{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G5MNK2IQXB6LNAJTE7ISSHK5SW","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":"310ca68281416f369c5b3cee8a5d890b52e2439e0cf67136f61816ac39cc91ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T19:07:48Z","title_canon_sha256":"8677a5fced08e3a5f0ad72a10fb1157d585909decec6d38cab2d6f2f0d6a28cb"},"schema_version":"1.0","source":{"id":"2303.02483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02483","created_at":"2026-07-05T05:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02483v1","created_at":"2026-07-05T05:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02483","created_at":"2026-07-05T05:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"G5MNK2IQXB6L","created_at":"2026-07-05T05:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"G5MNK2IQXB6LNAJT","created_at":"2026-07-05T05:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"G5MNK2IQ","created_at":"2026-07-05T05:48:11Z"}],"graph_snapshots":[{"event_id":"sha256:3759882a87b56105aa247d8337737d31655ed3b59f823b4ded9266d4d1737791","target":"graph","created_at":"2026-07-05T05:48:11Z","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/2303.02483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual input/output format and dataset size. It has been common to design a task-specific model and fine-tune it independently from a pre-trained V+L model (e.g., CLIP). This results in parameter inefficiency and inability to exploit inter-task relatedness. To address such issues, we propose a novel FAshion-focused Multi-task Efficient learning method for Vision-and-L","authors_text":"Licheng Yu, Li Zhang, Tao Xiang, Xiao Han, Xiatian Zhu, Yi-Zhe Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T19:07:48Z","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02483","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":"sha256:75fcf344d8100bef8b1c9f737abce9639da5baf902db9351e408808b34bfcb66","target":"record","created_at":"2026-07-05T05:48:11Z","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":"310ca68281416f369c5b3cee8a5d890b52e2439e0cf67136f61816ac39cc91ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T19:07:48Z","title_canon_sha256":"8677a5fced08e3a5f0ad72a10fb1157d585909decec6d38cab2d6f2f0d6a28cb"},"schema_version":"1.0","source":{"id":"2303.02483","kind":"arxiv","version":1}},"canonical_sha256":"3758d56910b87cb6813327d1291d5d95984731e9981328b42ac8a8b58ac851ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3758d56910b87cb6813327d1291d5d95984731e9981328b42ac8a8b58ac851ea","first_computed_at":"2026-07-05T05:48:11.864621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:11.864621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"71mkzvU6QEv6Yn/OIGMMKqNgblzH35TRf3dQXE21KLkakpnTqbuCT0zZCkDwhzODrNFTzq2t7vPOcoX2AkPvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:11.864969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75fcf344d8100bef8b1c9f737abce9639da5baf902db9351e408808b34bfcb66","sha256:3759882a87b56105aa247d8337737d31655ed3b59f823b4ded9266d4d1737791"],"state_sha256":"069a0f1e199620382741208157142800288a1c02281fb045f14d0004d60b2016"}