258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0389e4babc6c8274473f6a8368f1a2f136dcdb3030bf10e6a398ddd56c76c2de","sha256:8467b53e35ac5eced521a059be74f303a7ce9043bc17357f800dfae22ea702bf"],"state_sha256":"cd5629038b368a635e073463153bc4eb80f7c2f399863d9df5771c5044e65dd3"}