{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IBSRN6RD3MXBT2KC76ZH3FGAZ5","short_pith_number":"pith:IBSRN6RD","schema_version":"1.0","canonical_sha256":"406516fa23db2e19e942ffb27d94c0cf46e6ee06f67dd8620aa878371883788b","source":{"kind":"arxiv","id":"2605.26441","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Chen, Daizong Liu, Jianfeng Dong, Keke Tang, Pan Zhou, Wanlong Fang, Xiang Fang, Xiaoye Qu, Yu Cheng, Zeyu Xiong","submitted_at":"2026-05-26T01:54:17Z","abstract_excerpt":"This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks have overlooked two indispensable issues: 1) Coarse-grained cross-modal learning: previous methods solely capture the global video-level alignment with the query, failing to model the detailed consistency between video frames and "},"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":"2605.26441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T01:54:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ab0c6af3af192211460c54d4113826961e1f0bdb212cf8eef1c3db2eac98f16","abstract_canon_sha256":"ca16950f5fb3e871f542402718e94d5ec3760eb8e687681be7da32a4b266ad38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:18.140457Z","signature_b64":"2mxD+IcELMU8Btzt9mGDPrNgcjgwqWiIc7Y1xlAk/rwQDHcy0JERLD+MX6RfaVBjxdYbOexO7I348VTlgaexAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"406516fa23db2e19e942ffb27d94c0cf46e6ee06f67dd8620aa878371883788b","last_reissued_at":"2026-05-27T01:05:18.139826Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:18.139826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Chen, Daizong Liu, Jianfeng Dong, Keke Tang, Pan Zhou, Wanlong Fang, Xiang Fang, Xiaoye Qu, Yu Cheng, Zeyu Xiong","submitted_at":"2026-05-26T01:54:17Z","abstract_excerpt":"This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks have overlooked two indispensable issues: 1) Coarse-grained cross-modal learning: previous methods solely capture the global video-level alignment with the query, failing to model the detailed consistency between video frames and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26441","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/2605.26441/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":"2605.26441","created_at":"2026-05-27T01:05:18.139935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26441v1","created_at":"2026-05-27T01:05:18.139935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26441","created_at":"2026-05-27T01:05:18.139935+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBSRN6RD3MXB","created_at":"2026-05-27T01:05:18.139935+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBSRN6RD3MXBT2KC","created_at":"2026-05-27T01:05:18.139935+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBSRN6RD","created_at":"2026-05-27T01:05:18.139935+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/IBSRN6RD3MXBT2KC76ZH3FGAZ5","json":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5.json","graph_json":"https://pith.science/api/pith-number/IBSRN6RD3MXBT2KC76ZH3FGAZ5/graph.json","events_json":"https://pith.science/api/pith-number/IBSRN6RD3MXBT2KC76ZH3FGAZ5/events.json","paper":"https://pith.science/paper/IBSRN6RD"},"agent_actions":{"view_html":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5","download_json":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5.json","view_paper":"https://pith.science/paper/IBSRN6RD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26441&json=true","fetch_graph":"https://pith.science/api/pith-number/IBSRN6RD3MXBT2KC76ZH3FGAZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/IBSRN6RD3MXBT2KC76ZH3FGAZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5/action/storage_attestation","attest_author":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5/action/author_attestation","sign_citation":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5/action/citation_signature","submit_replication":"https://pith.science/pith/IBSRN6RD3MXBT2KC76ZH3FGAZ5/action/replication_record"}},"created_at":"2026-05-27T01:05:18.139935+00:00","updated_at":"2026-05-27T01:05:18.139935+00:00"}