{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2PCWWQXMSQJTNZVHJUCMTXW7L3","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":"c08183fea286a1b5e63c0d8372e35e4cdd611334d127a29fa25ed32bc5cf2bb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T20:02:10Z","title_canon_sha256":"55d17a83af1de286e40ce017b5fc920fce999f3100ad64193c821677647c6edd"},"schema_version":"1.0","source":{"id":"2112.13884","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13884","created_at":"2026-07-05T03:46:26Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13884v2","created_at":"2026-07-05T03:46:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13884","created_at":"2026-07-05T03:46:26Z"},{"alias_kind":"pith_short_12","alias_value":"2PCWWQXMSQJT","created_at":"2026-07-05T03:46:26Z"},{"alias_kind":"pith_short_16","alias_value":"2PCWWQXMSQJTNZVH","created_at":"2026-07-05T03:46:26Z"},{"alias_kind":"pith_short_8","alias_value":"2PCWWQXM","created_at":"2026-07-05T03:46:26Z"}],"graph_snapshots":[{"event_id":"sha256:c3761e908929a6d7a08a86008facc14471115e300b2a0e81a048908ca857dfac","target":"graph","created_at":"2026-07-05T03:46:26Z","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/2112.13884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using natural language as a supervision for training visual recognition models holds great promise. Recent works have shown that if such supervision is used in the form of alignment between images and captions in large training datasets, then the resulting aligned models perform well on zero-shot classification as downstream tasks2. In this paper, we focus on teasing out what parts of the language supervision are essential for training zero-shot image classification models. Through extensive and careful experiments, we show that: 1) A simple Bag-of-Words (BoW) caption could be used as a replac","authors_text":"Ajinkya Tejankar, Bichen Wu, Hamed Firooz, Hamed Pirsiavash, Madian Khabsa, Maziar Sanjabi, Saining Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T20:02:10Z","title":"A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13884","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":"sha256:239f44f61f89c0a0f3473a0f2514685d0dd12facf904c372c2b4abd643f2a069","target":"record","created_at":"2026-07-05T03:46:26Z","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":"c08183fea286a1b5e63c0d8372e35e4cdd611334d127a29fa25ed32bc5cf2bb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T20:02:10Z","title_canon_sha256":"55d17a83af1de286e40ce017b5fc920fce999f3100ad64193c821677647c6edd"},"schema_version":"1.0","source":{"id":"2112.13884","kind":"arxiv","version":2}},"canonical_sha256":"d3c56b42ec941336e6a74d04c9dedf5ef6b5aa56bc5568c648edda96282b88d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3c56b42ec941336e6a74d04c9dedf5ef6b5aa56bc5568c648edda96282b88d9","first_computed_at":"2026-07-05T03:46:26.066559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:26.066559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ueXfxL0bqyZjhGHa+ZKv5kA6se4Kl7GIXZ5FqS+ImisxoxbkCUwoJWwv2uVZoeMhnyP548E+Cya5Y550Bwq5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:26.067106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13884","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:239f44f61f89c0a0f3473a0f2514685d0dd12facf904c372c2b4abd643f2a069","sha256:c3761e908929a6d7a08a86008facc14471115e300b2a0e81a048908ca857dfac"],"state_sha256":"d3d801af57e6aff438e7de49201b718a1994c105271007c9d616003c55d9a62f"}