{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WR2XJRK3EMU3VV7NUCEJ5EK3JD","short_pith_number":"pith:WR2XJRK3","schema_version":"1.0","canonical_sha256":"b47574c55b2329bad7eda0889e915b48fa43ac3648c6ef9b68280336dc1e559f","source":{"kind":"arxiv","id":"2606.20244","version":1},"attestation_state":"computed","paper":{"title":"SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Yin, Chengming Xu, Cheng Tan, Jiangning Zhang, Mo Yang, Peng-Tao Jiang, Ruolin Shen, Shuicheng Yan, Xiaobin Hu","submitted_at":"2026-06-18T13:56:30Z","abstract_excerpt":"Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidenc"},"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":"2606.20244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T13:56:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee307880338ac4e9f2d1dab9670b1fdd53f38b4c97c09a0e797b8ed4d2e55e9d","abstract_canon_sha256":"8b1fa616f401e044c7eccad7fe8be2f7cbf5b0366273653c3b944f38f586623b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:06.771908Z","signature_b64":"6qlzqp74YjJ6itfhC3edpNuMa3NB9taB0NjxduhVVJE1BdPcR9cOQy3GOPKY2lQ2KmHDfD8ECPvAOT59EEMgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47574c55b2329bad7eda0889e915b48fa43ac3648c6ef9b68280336dc1e559f","last_reissued_at":"2026-06-19T16:13:06.771558Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:06.771558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Yin, Chengming Xu, Cheng Tan, Jiangning Zhang, Mo Yang, Peng-Tao Jiang, Ruolin Shen, Shuicheng Yan, Xiaobin Hu","submitted_at":"2026-06-18T13:56:30Z","abstract_excerpt":"Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20244","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/2606.20244/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":"2606.20244","created_at":"2026-06-19T16:13:06.771624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20244v1","created_at":"2026-06-19T16:13:06.771624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20244","created_at":"2026-06-19T16:13:06.771624+00:00"},{"alias_kind":"pith_short_12","alias_value":"WR2XJRK3EMU3","created_at":"2026-06-19T16:13:06.771624+00:00"},{"alias_kind":"pith_short_16","alias_value":"WR2XJRK3EMU3VV7N","created_at":"2026-06-19T16:13:06.771624+00:00"},{"alias_kind":"pith_short_8","alias_value":"WR2XJRK3","created_at":"2026-06-19T16:13:06.771624+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/WR2XJRK3EMU3VV7NUCEJ5EK3JD","json":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD.json","graph_json":"https://pith.science/api/pith-number/WR2XJRK3EMU3VV7NUCEJ5EK3JD/graph.json","events_json":"https://pith.science/api/pith-number/WR2XJRK3EMU3VV7NUCEJ5EK3JD/events.json","paper":"https://pith.science/paper/WR2XJRK3"},"agent_actions":{"view_html":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD","download_json":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD.json","view_paper":"https://pith.science/paper/WR2XJRK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20244&json=true","fetch_graph":"https://pith.science/api/pith-number/WR2XJRK3EMU3VV7NUCEJ5EK3JD/graph.json","fetch_events":"https://pith.science/api/pith-number/WR2XJRK3EMU3VV7NUCEJ5EK3JD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD/action/storage_attestation","attest_author":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD/action/author_attestation","sign_citation":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD/action/citation_signature","submit_replication":"https://pith.science/pith/WR2XJRK3EMU3VV7NUCEJ5EK3JD/action/replication_record"}},"created_at":"2026-06-19T16:13:06.771624+00:00","updated_at":"2026-06-19T16:13:06.771624+00:00"}