{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CSCDP3RLMHJCD7SECEI6OGRONQ","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":"a0c769818756d0cb3631fab57660c7c30682d5fadf513931f4bf91bfbafbfc52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T05:48:59Z","title_canon_sha256":"bfd2cd8e5efdf9658cbbfd370cff7308fe0083d5551f76233b59ab9d66f87197"},"schema_version":"1.0","source":{"id":"2503.15871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15871","created_at":"2026-07-05T10:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15871v1","created_at":"2026-07-05T10:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15871","created_at":"2026-07-05T10:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"CSCDP3RLMHJC","created_at":"2026-07-05T10:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"CSCDP3RLMHJCD7SE","created_at":"2026-07-05T10:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"CSCDP3RL","created_at":"2026-07-05T10:36:00Z"}],"graph_snapshots":[{"event_id":"sha256:88fdc0a0c2ed19441f85e8c841f54ab4f49ddab94838324792747fcfe6718925","target":"graph","created_at":"2026-07-05T10:36:00Z","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/2503.15871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we tackle action-scene hallucination in Video Large Language Models (Video-LLMs), where models incorrectly predict actions based on the scene context or scenes based on observed actions. We observe that existing Video-LLMs often suffer from action-scene hallucination due to two main factors. First, existing Video-LLMs intermingle spatial and temporal features by applying an attention operation across all tokens. Second, they use the standard Rotary Position Embedding (RoPE), which causes the text tokens to overemphasize certain types of tokens depending on their sequential orders","authors_text":"Gunhee Lee, Jinhyung Kim, Jinwoo Choi, Kyungho Bae, Sihaeng Lee, Soonyoung Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T05:48:59Z","title":"MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15871","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:c5c017adbad803c5a2d685f9170d685d2c09f0b8d895a75a23be5533cadf5c4b","target":"record","created_at":"2026-07-05T10:36:00Z","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":"a0c769818756d0cb3631fab57660c7c30682d5fadf513931f4bf91bfbafbfc52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T05:48:59Z","title_canon_sha256":"bfd2cd8e5efdf9658cbbfd370cff7308fe0083d5551f76233b59ab9d66f87197"},"schema_version":"1.0","source":{"id":"2503.15871","kind":"arxiv","version":1}},"canonical_sha256":"148437ee2b61d221fe441111e71a2e6c24175429b60dba7abc5c61551354d8eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"148437ee2b61d221fe441111e71a2e6c24175429b60dba7abc5c61551354d8eb","first_computed_at":"2026-07-05T10:36:00.412259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:00.412259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qxdy+ze9a7JFs/2DphbicJ9ZHH2IdIH6OBOOnnzND3fAzC5iLhwPXcXONY77rVPUBfhPoujiI7UK8dW+vImoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:00.412752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5c017adbad803c5a2d685f9170d685d2c09f0b8d895a75a23be5533cadf5c4b","sha256:88fdc0a0c2ed19441f85e8c841f54ab4f49ddab94838324792747fcfe6718925"],"state_sha256":"a713aacc178cc3080fb9cb4b5fc16155214e03f9e7de19e4023e379714cefb5d"}