{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QIDQIPP64ARQQ2FCWORMD237F6","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":"95284d20bdf4e55320a41e17cc027064528873cd0264e411630e02aa81e72d20","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T16:45:12Z","title_canon_sha256":"b2df748ae3ed2314fb9fb4fbf68fa2b9e8f3ddd38cbd2c5a0efd52a338906b45"},"schema_version":"1.0","source":{"id":"2503.13360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13360","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13360v2","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13360","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"QIDQIPP64ARQ","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"QIDQIPP64ARQQ2FC","created_at":"2026-07-05T11:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"QIDQIPP6","created_at":"2026-07-05T11:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:819f4c0773171bb36ad8f1c525f24c17fc9c9c00a0f25784538f0549450c5da2","target":"graph","created_at":"2026-07-05T11:14:28Z","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/2503.13360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated enhanced reasoning capabilities, evolving from Chain-of-Thought (CoT) prompting to advanced, product-oriented solutions like OpenAI o1. During our re-implementation of this model, we noticed that in multimodal tasks requiring visual input (e.g., geometry problems), Multimodal LLMs (MLLMs) struggle to maintain focus on the visual information, in other words, MLLMs suffer from a gradual decline in attention to visual information as reasoning progresses, causing text-over-relied outputs. To investigate this, we ablate image inp","authors_text":"Hai-Long Sun, Han-Jia Ye, Houwen Peng, Zhun Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T16:45:12Z","title":"Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13360","kind":"arxiv","version":2},"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:f7fd398119015e270c5c3736c9d32b268d5b6a21c5d67baf1a4bab9b5a732b99","target":"record","created_at":"2026-07-05T11:14:28Z","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":"95284d20bdf4e55320a41e17cc027064528873cd0264e411630e02aa81e72d20","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T16:45:12Z","title_canon_sha256":"b2df748ae3ed2314fb9fb4fbf68fa2b9e8f3ddd38cbd2c5a0efd52a338906b45"},"schema_version":"1.0","source":{"id":"2503.13360","kind":"arxiv","version":2}},"canonical_sha256":"8207043dfee0230868a2b3a2c1eb7f2f8adaf752df1b634a773cec46c315835d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8207043dfee0230868a2b3a2c1eb7f2f8adaf752df1b634a773cec46c315835d","first_computed_at":"2026-07-05T11:14:28.049688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:28.049688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FKL4ZaHQ8dTik+iyk+jmipgpWiWnSLD7951p01bfROMVBGDZGceqjYxpz96/UG65uZ+C462C7k+pcL12EiDgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:28.050131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7fd398119015e270c5c3736c9d32b268d5b6a21c5d67baf1a4bab9b5a732b99","sha256:819f4c0773171bb36ad8f1c525f24c17fc9c9c00a0f25784538f0549450c5da2"],"state_sha256":"d61cc3539988b361db91140d7de470c70bebad55c437fa563c589d74236e9afa"}