{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S24J2ZRYOPNRUMGRWMC2XWLCER","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":"4f60bd0fe7b962ea639131be20573e3132f77856c26b087ac402ed477bee5bfc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T04:38:02Z","title_canon_sha256":"c2e62462dfe5afea511e59cf714bbb7c71a92a95f870ae9fa9f78267d3d686ef"},"schema_version":"1.0","source":{"id":"2605.21988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21988","created_at":"2026-05-22T01:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21988v1","created_at":"2026-05-22T01:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21988","created_at":"2026-05-22T01:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"S24J2ZRYOPNR","created_at":"2026-05-22T01:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"S24J2ZRYOPNRUMGR","created_at":"2026-05-22T01:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"S24J2ZRY","created_at":"2026-05-22T01:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:7edf2dcb7f7bdd7599f637203339051dd6dc43370f0bd8c33ab61099928e3c97","target":"graph","created_at":"2026-05-22T01:04:19Z","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/2605.21988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video large language models (Video LLMs) achieve strong benchmark accuracy, yet often answer video questions through shortcuts such as single-frame cues and language priors rather than by tracking spatiotemporal dynamics. This issue is exacerbated in RL post-training, where correctness-only rewards can further reinforce shortcut policies that obtain high reward without tracking video dynamics. We address this by asking a controlled counterfactual question: if the visual world changed while the question remained fixed, should the answer change or stay the same? Based on this view, we propose \\t","authors_text":"Bohai Gu, Dazhao Du, Eric Liu, Fangqi Zhu, Jialong Qin, Jian Liu, Song Guo, Tao Han, Xi Chen, Yujia Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T04:38:02Z","title":"Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21988","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:f2c6f6ea1e574b0fe46773606d1e8351ad412dca77c0806b4c05dd383bf197d8","target":"record","created_at":"2026-05-22T01:04:19Z","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":"4f60bd0fe7b962ea639131be20573e3132f77856c26b087ac402ed477bee5bfc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T04:38:02Z","title_canon_sha256":"c2e62462dfe5afea511e59cf714bbb7c71a92a95f870ae9fa9f78267d3d686ef"},"schema_version":"1.0","source":{"id":"2605.21988","kind":"arxiv","version":1}},"canonical_sha256":"96b89d663873db1a30d1b305abd962245601016258ce1e824a68370f027e2c5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96b89d663873db1a30d1b305abd962245601016258ce1e824a68370f027e2c5d","first_computed_at":"2026-05-22T01:04:19.069402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:19.069402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GhmvU8pzHOfNmz6FTqjyQJ9Z08qBuqZxPwtMHiRXUe2+IzUJ2D88Hg8eSpO1zIflDL9O3AHLg4Mw2IftIX8lCA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:19.070178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2c6f6ea1e574b0fe46773606d1e8351ad412dca77c0806b4c05dd383bf197d8","sha256:7edf2dcb7f7bdd7599f637203339051dd6dc43370f0bd8c33ab61099928e3c97"],"state_sha256":"f5b081ed479a29f1b06dac6abcb99bba5002220a7101bf4546bfab4ce22d67fa"}