{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ESLXBZH2I7CSOP4UMPOGCKJ2E4","short_pith_number":"pith:ESLXBZH2","schema_version":"1.0","canonical_sha256":"249770e4fa47c5273f9463dc61293a271c441d9685f3b8a40be7dd0037c25a82","source":{"kind":"arxiv","id":"2505.06524","version":1},"attestation_state":"computed","paper":{"title":"Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changwen Zheng, JianQi Zhang, Jingyao Wang, Wenwen Qiang","submitted_at":"2025-05-10T05:55:33Z","abstract_excerpt":"Despite the strength of the Segment Anything Model (SAM), it struggles with generalization issues in open-vocabulary multi-entity segmentation (OVMS). Through empirical and causal analyses, we find that (i) the prompt bias is the primary cause of the generalization issues; (ii) this bias is closely tied to the task-irrelevant generating factors within the prompts, which act as confounders and affect generalization. To address the generalization issues, we aim to propose a method that can calibrate prompts to eliminate confounders for accurate OVMS. Building upon the causal analysis, we propose"},"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":"2505.06524","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-10T05:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"6a4a4cd09252a0e155b8f851ef0b0c3ad9e9b5cf1fad94f83b7558a28fd145d4","abstract_canon_sha256":"d8d4791170afcf6698080f845304ab143f422bb2626daa81ea91fa5028309255"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:11.044179Z","signature_b64":"khQT/Tn0suI90eMZEZLp35UiqLy8GUIiuziW8fpANvhj1ALWxMPxk7r3eHP5/E4caAlnmk/rq4YOj97T5bJ1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"249770e4fa47c5273f9463dc61293a271c441d9685f3b8a40be7dd0037c25a82","last_reissued_at":"2026-07-05T11:01:11.043664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:11.043664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changwen Zheng, JianQi Zhang, Jingyao Wang, Wenwen Qiang","submitted_at":"2025-05-10T05:55:33Z","abstract_excerpt":"Despite the strength of the Segment Anything Model (SAM), it struggles with generalization issues in open-vocabulary multi-entity segmentation (OVMS). Through empirical and causal analyses, we find that (i) the prompt bias is the primary cause of the generalization issues; (ii) this bias is closely tied to the task-irrelevant generating factors within the prompts, which act as confounders and affect generalization. To address the generalization issues, we aim to propose a method that can calibrate prompts to eliminate confounders for accurate OVMS. Building upon the causal analysis, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06524","kind":"arxiv","version":1},"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/2505.06524/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":"2505.06524","created_at":"2026-07-05T11:01:11.043740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06524v1","created_at":"2026-07-05T11:01:11.043740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06524","created_at":"2026-07-05T11:01:11.043740+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESLXBZH2I7CS","created_at":"2026-07-05T11:01:11.043740+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESLXBZH2I7CSOP4U","created_at":"2026-07-05T11:01:11.043740+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESLXBZH2","created_at":"2026-07-05T11:01:11.043740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4","json":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4.json","graph_json":"https://pith.science/api/pith-number/ESLXBZH2I7CSOP4UMPOGCKJ2E4/graph.json","events_json":"https://pith.science/api/pith-number/ESLXBZH2I7CSOP4UMPOGCKJ2E4/events.json","paper":"https://pith.science/paper/ESLXBZH2"},"agent_actions":{"view_html":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4","download_json":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4.json","view_paper":"https://pith.science/paper/ESLXBZH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06524&json=true","fetch_graph":"https://pith.science/api/pith-number/ESLXBZH2I7CSOP4UMPOGCKJ2E4/graph.json","fetch_events":"https://pith.science/api/pith-number/ESLXBZH2I7CSOP4UMPOGCKJ2E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4/action/storage_attestation","attest_author":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4/action/author_attestation","sign_citation":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4/action/citation_signature","submit_replication":"https://pith.science/pith/ESLXBZH2I7CSOP4UMPOGCKJ2E4/action/replication_record"}},"created_at":"2026-07-05T11:01:11.043740+00:00","updated_at":"2026-07-05T11:01:11.043740+00:00"}