{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DXMSTLTJZBPPMN75UMTU3PDYFQ","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":"d762d79c3d959201811a51a1315039108f1d341c037f06801a040ed00eeed996","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T07:23:49Z","title_canon_sha256":"34381e5f155ff5c2a1cb8e6337d704dbf0fe62b2bc24958776676b2415fadc68"},"schema_version":"1.0","source":{"id":"2501.08347","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08347","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08347v1","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08347","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"DXMSTLTJZBPP","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"DXMSTLTJZBPPMN75","created_at":"2026-07-05T10:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"DXMSTLTJ","created_at":"2026-07-05T10:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:696092a295f6aa447c581830adb253f5c1596bcbe36bfb720faa3cf49220eb86","target":"graph","created_at":"2026-07-05T10:01:01Z","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/2501.08347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains including product retrieval (e-commerce) and web search. Existing methods primarily focus on fully-supervised learning, wherein models are trained on datasets of labeled triplets such as FashionIQ and CIRR. This poses two significant challenges: (i) curating such triplet datasets is labor intensive; and (ii) models lack generalization to unseen objects and domains. In this work, w","authors_text":"Amir Erfan Eshratifar, Benjamin Culpepper, Bhavin Jawade, Deen Dayal Mohan, Joao V. B. Soares, Kapil Thadani, Paloma de Juan, Srirangaraj Setlur, Venu Govindaraju","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T07:23:49Z","title":"SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08347","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":"sha256:41020100d7ce7cfc1d15c04a1e9db40653a4fc520a13ee60890d70393a51720f","target":"record","created_at":"2026-07-05T10:01:01Z","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":"d762d79c3d959201811a51a1315039108f1d341c037f06801a040ed00eeed996","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T07:23:49Z","title_canon_sha256":"34381e5f155ff5c2a1cb8e6337d704dbf0fe62b2bc24958776676b2415fadc68"},"schema_version":"1.0","source":{"id":"2501.08347","kind":"arxiv","version":1}},"canonical_sha256":"1dd929ae69c85ef637fda3274dbc782c13b7dd2a88f9148bf6826d2fba122e3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dd929ae69c85ef637fda3274dbc782c13b7dd2a88f9148bf6826d2fba122e3c","first_computed_at":"2026-07-05T10:01:01.406159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:01.406159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2XcpPTvIdWbUBXXUDPuxioQJWwTkwN8NcFUSXWcaHoAYEtsEijf5m065HgzuwVhuJZmxxg8hgPBh4zt9IIsCAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:01.406653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08347","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41020100d7ce7cfc1d15c04a1e9db40653a4fc520a13ee60890d70393a51720f","sha256:696092a295f6aa447c581830adb253f5c1596bcbe36bfb720faa3cf49220eb86"],"state_sha256":"43074a6eae0a4194b7f655ef41d02b9b5c15a96472449251b965d432ca5be78a"}