{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LRZQUDBGR4UYG43VGUK4BAFFKH","short_pith_number":"pith:LRZQUDBG","schema_version":"1.0","canonical_sha256":"5c730a0c268f298373753515c080a551ecfcd78a1fc0c0497ae290f806d2004e","source":{"kind":"arxiv","id":"2606.24726","version":1},"attestation_state":"computed","paper":{"title":"SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Kanghui Tian, Sheng Xia, Shoujun Zhou, Tianxiang Jiang, Yi Wang, Zhengqin Lai","submitted_at":"2026-06-23T15:50:33Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.24726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T15:50:33Z","cross_cats_sorted":[],"title_canon_sha256":"3660ea343531030af7fdc7a85f97403d9c5f5b0c3f7b966dba18197166dae043","abstract_canon_sha256":"9bed7e42bd93d039bdd6cdf9bbc2877973b7493f16ef797f7d6f8f63feac7086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:40.202986Z","signature_b64":"el9PMOP+q4vf8OoLJszrZYncZNFA+saVQGNa1zJ69InBWoPa80ic4deJ0ezqEG0GATlbdyAFG5YOaTJeZEq6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c730a0c268f298373753515c080a551ecfcd78a1fc0c0497ae290f806d2004e","last_reissued_at":"2026-06-24T01:15:40.202627Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:40.202627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SER: Learning to Ground Video Reasoning with Semantic Evidence Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Kanghui Tian, Sheng Xia, Shoujun Zhou, Tianxiang Jiang, Yi Wang, Zhengqin Lai","submitted_at":"2026-06-23T15:50:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24726","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/2606.24726/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.24726","created_at":"2026-06-24T01:15:40.202688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24726v1","created_at":"2026-06-24T01:15:40.202688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24726","created_at":"2026-06-24T01:15:40.202688+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRZQUDBGR4UY","created_at":"2026-06-24T01:15:40.202688+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRZQUDBGR4UYG43V","created_at":"2026-06-24T01:15:40.202688+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRZQUDBG","created_at":"2026-06-24T01:15:40.202688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH","json":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH.json","graph_json":"https://pith.science/api/pith-number/LRZQUDBGR4UYG43VGUK4BAFFKH/graph.json","events_json":"https://pith.science/api/pith-number/LRZQUDBGR4UYG43VGUK4BAFFKH/events.json","paper":"https://pith.science/paper/LRZQUDBG"},"agent_actions":{"view_html":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH","download_json":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH.json","view_paper":"https://pith.science/paper/LRZQUDBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24726&json=true","fetch_graph":"https://pith.science/api/pith-number/LRZQUDBGR4UYG43VGUK4BAFFKH/graph.json","fetch_events":"https://pith.science/api/pith-number/LRZQUDBGR4UYG43VGUK4BAFFKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH/action/storage_attestation","attest_author":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH/action/author_attestation","sign_citation":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH/action/citation_signature","submit_replication":"https://pith.science/pith/LRZQUDBGR4UYG43VGUK4BAFFKH/action/replication_record"}},"created_at":"2026-06-24T01:15:40.202688+00:00","updated_at":"2026-06-24T01:15:40.202688+00:00"}