{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LCVXSKXLRT26GNBTTIEJCS6CCA","short_pith_number":"pith:LCVXSKXL","canonical_record":{"source":{"id":"2501.04568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T15:32:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e836f6032d6cc774a2b629e1f63e64f7616e4e3ee6af8ce979920ceb190891aa","abstract_canon_sha256":"0480f58ffe5691a2d4d62a06f6bdf150a8e2cc38e6884cd6bcf1ae45717f1ed6"},"schema_version":"1.0"},"canonical_sha256":"58ab792aeb8cf5e334339a08914bc210232e43bbe5d657da5c03174db65f594e","source":{"kind":"arxiv","id":"2501.04568","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LCVXSKXLRT26GNBTTIEJCS6CCA","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T15:32:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"e836f6032d6cc774a2b629e1f63e64f7616e4e3ee6af8ce979920ceb190891aa","abstract_canon_sha256":"0480f58ffe5691a2d4d62a06f6bdf150a8e2cc38e6884cd6bcf1ae45717f1ed6"},"schema_version":"1.0"},"canonical_sha256":"58ab792aeb8cf5e334339a08914bc210232e43bbe5d657da5c03174db65f594e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:22.879263Z","signature_b64":"xSzXOegWt5G0FZpkYXupB7Y+Aac0TQgAOmwbGJuDVPNGwrjD6UwBC4zcFngydqiTMIo2lqzv+t39JiHz5lRJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ab792aeb8cf5e334339a08914bc210232e43bbe5d657da5c03174db65f594e","last_reissued_at":"2026-07-05T11:05:22.878777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:22.878777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04568","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":"2026-07-05T11:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TUAoBAdSAAfgx7YUjWn58VSU4AcuxDYfVULFlcDeTSALrMLTsR9TKY/9vAsAitvuNNXm7FHVjRNklXo5zz03AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T22:09:18.006786Z"},"content_sha256":"f9f2ddb413c106981e2b534835fa033e82c2cbac67eabf3f63a0f6a213b43cad","schema_version":"1.0","event_id":"sha256:f9f2ddb413c106981e2b534835fa033e82c2cbac67eabf3f63a0f6a213b43cad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LCVXSKXLRT26GNBTTIEJCS6CCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feedback-Driven Vision-Language Alignment with Minimal Human Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleix Martinez, Evgeny Perevodchikov, Giorgio Giannone, Qianli Feng, Rui Chen, Ruoteng Li","submitted_at":"2025-01-08T15:32:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04568","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/2501.04568/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":"2026-07-05T11:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uqOQTcMQOpOvMuKGTLJ87AlHzJgDru5rjPLCBRuZ0Ay37omu0BCI3Baa7uMoDxQeieloz415ETgHpJgxY2O9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T22:09:18.007285Z"},"content_sha256":"43a0ccfe44a6d216d1bb2900f5fe0b079d42ed8d94e772235fd1254f33418012","schema_version":"1.0","event_id":"sha256:43a0ccfe44a6d216d1bb2900f5fe0b079d42ed8d94e772235fd1254f33418012"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LCVXSKXLRT26GNBTTIEJCS6CCA/bundle.json","state_url":"https://pith.science/pith/LCVXSKXLRT26GNBTTIEJCS6CCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LCVXSKXLRT26GNBTTIEJCS6CCA/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":"2026-08-11T22:09:18Z","links":{"resolver":"https://pith.science/pith/LCVXSKXLRT26GNBTTIEJCS6CCA","bundle":"https://pith.science/pith/LCVXSKXLRT26GNBTTIEJCS6CCA/bundle.json","state":"https://pith.science/pith/LCVXSKXLRT26GNBTTIEJCS6CCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LCVXSKXLRT26GNBTTIEJCS6CCA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6SAytWmwVZQu149qg/+ZZ++2RZlT/Cr8jk2JYSEvp3Wb/tbg9G46700G8dy3QaAD8dqnmre1T+0o/wKs4TvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T22:09:18.012317Z","bundle_sha256":"af69c84bfe85faedab8cb1e2f7f7cca857720f5175a7b9d3486f31cfe26812e7"}}