{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6P2VRVAXVAFJDO542R6RDZIFIW","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":"02aad3f0010cb8006bbf24dd21f6d3992b183da75c3df562533b29530f639c83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T17:50:53Z","title_canon_sha256":"42286d99452ecfcca0751b3e98f4836e3fa9ebb18fb007caeed5f44bab70d110"},"schema_version":"1.0","source":{"id":"2412.07704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07704","created_at":"2026-07-05T09:47:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07704v1","created_at":"2026-07-05T09:47:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07704","created_at":"2026-07-05T09:47:14Z"},{"alias_kind":"pith_short_12","alias_value":"6P2VRVAXVAFJ","created_at":"2026-07-05T09:47:14Z"},{"alias_kind":"pith_short_16","alias_value":"6P2VRVAXVAFJDO54","created_at":"2026-07-05T09:47:14Z"},{"alias_kind":"pith_short_8","alias_value":"6P2VRVAX","created_at":"2026-07-05T09:47:14Z"}],"graph_snapshots":[{"event_id":"sha256:61fdea22ff413e1c1a65be43dc8fe068b6eb3e1a7e93b0f268c191de4322cb25","target":"graph","created_at":"2026-07-05T09:47:14Z","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/2412.07704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In various video-language learning tasks, the challenge of achieving cross-modality alignment with multi-grained data persists. We propose a method to tackle this challenge from two crucial perspectives: data and modeling. Given the absence of a multi-grained video-text pretraining dataset, we introduce a Granularity EXpansion (GEX) method with Integration and Compression operations to expand the granularity of a single-grained dataset. To better model multi-grained data, we introduce an Iterative Approximation Module (IAM), which embeds multi-grained videos and texts into a unified, low-dimen","authors_text":"David Fan, Jue Wang, Linda Liu, Vimal Bhat, Xiang Hao, Xinyu Li, Yicheng Wang, Zhenlin Xu, Zhikang Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T17:50:53Z","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07704","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":"sha256:4d293321a08771830a0ed7e7084c4a481aeeba7bad58a5889b4973b8003e85de","target":"record","created_at":"2026-07-05T09:47:14Z","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":"02aad3f0010cb8006bbf24dd21f6d3992b183da75c3df562533b29530f639c83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T17:50:53Z","title_canon_sha256":"42286d99452ecfcca0751b3e98f4836e3fa9ebb18fb007caeed5f44bab70d110"},"schema_version":"1.0","source":{"id":"2412.07704","kind":"arxiv","version":1}},"canonical_sha256":"f3f558d417a80a91bbbcd47d11e505458c5e9ce2cace9e7320b403c95aafc26f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3f558d417a80a91bbbcd47d11e505458c5e9ce2cace9e7320b403c95aafc26f","first_computed_at":"2026-07-05T09:47:14.221886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:14.221886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/PteSTIf2kmFCLwMETQmHNi8F+NXo4zykTfkBGomga9H0cf/GeWAW+L6a+Z5vhMHmqAiaG+NbAqnmhDsrf15Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:14.222369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d293321a08771830a0ed7e7084c4a481aeeba7bad58a5889b4973b8003e85de","sha256:61fdea22ff413e1c1a65be43dc8fe068b6eb3e1a7e93b0f268c191de4322cb25"],"state_sha256":"18a72b9803d2de52c1703db6c4fc0e1f588c53c5a6e82a405d0b1dd77d208348"}