{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E57ACXQDLBHIVYIQQICTQXWATK","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":"ef7f3a7750bd3bd65cf85179481e5d34ff4b68187bc5784a86aa6f11f988028d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-02T21:00:17Z","title_canon_sha256":"f822a03b49fdbed8727150f9a28840c9cafda1067922f6a45de8c4acb6ad114f"},"schema_version":"1.0","source":{"id":"2505.01583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01583","created_at":"2026-07-05T10:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01583v1","created_at":"2026-07-05T10:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01583","created_at":"2026-07-05T10:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"E57ACXQDLBHI","created_at":"2026-07-05T10:58:00Z"},{"alias_kind":"pith_short_16","alias_value":"E57ACXQDLBHIVYIQ","created_at":"2026-07-05T10:58:00Z"},{"alias_kind":"pith_short_8","alias_value":"E57ACXQD","created_at":"2026-07-05T10:58:00Z"}],"graph_snapshots":[{"event_id":"sha256:a368bb61468bc9a7113eb97666efa2ed1db3b27338e1fb5320c059bffdbf9f46","target":"graph","created_at":"2026-07-05T10:58:00Z","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/2505.01583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as unsegmented streams, which obscures fine-grained event boundaries and limits the modeling of causal dependencies. We propose TEMPURA (Temporal Event Masked Prediction and Understanding for Reasoning in Action), a two-stage training framework that enhances video temporal understanding. TEMPURA first applies masked event prediction reasoning to reconstruct mis","authors_text":"Cheng-Yen Yang, Hou-I Liu, Hsiang-Wei Huang, Huapeng Zhou, Huayu Wang, Jen-Hao Cheng, Jenq-Neng Hwang, Kuang-Ming Chen, Qin Cai, Vibhav Vineet, Vivian Wang, Wenhao Chai, Yi-Hao Peng, Yi-Ling Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-02T21:00:17Z","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01583","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":"sha256:20bb89f8d369c1d87bb71db236b824fbee8880befb225f7b4997c7c5f13316f2","target":"record","created_at":"2026-07-05T10:58:00Z","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":"ef7f3a7750bd3bd65cf85179481e5d34ff4b68187bc5784a86aa6f11f988028d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-02T21:00:17Z","title_canon_sha256":"f822a03b49fdbed8727150f9a28840c9cafda1067922f6a45de8c4acb6ad114f"},"schema_version":"1.0","source":{"id":"2505.01583","kind":"arxiv","version":1}},"canonical_sha256":"277e015e03584e8ae1108205385ec09ab9489c77a60de0d522a0590472c90527","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"277e015e03584e8ae1108205385ec09ab9489c77a60de0d522a0590472c90527","first_computed_at":"2026-07-05T10:58:00.475059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:00.475059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HEg+0k26PluuyiJQd+N4+1ltRqDj0mJYuT41EOqTlG68m6k7NF4M5sg2sBvTo2EyC4Zw+O+Nd9ZUt2edUkl+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:00.475855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20bb89f8d369c1d87bb71db236b824fbee8880befb225f7b4997c7c5f13316f2","sha256:a368bb61468bc9a7113eb97666efa2ed1db3b27338e1fb5320c059bffdbf9f46"],"state_sha256":"c367a2c8ca0b6147750fc1a9afc2f35fd65acf63e40c5c41310d5bee1032d53b"}