{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CGRJCBEZPWM7PB6DV6LNR57NCV","short_pith_number":"pith:CGRJCBEZ","schema_version":"1.0","canonical_sha256":"11a29104997d99f787c3af96d8f7ed155f428e3b9840796be7e0862054363336","source":{"kind":"arxiv","id":"2507.04702","version":1},"attestation_state":"computed","paper":{"title":"Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feifei Zhang, Feng Yue, Junming Jiao, Rong Shen, Shiwen Cao, Zhaoxing Zhang, Zhengyu Liang","submitted_at":"2025-07-07T06:51:40Z","abstract_excerpt":"Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of information and redundancy than texts or images. Models should present comprehensive understanding of the whole video to accurately retrieve query-relevant clips. We thus propose Tempo-R0: a Video Multimodal Large Language Model (Video-MLLM) for the temporal video grounding task via multimodal temporal sensing reinforcement. Specifically, during the preprocess"},"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":"2507.04702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T06:51:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98973f654637ab30c9aa4a87f84d02d6de2e0a674311b9fe5d52539930e8d842","abstract_canon_sha256":"57fd69a2c4032f4b7378bb7072848832a1b27c554afb86dc0f10f767922bd188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:52.407596Z","signature_b64":"JdgMQmU7jhERvGJuJVpv6sQAYh2L0SVtyLA6vDS0L2ei1QMnOHYsGC10VqGf/vR7yxDjXedsZBCXWLbg5ojkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11a29104997d99f787c3af96d8f7ed155f428e3b9840796be7e0862054363336","last_reissued_at":"2026-07-05T11:32:52.407003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:52.407003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feifei Zhang, Feng Yue, Junming Jiao, Rong Shen, Shiwen Cao, Zhaoxing Zhang, Zhengyu Liang","submitted_at":"2025-07-07T06:51:40Z","abstract_excerpt":"Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of information and redundancy than texts or images. Models should present comprehensive understanding of the whole video to accurately retrieve query-relevant clips. We thus propose Tempo-R0: a Video Multimodal Large Language Model (Video-MLLM) for the temporal video grounding task via multimodal temporal sensing reinforcement. Specifically, during the preprocess"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04702","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/2507.04702/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":"2507.04702","created_at":"2026-07-05T11:32:52.407091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04702v1","created_at":"2026-07-05T11:32:52.407091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04702","created_at":"2026-07-05T11:32:52.407091+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGRJCBEZPWM7","created_at":"2026-07-05T11:32:52.407091+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGRJCBEZPWM7PB6D","created_at":"2026-07-05T11:32:52.407091+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGRJCBEZ","created_at":"2026-07-05T11:32:52.407091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21954","citing_title":"MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02994","citing_title":"Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV","json":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV.json","graph_json":"https://pith.science/api/pith-number/CGRJCBEZPWM7PB6DV6LNR57NCV/graph.json","events_json":"https://pith.science/api/pith-number/CGRJCBEZPWM7PB6DV6LNR57NCV/events.json","paper":"https://pith.science/paper/CGRJCBEZ"},"agent_actions":{"view_html":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV","download_json":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV.json","view_paper":"https://pith.science/paper/CGRJCBEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04702&json=true","fetch_graph":"https://pith.science/api/pith-number/CGRJCBEZPWM7PB6DV6LNR57NCV/graph.json","fetch_events":"https://pith.science/api/pith-number/CGRJCBEZPWM7PB6DV6LNR57NCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV/action/storage_attestation","attest_author":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV/action/author_attestation","sign_citation":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV/action/citation_signature","submit_replication":"https://pith.science/pith/CGRJCBEZPWM7PB6DV6LNR57NCV/action/replication_record"}},"created_at":"2026-07-05T11:32:52.407091+00:00","updated_at":"2026-07-05T11:32:52.407091+00:00"}