{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CQJOFFPJNR6FSHV2ESM3J46KLC","short_pith_number":"pith:CQJOFFPJ","canonical_record":{"source":{"id":"2607.02089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T14:25:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"0793e482b44f4d60747a889d0876f2e6fee6983c259a4248353418a246dc2580","abstract_canon_sha256":"a37ac115271dc32ccdf7fed65e3a15f25ab43f4b679a25271d51fb1d8ad87869"},"schema_version":"1.0"},"canonical_sha256":"1412e295e96c7c591eba2499b4f3ca58902dadbadcb16ecf76ea98e7b9413b66","source":{"kind":"arxiv","id":"2607.02089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02089","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02089v1","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02089","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"CQJOFFPJNR6F","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"CQJOFFPJNR6FSHV2","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"CQJOFFPJ","created_at":"2026-07-03T01:17:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CQJOFFPJNR6FSHV2ESM3J46KLC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T14:25:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"0793e482b44f4d60747a889d0876f2e6fee6983c259a4248353418a246dc2580","abstract_canon_sha256":"a37ac115271dc32ccdf7fed65e3a15f25ab43f4b679a25271d51fb1d8ad87869"},"schema_version":"1.0"},"canonical_sha256":"1412e295e96c7c591eba2499b4f3ca58902dadbadcb16ecf76ea98e7b9413b66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:41.960679Z","signature_b64":"ly5Fl57iBzathNuP25tbNbkR+PWC/JdlNS1rHx/uqJcz2w4BZ/cP6/HIENN9tIN57OP56HLSV3tfsHeHAVzxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1412e295e96c7c591eba2499b4f3ca58902dadbadcb16ecf76ea98e7b9413b66","last_reissued_at":"2026-07-03T01:17:41.960234Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:41.960234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02089","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"paccxUjr6pbdVkFS9MjLjHDKxW0c4S3UDvFg7bPtoI4mgpPKgbpbI8J/DMv5juHQnGR51CwK6SkKR1p5IRitAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T03:56:04.407555Z"},"content_sha256":"b4237ca1de1da7a724a39c8ee71e390bb75853e5c57ad5966f790e3523cb9a04","schema_version":"1.0","event_id":"sha256:b4237ca1de1da7a724a39c8ee71e390bb75853e5c57ad5966f790e3523cb9a04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CQJOFFPJNR6FSHV2ESM3J46KLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Cuong Tuan Nguyen, Dat Nguyen, Hoang M. Le, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Minh-Nhat Nguyen, Min Xu, Nguyen Nhat Huy, Phat Kim Huynh, Thanh-Huy Nguyen, Tien-Huy Nguyen, Ulas Bagci","submitted_at":"2026-07-01T14:25:43Z","abstract_excerpt":"Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Existing self-correction methods mitigate these issues but typically rely on post-training or carefully engineered feedback, incurring high computational cost. In this work, we revisit this challenge through the lens of emotional cues, asking whether they can activate latent self-correction behaviors in VLMs without additional training. \\textbf{We find that emotional signals serve as an effective trigger for self-correction, encouraging more cautio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02089","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/2607.02089/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lW/R2OPSDmMx0lXqF3gREz1miXvyhFZru8Qi3547dJ6aaIDddAd+ILRvuETNhLzzr76LvKt/VnAsExiaTyTVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T03:56:04.407926Z"},"content_sha256":"1bdddc54f241f0ddd9d8aa32974f788b600c628262337c591516f7e46f5f8f06","schema_version":"1.0","event_id":"sha256:1bdddc54f241f0ddd9d8aa32974f788b600c628262337c591516f7e46f5f8f06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQJOFFPJNR6FSHV2ESM3J46KLC/bundle.json","state_url":"https://pith.science/pith/CQJOFFPJNR6FSHV2ESM3J46KLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQJOFFPJNR6FSHV2ESM3J46KLC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T03:56:04Z","links":{"resolver":"https://pith.science/pith/CQJOFFPJNR6FSHV2ESM3J46KLC","bundle":"https://pith.science/pith/CQJOFFPJNR6FSHV2ESM3J46KLC/bundle.json","state":"https://pith.science/pith/CQJOFFPJNR6FSHV2ESM3J46KLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQJOFFPJNR6FSHV2ESM3J46KLC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQJOFFPJNR6FSHV2ESM3J46KLC","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":"a37ac115271dc32ccdf7fed65e3a15f25ab43f4b679a25271d51fb1d8ad87869","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T14:25:43Z","title_canon_sha256":"0793e482b44f4d60747a889d0876f2e6fee6983c259a4248353418a246dc2580"},"schema_version":"1.0","source":{"id":"2607.02089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02089","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02089v1","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02089","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"CQJOFFPJNR6F","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"CQJOFFPJNR6FSHV2","created_at":"2026-07-03T01:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"CQJOFFPJ","created_at":"2026-07-03T01:17:41Z"}],"graph_snapshots":[{"event_id":"sha256:1bdddc54f241f0ddd9d8aa32974f788b600c628262337c591516f7e46f5f8f06","target":"graph","created_at":"2026-07-03T01:17:41Z","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/2607.02089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Existing self-correction methods mitigate these issues but typically rely on post-training or carefully engineered feedback, incurring high computational cost. In this work, we revisit this challenge through the lens of emotional cues, asking whether they can activate latent self-correction behaviors in VLMs without additional training. \\textbf{We find that emotional signals serve as an effective trigger for self-correction, encouraging more cautio","authors_text":"Cuong Tuan Nguyen, Dat Nguyen, Hoang M. Le, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Minh-Nhat Nguyen, Min Xu, Nguyen Nhat Huy, Phat Kim Huynh, Thanh-Huy Nguyen, Tien-Huy Nguyen, Ulas Bagci","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T14:25:43Z","title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02089","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:b4237ca1de1da7a724a39c8ee71e390bb75853e5c57ad5966f790e3523cb9a04","target":"record","created_at":"2026-07-03T01:17:41Z","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":"a37ac115271dc32ccdf7fed65e3a15f25ab43f4b679a25271d51fb1d8ad87869","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T14:25:43Z","title_canon_sha256":"0793e482b44f4d60747a889d0876f2e6fee6983c259a4248353418a246dc2580"},"schema_version":"1.0","source":{"id":"2607.02089","kind":"arxiv","version":1}},"canonical_sha256":"1412e295e96c7c591eba2499b4f3ca58902dadbadcb16ecf76ea98e7b9413b66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1412e295e96c7c591eba2499b4f3ca58902dadbadcb16ecf76ea98e7b9413b66","first_computed_at":"2026-07-03T01:17:41.960234Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:41.960234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ly5Fl57iBzathNuP25tbNbkR+PWC/JdlNS1rHx/uqJcz2w4BZ/cP6/HIENN9tIN57OP56HLSV3tfsHeHAVzxAQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:41.960679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4237ca1de1da7a724a39c8ee71e390bb75853e5c57ad5966f790e3523cb9a04","sha256:1bdddc54f241f0ddd9d8aa32974f788b600c628262337c591516f7e46f5f8f06"],"state_sha256":"1f2d40c8b6adb430de66cd839b83d24ff4f7862428953886a966890126fab9bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJY3rXBPCqjBLGxauoFindIqe0jZDg1ZGVURmXk2XyVH0Hl57jxRK2sUTP68rpz+XqhL9/ApmXRHbT0ydx+3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T03:56:04.410268Z","bundle_sha256":"798a63ae5390c4d4e52114f8bab66cc3d032faf852875f3e9ded33f64718c608"}}