{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FDZEP67WH7XPRZOOA3KSI6RSAO","short_pith_number":"pith:FDZEP67W","schema_version":"1.0","canonical_sha256":"28f247fbf63feef8e5ce06d5247a3203a363013a077e8fe4309c7b18a64f45f8","source":{"kind":"arxiv","id":"2308.01313","version":3},"attestation_state":"computed","paper":{"title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bang An, Chaithanya Kumar Mummadi, Furong Huang, Michael-Andrei Panaitescu-Liess, Sicheng Zhu","submitted_at":"2023-08-02T17:57:25Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.01313","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T17:57:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d763cd290894ae70854b68618a2583f0c23e102f184038ef62392e0e9b862989","abstract_canon_sha256":"14619c7024a3ea724b795e884501bbf1bf0697a38369e182a634e5240a3bc1b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:27.565645Z","signature_b64":"vQ5Mjzt+NFq03J5PBvh2T0EafJNYyigq+TUfGCXIX3uvBbdZBIwntWSLNqXaRyLeKNajHwCQq4ie1wgHHXbCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28f247fbf63feef8e5ce06d5247a3203a363013a077e8fe4309c7b18a64f45f8","last_reissued_at":"2026-07-05T07:57:27.565047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:27.565047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bang An, Chaithanya Kumar Mummadi, Furong Huang, Michael-Andrei Panaitescu-Liess, Sicheng Zhu","submitted_at":"2023-08-02T17:57:25Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01313","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.01313/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.01313","created_at":"2026-07-05T07:57:27.565113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01313v3","created_at":"2026-07-05T07:57:27.565113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01313","created_at":"2026-07-05T07:57:27.565113+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDZEP67WH7XP","created_at":"2026-07-05T07:57:27.565113+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDZEP67WH7XPRZOO","created_at":"2026-07-05T07:57:27.565113+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDZEP67W","created_at":"2026-07-05T07:57:27.565113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06093","citing_title":"Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO","json":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO.json","graph_json":"https://pith.science/api/pith-number/FDZEP67WH7XPRZOOA3KSI6RSAO/graph.json","events_json":"https://pith.science/api/pith-number/FDZEP67WH7XPRZOOA3KSI6RSAO/events.json","paper":"https://pith.science/paper/FDZEP67W"},"agent_actions":{"view_html":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO","download_json":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO.json","view_paper":"https://pith.science/paper/FDZEP67W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01313&json=true","fetch_graph":"https://pith.science/api/pith-number/FDZEP67WH7XPRZOOA3KSI6RSAO/graph.json","fetch_events":"https://pith.science/api/pith-number/FDZEP67WH7XPRZOOA3KSI6RSAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO/action/storage_attestation","attest_author":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO/action/author_attestation","sign_citation":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO/action/citation_signature","submit_replication":"https://pith.science/pith/FDZEP67WH7XPRZOOA3KSI6RSAO/action/replication_record"}},"created_at":"2026-07-05T07:57:27.565113+00:00","updated_at":"2026-07-05T07:57:27.565113+00:00"}