{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R4HZHIS3NG4HGC2BWB3Y363HTJ","short_pith_number":"pith:R4HZHIS3","canonical_record":{"source":{"id":"2607.23944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T02:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"08802baa91c9c0c1c8b34be4c2c22662c40be817df86cca5535a58df072cee58","abstract_canon_sha256":"5b07ce760b417765e4bb78faa8e4e2372c9b5c2be5dabb44d65f5d80bb67b1ab"},"schema_version":"1.0"},"canonical_sha256":"8f0f93a25b69b8730b41b0778dfb679a62c6ee7eae8726b5e71b73b2a1085243","source":{"kind":"arxiv","id":"2607.23944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23944","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23944v1","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23944","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"R4HZHIS3NG4H","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"R4HZHIS3NG4HGC2B","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"R4HZHIS3","created_at":"2026-07-28T01:23:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R4HZHIS3NG4HGC2BWB3Y363HTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23944","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T02:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"08802baa91c9c0c1c8b34be4c2c22662c40be817df86cca5535a58df072cee58","abstract_canon_sha256":"5b07ce760b417765e4bb78faa8e4e2372c9b5c2be5dabb44d65f5d80bb67b1ab"},"schema_version":"1.0"},"canonical_sha256":"8f0f93a25b69b8730b41b0778dfb679a62c6ee7eae8726b5e71b73b2a1085243","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:37.054013Z","signature_b64":"q/C8NQ8hEISo0gVkDMNIqyHKG/Qs8yB0R/EcpdFSQBGXD4w7NP9uY8JFzA87bpWH3MQ1juB5e7FOOiwkepfWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f0f93a25b69b8730b41b0778dfb679a62c6ee7eae8726b5e71b73b2a1085243","last_reissued_at":"2026-07-28T01:23:37.053126Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:37.053126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23944","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":"2026-07-28T01:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+CeYYru5P1v4FCjxULvR2mXwApqlnKX7/PozRYDt8Lx8PZViZhhcTviYycolAhToGu0MVWnKRIS3abyriGmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T15:37:48.176844Z"},"content_sha256":"2f654f55ba548f0bbb311b31f74e76e83d22517e2440853b826993d93598d139","schema_version":"1.0","event_id":"sha256:2f654f55ba548f0bbb311b31f74e76e83d22517e2440853b826993d93598d139"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R4HZHIS3NG4HGC2BWB3Y363HTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Yang, Jin Wang, Xuejie Zhang","submitted_at":"2026-07-27T02:40:49Z","abstract_excerpt":"Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question-relevant regions. However, multimodal large language models may deviate from this pattern due to attention drift and the underutilization of visual evidence, which can lead to hallucinations. To mitigate these issues, this study proposes a Dual-Indicator Guided Contrastive Alignment (DICA), which tracks two information-theoretic indicators during inference: Visual Attention Entropy (VAE), which reflects the concentration of visual attention, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23944","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/2607.23944/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":"2026-07-28T01:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uE71RxWOOtI1faYJO5bOSbIsjVKSLqeblWPxPUEydKOA0vGb0KXBjK93nhTi37JqeaapMIZqJgJc/Y0+2F/HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T15:37:48.177373Z"},"content_sha256":"36539575a7cdc424a63423c8cb04bfce2f3b75d99b98c6c91cc345e538d40231","schema_version":"1.0","event_id":"sha256:36539575a7cdc424a63423c8cb04bfce2f3b75d99b98c6c91cc345e538d40231"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ/bundle.json","state_url":"https://pith.science/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ/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":"2026-08-02T15:37:48Z","links":{"resolver":"https://pith.science/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ","bundle":"https://pith.science/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ/bundle.json","state":"https://pith.science/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4HZHIS3NG4HGC2BWB3Y363HTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R4HZHIS3NG4HGC2BWB3Y363HTJ","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":"5b07ce760b417765e4bb78faa8e4e2372c9b5c2be5dabb44d65f5d80bb67b1ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T02:40:49Z","title_canon_sha256":"08802baa91c9c0c1c8b34be4c2c22662c40be817df86cca5535a58df072cee58"},"schema_version":"1.0","source":{"id":"2607.23944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23944","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23944v1","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23944","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"R4HZHIS3NG4H","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"R4HZHIS3NG4HGC2B","created_at":"2026-07-28T01:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"R4HZHIS3","created_at":"2026-07-28T01:23:37Z"}],"graph_snapshots":[{"event_id":"sha256:36539575a7cdc424a63423c8cb04bfce2f3b75d99b98c6c91cc345e538d40231","target":"graph","created_at":"2026-07-28T01:23:37Z","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/2607.23944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question-relevant regions. However, multimodal large language models may deviate from this pattern due to attention drift and the underutilization of visual evidence, which can lead to hallucinations. To mitigate these issues, this study proposes a Dual-Indicator Guided Contrastive Alignment (DICA), which tracks two information-theoretic indicators during inference: Visual Attention Entropy (VAE), which reflects the concentration of visual attention, a","authors_text":"Hao Yang, Jin Wang, Xuejie Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T02:40:49Z","title":"DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23944","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":"sha256:2f654f55ba548f0bbb311b31f74e76e83d22517e2440853b826993d93598d139","target":"record","created_at":"2026-07-28T01:23:37Z","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":"5b07ce760b417765e4bb78faa8e4e2372c9b5c2be5dabb44d65f5d80bb67b1ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T02:40:49Z","title_canon_sha256":"08802baa91c9c0c1c8b34be4c2c22662c40be817df86cca5535a58df072cee58"},"schema_version":"1.0","source":{"id":"2607.23944","kind":"arxiv","version":1}},"canonical_sha256":"8f0f93a25b69b8730b41b0778dfb679a62c6ee7eae8726b5e71b73b2a1085243","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f0f93a25b69b8730b41b0778dfb679a62c6ee7eae8726b5e71b73b2a1085243","first_computed_at":"2026-07-28T01:23:37.053126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:37.053126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q/C8NQ8hEISo0gVkDMNIqyHKG/Qs8yB0R/EcpdFSQBGXD4w7NP9uY8JFzA87bpWH3MQ1juB5e7FOOiwkepfWDA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:37.054013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f654f55ba548f0bbb311b31f74e76e83d22517e2440853b826993d93598d139","sha256:36539575a7cdc424a63423c8cb04bfce2f3b75d99b98c6c91cc345e538d40231"],"state_sha256":"31ff26f089b592e95560be3cffeae209044a13b6147073e4ae831ad6fe5931a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IqDMnIF0FqZ/20S1DYFNftp+OQLWJcNPoEF3C4OxpbYBccR2C/vpbiE2h83mTpPsrIL6ekAji3J+PstAmAwfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T15:37:48.181590Z","bundle_sha256":"d4abf15296f4d92de27e527f4e2f2c47a5a995a0c9236137bc47c8dcf9ae6dc0"}}