{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LCVXSKXLRT26GNBTTIEJCS6CCA","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":"0480f58ffe5691a2d4d62a06f6bdf150a8e2cc38e6884cd6bcf1ae45717f1ed6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T15:32:12Z","title_canon_sha256":"e836f6032d6cc774a2b629e1f63e64f7616e4e3ee6af8ce979920ceb190891aa"},"schema_version":"1.0","source":{"id":"2501.04568","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04568","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04568v2","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04568","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"LCVXSKXLRT26","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"LCVXSKXLRT26GNBT","created_at":"2026-07-05T11:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"LCVXSKXL","created_at":"2026-07-05T11:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:43a0ccfe44a6d216d1bb2900f5fe0b079d42ed8d94e772235fd1254f33418012","target":"graph","created_at":"2026-07-05T11:05:22Z","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/2501.04568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for extensive, high-quality image-text training data. Curation of these image-text pairs is both time-consuming and computationally expensive. To address this challenge, we introduce SVP (Sampling-based Visual Projection), a novel framework that enhances vision-language alignment without relying on manually curated text-image pairs or preference annotation. SVP leverages a small set of manually selected images, self-captio","authors_text":"Aleix Martinez, Evgeny Perevodchikov, Giorgio Giannone, Qianli Feng, Rui Chen, Ruoteng Li","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T15:32:12Z","title":"Feedback-Driven Vision-Language Alignment with Minimal Human Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04568","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:f9f2ddb413c106981e2b534835fa033e82c2cbac67eabf3f63a0f6a213b43cad","target":"record","created_at":"2026-07-05T11:05:22Z","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":"0480f58ffe5691a2d4d62a06f6bdf150a8e2cc38e6884cd6bcf1ae45717f1ed6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T15:32:12Z","title_canon_sha256":"e836f6032d6cc774a2b629e1f63e64f7616e4e3ee6af8ce979920ceb190891aa"},"schema_version":"1.0","source":{"id":"2501.04568","kind":"arxiv","version":2}},"canonical_sha256":"58ab792aeb8cf5e334339a08914bc210232e43bbe5d657da5c03174db65f594e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58ab792aeb8cf5e334339a08914bc210232e43bbe5d657da5c03174db65f594e","first_computed_at":"2026-07-05T11:05:22.878777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:22.878777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xSzXOegWt5G0FZpkYXupB7Y+Aac0TQgAOmwbGJuDVPNGwrjD6UwBC4zcFngydqiTMIo2lqzv+t39JiHz5lRJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:22.879263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04568","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9f2ddb413c106981e2b534835fa033e82c2cbac67eabf3f63a0f6a213b43cad","sha256:43a0ccfe44a6d216d1bb2900f5fe0b079d42ed8d94e772235fd1254f33418012"],"state_sha256":"08b6b65f75961e550bdb82adf2ef99e50f60146927c2b9c5110874f2f95e6573"}