{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XQ72UZRDMR226KMCPQAOV3E3EH","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":"78c1fb61bb806fad9e468668f5369b553dbc1442fd6aca8b8879de3fe746a765","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2025-12-12T19:06:14Z","title_canon_sha256":"6163d52da342eb7b0590725907e35403bb22795248731c025f5967b019bc154b"},"schema_version":"1.0","source":{"id":"2512.11982","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.11982","created_at":"2026-06-11T01:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2512.11982v2","created_at":"2026-06-11T01:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11982","created_at":"2026-06-11T01:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"XQ72UZRDMR22","created_at":"2026-06-11T01:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"XQ72UZRDMR226KMC","created_at":"2026-06-11T01:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"XQ72UZRD","created_at":"2026-06-11T01:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:1f5e5956d991e287e1a0185c71ba124c375baf2fc9b5136e27fa69fb4ec499d3","target":"graph","created_at":"2026-06-11T01:09:24Z","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/2512.11982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes. In this work, we develop a pipeline to create a semantic search engine from completely unlabeled image data. Our method leverages Vision-Language Models (VLMs) to generate descriptions for galaxy images, then contrastively aligns a pre-trained astronomy foundation model with these embedded descriptions to produce searchable embeddings at scale. We find that current VLMs provide descriptions that are sufficiently informa","authors_text":"Francois Lanusse, Irina Espejo, Jo Bovy, Liam Parker, Nolan Koblischke, Shirley Ho","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2025-12-12T19:06:14Z","title":"Semantic search for 100M+ galaxy images using AI-generated captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11982","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":"sha256:9fd71483a089a7e8d3d9451394750badb8fa5047446564571bc9278875dab0ba","target":"record","created_at":"2026-06-11T01:09:24Z","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":"78c1fb61bb806fad9e468668f5369b553dbc1442fd6aca8b8879de3fe746a765","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2025-12-12T19:06:14Z","title_canon_sha256":"6163d52da342eb7b0590725907e35403bb22795248731c025f5967b019bc154b"},"schema_version":"1.0","source":{"id":"2512.11982","kind":"arxiv","version":2}},"canonical_sha256":"bc3faa66236475af29827c00eaec9b21d0bc68bc1e52ec0c47d196ed5e7bae26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc3faa66236475af29827c00eaec9b21d0bc68bc1e52ec0c47d196ed5e7bae26","first_computed_at":"2026-06-11T01:09:24.353217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:24.353217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"37L5Q3CC9jXhLCyxhsFXpNWZrucf0eX7C61EpMXGdozy+qCH49JL8FbI+AQL3/kQ4I6JgnYQnvX/r8MNYHwkBQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:24.354277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.11982","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fd71483a089a7e8d3d9451394750badb8fa5047446564571bc9278875dab0ba","sha256:1f5e5956d991e287e1a0185c71ba124c375baf2fc9b5136e27fa69fb4ec499d3"],"state_sha256":"b372cc031eac5f2f8d77e179994153c6a4069e0e54e68c0df3440362c833b151"}