{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5BFESIVRYLOKSEYAEZSV5RQTN3","short_pith_number":"pith:5BFESIVR","schema_version":"1.0","canonical_sha256":"e84a4922b1c2dca9130026655ec6136ed739e1ef7aab2ee0c364bfaf52a25c5b","source":{"kind":"arxiv","id":"2605.21931","version":1},"attestation_state":"computed","paper":{"title":"EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bihan Wen, Han Qiu, Qi She, Shiqi Huang, Zhongrong Zuo, Ziyue Wang","submitted_at":"2026-05-21T03:00:35Z","abstract_excerpt":"Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, existing RL pipelines rely heavily on human-annotated tasks and solutions, making them costly to scale and fundamentally constrained by human expertise. Self-evolving frameworks have recently emerged as a promising alternative through autonomous Questioner-Solver self-play. Unfortunately, these approaches are primarily designed for static modalities such as text and images, fundamentally failing to capture the temporal dynamics that are central "},"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":"2605.21931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T03:00:35Z","cross_cats_sorted":[],"title_canon_sha256":"649f2bbcf5c2f85c258eb3c849b3b4f5b3f9de19b1866502fe0bb14083f50937","abstract_canon_sha256":"f98a621c5a80880dba20d5f4b3011e74e48ca79805ff4da53f44a9efe00d5a1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:15.468348Z","signature_b64":"+pj9B7Uge0+aZgyUYPgecdWlf6W68MGnG6f4ONHqbURYzxCvUOyRm9pm/yBJSvMLGpJtKgxpi+KgCGF4+XS9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e84a4922b1c2dca9130026655ec6136ed739e1ef7aab2ee0c364bfaf52a25c5b","last_reissued_at":"2026-05-22T01:04:15.467550Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:15.467550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bihan Wen, Han Qiu, Qi She, Shiqi Huang, Zhongrong Zuo, Ziyue Wang","submitted_at":"2026-05-21T03:00:35Z","abstract_excerpt":"Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, existing RL pipelines rely heavily on human-annotated tasks and solutions, making them costly to scale and fundamentally constrained by human expertise. Self-evolving frameworks have recently emerged as a promising alternative through autonomous Questioner-Solver self-play. Unfortunately, these approaches are primarily designed for static modalities such as text and images, fundamentally failing to capture the temporal dynamics that are central "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21931","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/2605.21931/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":"2605.21931","created_at":"2026-05-22T01:04:15.467691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21931v1","created_at":"2026-05-22T01:04:15.467691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21931","created_at":"2026-05-22T01:04:15.467691+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BFESIVRYLOK","created_at":"2026-05-22T01:04:15.467691+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BFESIVRYLOKSEYA","created_at":"2026-05-22T01:04:15.467691+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BFESIVR","created_at":"2026-05-22T01:04:15.467691+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/5BFESIVRYLOKSEYAEZSV5RQTN3","json":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3.json","graph_json":"https://pith.science/api/pith-number/5BFESIVRYLOKSEYAEZSV5RQTN3/graph.json","events_json":"https://pith.science/api/pith-number/5BFESIVRYLOKSEYAEZSV5RQTN3/events.json","paper":"https://pith.science/paper/5BFESIVR"},"agent_actions":{"view_html":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3","download_json":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3.json","view_paper":"https://pith.science/paper/5BFESIVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21931&json=true","fetch_graph":"https://pith.science/api/pith-number/5BFESIVRYLOKSEYAEZSV5RQTN3/graph.json","fetch_events":"https://pith.science/api/pith-number/5BFESIVRYLOKSEYAEZSV5RQTN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3/action/storage_attestation","attest_author":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3/action/author_attestation","sign_citation":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3/action/citation_signature","submit_replication":"https://pith.science/pith/5BFESIVRYLOKSEYAEZSV5RQTN3/action/replication_record"}},"created_at":"2026-05-22T01:04:15.467691+00:00","updated_at":"2026-05-22T01:04:15.467691+00:00"}