{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CDVJHVQWE7T64Z75DSUSAR4NUP","short_pith_number":"pith:CDVJHVQW","canonical_record":{"source":{"id":"2505.20124","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:24:06Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6f3e6d5c6eafd5f8a5ae7fab40c6b98504699f7f9f49a37c04e148e59143385f","abstract_canon_sha256":"9599e30e960644b74d348c58aab13bc5d632f23421d7eb9158218190a53ec271"},"schema_version":"1.0"},"canonical_sha256":"10ea93d61627e7ee67fd1ca920478da3d6503b2ebf6fae03cdd75a4f2bb91b7e","source":{"kind":"arxiv","id":"2505.20124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20124","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20124v2","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20124","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"CDVJHVQWE7T6","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"CDVJHVQWE7T64Z75","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"CDVJHVQW","created_at":"2026-07-05T11:17:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CDVJHVQWE7T64Z75DSUSAR4NUP","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20124","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:24:06Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6f3e6d5c6eafd5f8a5ae7fab40c6b98504699f7f9f49a37c04e148e59143385f","abstract_canon_sha256":"9599e30e960644b74d348c58aab13bc5d632f23421d7eb9158218190a53ec271"},"schema_version":"1.0"},"canonical_sha256":"10ea93d61627e7ee67fd1ca920478da3d6503b2ebf6fae03cdd75a4f2bb91b7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:45.888757Z","signature_b64":"YwVygb0py7SdT6U/J1VGi0XtnjRB0dxSwouQE4LWIzmRU/dHJiB7oFMRmEKsf+8AwVJvbxKCSr80YAeTsPRyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10ea93d61627e7ee67fd1ca920478da3d6503b2ebf6fae03cdd75a4f2bb91b7e","last_reissued_at":"2026-07-05T11:17:45.888138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:45.888138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20124","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lk2l08UxoEvUSU/kJTq/6VVWTOGEv7et/ntxZSzR4GGFH1Ba4rB+mNqLmJSh2flPFXt1f1RqfggO0PgMkaQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:40:31.660993Z"},"content_sha256":"c18d11b024e4b91b41c52b40e375992018f9a4da74867a962e2cc403c4bcc78e","schema_version":"1.0","event_id":"sha256:c18d11b024e4b91b41c52b40e375992018f9a4da74867a962e2cc403c4bcc78e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CDVJHVQWE7T64Z75DSUSAR4NUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Daling Wang, Fanheng Kong, Fuzheng Zhang, Hongzhi Zhang, Jingyuan Zhang, Linhao Yu, Shi Feng, Victoria W., Xingguang Ji, Yu Tian","submitted_at":"2025-05-26T15:24:06Z","abstract_excerpt":"Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing benchmarks for video understanding often treat these properties separately or narrowly focus on specific aspects, overlooking the holistic nature of video content. To address this, we introduce TUNA, a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos, with two complementary tasks: captioning and QA. Our TUNA features diverse video scenarios and dynamics, assisted by interpretable and ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20124","kind":"arxiv","version":2},"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/2505.20124/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U7hiY00Tb6da1a9y03F5QgrMHX5NL6VO+2Y9cEBnYNgkvS488e2pfSIQPU3bvpiUd3InaQdA0KuNCkdC610IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:40:31.661561Z"},"content_sha256":"2473e909eaf6b86700aff2621267d5a6096cb0b46553bb517e81f7036794ca2a","schema_version":"1.0","event_id":"sha256:2473e909eaf6b86700aff2621267d5a6096cb0b46553bb517e81f7036794ca2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CDVJHVQWE7T64Z75DSUSAR4NUP/bundle.json","state_url":"https://pith.science/pith/CDVJHVQWE7T64Z75DSUSAR4NUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CDVJHVQWE7T64Z75DSUSAR4NUP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:40:31Z","links":{"resolver":"https://pith.science/pith/CDVJHVQWE7T64Z75DSUSAR4NUP","bundle":"https://pith.science/pith/CDVJHVQWE7T64Z75DSUSAR4NUP/bundle.json","state":"https://pith.science/pith/CDVJHVQWE7T64Z75DSUSAR4NUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CDVJHVQWE7T64Z75DSUSAR4NUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CDVJHVQWE7T64Z75DSUSAR4NUP","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":"9599e30e960644b74d348c58aab13bc5d632f23421d7eb9158218190a53ec271","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:24:06Z","title_canon_sha256":"6f3e6d5c6eafd5f8a5ae7fab40c6b98504699f7f9f49a37c04e148e59143385f"},"schema_version":"1.0","source":{"id":"2505.20124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20124","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20124v2","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20124","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"CDVJHVQWE7T6","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"CDVJHVQWE7T64Z75","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"CDVJHVQW","created_at":"2026-07-05T11:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:2473e909eaf6b86700aff2621267d5a6096cb0b46553bb517e81f7036794ca2a","target":"graph","created_at":"2026-07-05T11:17:45Z","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/2505.20124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing benchmarks for video understanding often treat these properties separately or narrowly focus on specific aspects, overlooking the holistic nature of video content. To address this, we introduce TUNA, a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos, with two complementary tasks: captioning and QA. Our TUNA features diverse video scenarios and dynamics, assisted by interpretable and ro","authors_text":"Daling Wang, Fanheng Kong, Fuzheng Zhang, Hongzhi Zhang, Jingyuan Zhang, Linhao Yu, Shi Feng, Victoria W., Xingguang Ji, Yu Tian","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:24:06Z","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20124","kind":"arxiv","version":2},"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:c18d11b024e4b91b41c52b40e375992018f9a4da74867a962e2cc403c4bcc78e","target":"record","created_at":"2026-07-05T11:17:45Z","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":"9599e30e960644b74d348c58aab13bc5d632f23421d7eb9158218190a53ec271","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T15:24:06Z","title_canon_sha256":"6f3e6d5c6eafd5f8a5ae7fab40c6b98504699f7f9f49a37c04e148e59143385f"},"schema_version":"1.0","source":{"id":"2505.20124","kind":"arxiv","version":2}},"canonical_sha256":"10ea93d61627e7ee67fd1ca920478da3d6503b2ebf6fae03cdd75a4f2bb91b7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10ea93d61627e7ee67fd1ca920478da3d6503b2ebf6fae03cdd75a4f2bb91b7e","first_computed_at":"2026-07-05T11:17:45.888138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:45.888138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YwVygb0py7SdT6U/J1VGi0XtnjRB0dxSwouQE4LWIzmRU/dHJiB7oFMRmEKsf+8AwVJvbxKCSr80YAeTsPRyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:45.888757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c18d11b024e4b91b41c52b40e375992018f9a4da74867a962e2cc403c4bcc78e","sha256:2473e909eaf6b86700aff2621267d5a6096cb0b46553bb517e81f7036794ca2a"],"state_sha256":"cf13aed448e36d7f790d4b35f0a1f2b1adaab7ef0d93ef3b5c4b7f5889e6cd35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwSuduo+mrpoOuMl9BmvLQeaJ6iBKGI02XEUC7sC8Iz/QqIHZuIn6BDBy5vHe1XXnOYCOU18tJS96ux9YmjqBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:40:31.666742Z","bundle_sha256":"bbf27cf1716ffc89eb7394ebc12a03dcd1850b6d0c71e8a9367a8a9e23930b8a"}}