{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KDJ2K6IS3T6MESZP7EFRUKMWFM","short_pith_number":"pith:KDJ2K6IS","canonical_record":{"source":{"id":"2607.22013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T06:22:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fdbf58257023968660cfc8fd1f1e9e338b7640eae606d2b08b9cf518e10a75bd","abstract_canon_sha256":"3b48058d486ffe4a81ab786b8106e4f97d427638e8053b5513a814a1e34db858"},"schema_version":"1.0"},"canonical_sha256":"50d3a57912dcfcc24b2ff90b1a29962b2d3217ca09d26aeb7459c60af8f44a97","source":{"kind":"arxiv","id":"2607.22013","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22013","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22013v1","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22013","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"KDJ2K6IS3T6M","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"KDJ2K6IS3T6MESZP","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"KDJ2K6IS","created_at":"2026-07-27T01:20:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KDJ2K6IS3T6MESZP7EFRUKMWFM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T06:22:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fdbf58257023968660cfc8fd1f1e9e338b7640eae606d2b08b9cf518e10a75bd","abstract_canon_sha256":"3b48058d486ffe4a81ab786b8106e4f97d427638e8053b5513a814a1e34db858"},"schema_version":"1.0"},"canonical_sha256":"50d3a57912dcfcc24b2ff90b1a29962b2d3217ca09d26aeb7459c60af8f44a97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:43.152947Z","signature_b64":"POG6MrtiVeYDkiu7woZD9y9Knv+00bH2TN+lKcTBGdVtduP3Skn4opby+3V7MdgujrqUnSSypSf9Rz9PSlb7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d3a57912dcfcc24b2ff90b1a29962b2d3217ca09d26aeb7459c60af8f44a97","last_reissued_at":"2026-07-27T01:20:43.152144Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:43.152144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22013","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":"2026-07-27T01:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N9mXSss+bv8NfRkLBB1IJS/jwtRoZfHuuiXFnEGTxRDaRpM63oQ/QzYj4qlRzlAviYeSGE+/hNkxBCcrBLFeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:20:46.473943Z"},"content_sha256":"a0f61a1ca95383b44bbb3065afe1b3ced4beebffebbcc2491fe21636f24ac2d7","schema_version":"1.0","event_id":"sha256:a0f61a1ca95383b44bbb3065afe1b3ced4beebffebbcc2491fe21636f24ac2d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KDJ2K6IS3T6MESZP7EFRUKMWFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Yang, Jin Wang, Xuejie Zhang","submitted_at":"2026-07-24T06:22:40Z","abstract_excerpt":"Multimodal chain-of-thought (CoT) reasoning integrates visual and textual cues through step-by-step inference. In small models with limited token budgets, modality-interaction fusion often suppresses tiny cross-modal differences. In particular, multimodal CoT often struggles when different images pair with identical text or different texts pair with an identical image, making such inputs nearly indistinguishable after fusion. This study proposes Visual Saliency Steering Distillation (VSSD). VSSD leverages the attention maps of multimodal large language models to generate perturbed images that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22013","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/2607.22013/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":"2026-07-27T01:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mhlaYxr4Fce9LMsLzhm6ZyvP0pvsx1PIfo1ULJSv91Uqqkrg2LEM9yPPD/E3z7la8WYpCOAYe8YXQ3qgoxHODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:20:46.474827Z"},"content_sha256":"3838950ed6982206aa3d81aba2ac9993235e85b5c818e19fbf336fe1674c6b0b","schema_version":"1.0","event_id":"sha256:3838950ed6982206aa3d81aba2ac9993235e85b5c818e19fbf336fe1674c6b0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM/bundle.json","state_url":"https://pith.science/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM/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":"2026-08-04T20:20:46Z","links":{"resolver":"https://pith.science/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM","bundle":"https://pith.science/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM/bundle.json","state":"https://pith.science/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KDJ2K6IS3T6MESZP7EFRUKMWFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KDJ2K6IS3T6MESZP7EFRUKMWFM","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":"3b48058d486ffe4a81ab786b8106e4f97d427638e8053b5513a814a1e34db858","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T06:22:40Z","title_canon_sha256":"fdbf58257023968660cfc8fd1f1e9e338b7640eae606d2b08b9cf518e10a75bd"},"schema_version":"1.0","source":{"id":"2607.22013","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22013","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22013v1","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22013","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"KDJ2K6IS3T6M","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"KDJ2K6IS3T6MESZP","created_at":"2026-07-27T01:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"KDJ2K6IS","created_at":"2026-07-27T01:20:43Z"}],"graph_snapshots":[{"event_id":"sha256:3838950ed6982206aa3d81aba2ac9993235e85b5c818e19fbf336fe1674c6b0b","target":"graph","created_at":"2026-07-27T01:20:43Z","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/2607.22013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal chain-of-thought (CoT) reasoning integrates visual and textual cues through step-by-step inference. In small models with limited token budgets, modality-interaction fusion often suppresses tiny cross-modal differences. In particular, multimodal CoT often struggles when different images pair with identical text or different texts pair with an identical image, making such inputs nearly indistinguishable after fusion. This study proposes Visual Saliency Steering Distillation (VSSD). VSSD leverages the attention maps of multimodal large language models to generate perturbed images that ","authors_text":"Hao Yang, Jin Wang, Xuejie Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T06:22:40Z","title":"Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22013","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:a0f61a1ca95383b44bbb3065afe1b3ced4beebffebbcc2491fe21636f24ac2d7","target":"record","created_at":"2026-07-27T01:20:43Z","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":"3b48058d486ffe4a81ab786b8106e4f97d427638e8053b5513a814a1e34db858","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T06:22:40Z","title_canon_sha256":"fdbf58257023968660cfc8fd1f1e9e338b7640eae606d2b08b9cf518e10a75bd"},"schema_version":"1.0","source":{"id":"2607.22013","kind":"arxiv","version":1}},"canonical_sha256":"50d3a57912dcfcc24b2ff90b1a29962b2d3217ca09d26aeb7459c60af8f44a97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50d3a57912dcfcc24b2ff90b1a29962b2d3217ca09d26aeb7459c60af8f44a97","first_computed_at":"2026-07-27T01:20:43.152144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:43.152144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"POG6MrtiVeYDkiu7woZD9y9Knv+00bH2TN+lKcTBGdVtduP3Skn4opby+3V7MdgujrqUnSSypSf9Rz9PSlb7Dw==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:43.152947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22013","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0f61a1ca95383b44bbb3065afe1b3ced4beebffebbcc2491fe21636f24ac2d7","sha256:3838950ed6982206aa3d81aba2ac9993235e85b5c818e19fbf336fe1674c6b0b"],"state_sha256":"3a1330a9caef4208bc67cb40125311e2c006484af76010e23779f289539f7d7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaUbQMJJP32hhM+KByrA9ul2s24h78vc4O/IIhTr4kPSY4AfIp1y+c4KnVfnnpvvnGkIcJjqgaunORp/bWeuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:20:46.500420Z","bundle_sha256":"6f04e675135a518695abc2767d636045225460d50dea431362df32f63a26e72f"}}