{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VZ2ABHKLDRZHKQYVTDBD7STPQB","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":"22c87be98fa8f92008607a6d4e48abc2bd2514b580a877f5c2c2a83c707a07c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T02:44:53Z","title_canon_sha256":"65298100d99258f40b5fb27c59a1e957eb23c4f8823b481bb5a66991c9e14bb7"},"schema_version":"1.0","source":{"id":"2505.04905","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04905","created_at":"2026-07-05T11:00:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04905v1","created_at":"2026-07-05T11:00:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04905","created_at":"2026-07-05T11:00:15Z"},{"alias_kind":"pith_short_12","alias_value":"VZ2ABHKLDRZH","created_at":"2026-07-05T11:00:15Z"},{"alias_kind":"pith_short_16","alias_value":"VZ2ABHKLDRZHKQYV","created_at":"2026-07-05T11:00:15Z"},{"alias_kind":"pith_short_8","alias_value":"VZ2ABHKL","created_at":"2026-07-05T11:00:15Z"}],"graph_snapshots":[{"event_id":"sha256:115dea82cf088b9d77e390c7c65ea02c9f16f53a49d17f2a2f0354bb180e734f","target":"graph","created_at":"2026-07-05T11:00:15Z","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/2505.04905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Current studies focus on the Class Activation Map (CAM) of CNN and the self-attention map of transformer to identify the region of objects. However, both CAM and self-attention maps can not learn pixel-level fine-grained information on the foreground objects, which hinders the further advance of WSOL. To address this problem, we initiatively leverage the capability of zero-shot generalization and fin","authors_text":"Nannan Wang, Songsong Duan, Xinbo Gao, Xi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T02:44:53Z","title":"Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04905","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:dd5da03e881eacc79992e236e5f2f4ddc4cb3bbb14cdde14d94dc0b9880218a3","target":"record","created_at":"2026-07-05T11:00:15Z","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":"22c87be98fa8f92008607a6d4e48abc2bd2514b580a877f5c2c2a83c707a07c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T02:44:53Z","title_canon_sha256":"65298100d99258f40b5fb27c59a1e957eb23c4f8823b481bb5a66991c9e14bb7"},"schema_version":"1.0","source":{"id":"2505.04905","kind":"arxiv","version":1}},"canonical_sha256":"ae74009d4b1c7275431598c23fca6f8072309b0e38bdaabb8e0d3f2de944aa8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae74009d4b1c7275431598c23fca6f8072309b0e38bdaabb8e0d3f2de944aa8a","first_computed_at":"2026-07-05T11:00:15.547655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:15.547655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CebC8KBkAJXhGlz9gfArAF6P2Qzxo0xd9Qmt9uYRT0qTQi6qvOri8ZrpEsj4XUId7N29viWgVkzD5jG6D92DBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:15.548135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04905","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd5da03e881eacc79992e236e5f2f4ddc4cb3bbb14cdde14d94dc0b9880218a3","sha256:115dea82cf088b9d77e390c7c65ea02c9f16f53a49d17f2a2f0354bb180e734f"],"state_sha256":"75a4cca7e8b7dde1a4fe00111a380cb452a46b98ac2a68a68b71c6e9f710c550"}