{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FDZEP67WH7XPRZOOA3KSI6RSAO","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":"14619c7024a3ea724b795e884501bbf1bf0697a38369e182a634e5240a3bc1b3","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T17:57:25Z","title_canon_sha256":"d763cd290894ae70854b68618a2583f0c23e102f184038ef62392e0e9b862989"},"schema_version":"1.0","source":{"id":"2308.01313","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01313","created_at":"2026-07-05T07:57:27Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01313v3","created_at":"2026-07-05T07:57:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01313","created_at":"2026-07-05T07:57:27Z"},{"alias_kind":"pith_short_12","alias_value":"FDZEP67WH7XP","created_at":"2026-07-05T07:57:27Z"},{"alias_kind":"pith_short_16","alias_value":"FDZEP67WH7XPRZOO","created_at":"2026-07-05T07:57:27Z"},{"alias_kind":"pith_short_8","alias_value":"FDZEP67W","created_at":"2026-07-05T07:57:27Z"}],"graph_snapshots":[{"event_id":"sha256:f9a8f266ac5aeeb3a1b4ff583f1de8cc03b07e5db4014506ca866035480cdec8","target":"graph","created_at":"2026-07-05T07:57:27Z","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/2308.01313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better performance is still an open question. This paper draws inspiration from the human visual perception process: when classifying an object, humans first infer contextual attributes (e.g., background and orientation) which help separate the foreground object from the background, and then classify the object based on ","authors_text":"Bang An, Chaithanya Kumar Mummadi, Furong Huang, Michael-Andrei Panaitescu-Liess, Sicheng Zhu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T17:57:25Z","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01313","kind":"arxiv","version":3},"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":"sha256:3db31637450d3ae28910ad31bf682bd5d529ba988a352e3f168c55dd488262a6","target":"record","created_at":"2026-07-05T07:57:27Z","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":"14619c7024a3ea724b795e884501bbf1bf0697a38369e182a634e5240a3bc1b3","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T17:57:25Z","title_canon_sha256":"d763cd290894ae70854b68618a2583f0c23e102f184038ef62392e0e9b862989"},"schema_version":"1.0","source":{"id":"2308.01313","kind":"arxiv","version":3}},"canonical_sha256":"28f247fbf63feef8e5ce06d5247a3203a363013a077e8fe4309c7b18a64f45f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28f247fbf63feef8e5ce06d5247a3203a363013a077e8fe4309c7b18a64f45f8","first_computed_at":"2026-07-05T07:57:27.565047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:27.565047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vQ5Mjzt+NFq03J5PBvh2T0EafJNYyigq+TUfGCXIX3uvBbdZBIwntWSLNqXaRyLeKNajHwCQq4ie1wgHHXbCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:27.565645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01313","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3db31637450d3ae28910ad31bf682bd5d529ba988a352e3f168c55dd488262a6","sha256:f9a8f266ac5aeeb3a1b4ff583f1de8cc03b07e5db4014506ca866035480cdec8"],"state_sha256":"0157afa15ca31b953fa38ea0b186e8e5af983b703493c92b5798c97429bee8c2"}