{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LRZQUDBGR4UYG43VGUK4BAFFKH","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":"9bed7e42bd93d039bdd6cdf9bbc2877973b7493f16ef797f7d6f8f63feac7086","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T15:50:33Z","title_canon_sha256":"3660ea343531030af7fdc7a85f97403d9c5f5b0c3f7b966dba18197166dae043"},"schema_version":"1.0","source":{"id":"2606.24726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24726","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24726v1","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24726","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"LRZQUDBGR4UY","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"LRZQUDBGR4UYG43V","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"LRZQUDBG","created_at":"2026-06-24T01:15:40Z"}],"graph_snapshots":[{"event_id":"sha256:89ecf85352c3c2e00b2e85bb5298003669e01d64259580bf50e8acca47d68183","target":"graph","created_at":"2026-06-24T01:15:40Z","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/2606.24726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video MLLMs often struggle with fine-grained spatio-temporal reasoning, sometimes generating correct answers based on irrelevant frames or objects. Although outputting spatio-temporal evidence during reasoning is a promising direction, existing RL frameworks typically rely on geometry-only (IoU) rewards, which can be sensitive to boundary perturbations and overlook semantic alignment. To address this, we propose Semantic Evidence Reward (SER), which reformulates spatio-temporal evidence grounding as a constrained verification task. Instead of computing pixel-level overlap, SER uses a referee V","authors_text":"Bin Li, Kanghui Tian, Sheng Xia, Shoujun Zhou, Tianxiang Jiang, Yi Wang, Zhengqin Lai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T15:50:33Z","title":"SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24726","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:b2cf3593383285a896617ea7dbc7f677ba08d0dfa1fba21ede6194ce99bad4b3","target":"record","created_at":"2026-06-24T01:15:40Z","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":"9bed7e42bd93d039bdd6cdf9bbc2877973b7493f16ef797f7d6f8f63feac7086","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T15:50:33Z","title_canon_sha256":"3660ea343531030af7fdc7a85f97403d9c5f5b0c3f7b966dba18197166dae043"},"schema_version":"1.0","source":{"id":"2606.24726","kind":"arxiv","version":1}},"canonical_sha256":"5c730a0c268f298373753515c080a551ecfcd78a1fc0c0497ae290f806d2004e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c730a0c268f298373753515c080a551ecfcd78a1fc0c0497ae290f806d2004e","first_computed_at":"2026-06-24T01:15:40.202627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:40.202627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"el9PMOP+q4vf8OoLJszrZYncZNFA+saVQGNa1zJ69InBWoPa80ic4deJ0ezqEG0GATlbdyAFG5YOaTJeZEq6CQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:40.202986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2cf3593383285a896617ea7dbc7f677ba08d0dfa1fba21ede6194ce99bad4b3","sha256:89ecf85352c3c2e00b2e85bb5298003669e01d64259580bf50e8acca47d68183"],"state_sha256":"6ffb1ac166178eaa6bc2b0cea02b3dee42db8f20ee60f1dcdb5dcdc480c01f4d"}