{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LTXSYXSGEN3V66M352E2ECHDS6","short_pith_number":"pith:LTXSYXSG","canonical_record":{"source":{"id":"2410.19702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T17:19:55Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c2df90cb5d7e916075b61ec13d7fb53b88d7e9c24cf029d7023b9d5744f17a7a","abstract_canon_sha256":"fecfb611ff3a54d914707e1d6ee2317d69d22bb70b6d21f96fe945e399cd73e1"},"schema_version":"1.0"},"canonical_sha256":"5cef2c5e4623775f799bee89a208e397b63b372c05863d1973e8a9ce42cc3623","source":{"kind":"arxiv","id":"2410.19702","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19702","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19702v2","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19702","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"LTXSYXSGEN3V","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"LTXSYXSGEN3V66M3","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"LTXSYXSG","created_at":"2026-07-05T10:13:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LTXSYXSGEN3V66M352E2ECHDS6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T17:19:55Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c2df90cb5d7e916075b61ec13d7fb53b88d7e9c24cf029d7023b9d5744f17a7a","abstract_canon_sha256":"fecfb611ff3a54d914707e1d6ee2317d69d22bb70b6d21f96fe945e399cd73e1"},"schema_version":"1.0"},"canonical_sha256":"5cef2c5e4623775f799bee89a208e397b63b372c05863d1973e8a9ce42cc3623","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:04.935032Z","signature_b64":"uJtTzef6GF2D1ijTxf5nkfeGRJbhfbAZ/jMFI05kd9Ef0KwUpVcIekLWkFnHB32FnLyTi/J65XzUxPPN1nb8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cef2c5e4623775f799bee89a208e397b63b372c05863d1973e8a9ce42cc3623","last_reissued_at":"2026-07-05T10:13:04.934572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:04.934572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19702","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":"2026-07-05T10:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gEK5wYmfbFMnkFWHR0+2INNUAl9AiNOiDh+8Hn7YJIqg9wisSkaFvK6oNI9rcC92O59SW74EE4bddn8tLP1PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:11:12.576160Z"},"content_sha256":"d8267f42aec55ac0be771e0546be17fefc51596a9557e2eca724ca26be990a00","schema_version":"1.0","event_id":"sha256:d8267f42aec55ac0be771e0546be17fefc51596a9557e2eca724ca26be990a00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LTXSYXSGEN3V66M352E2ECHDS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chenting Wang, Kunchang Li, Limin Wang, Songze Li, Tianxiang Jiang, Xiangyu Zeng, Xinhao Li, Yali Wang, Yansong Shi, Yi Wang, Yu Qiao, Zhengrong Yue, Ziang Yan","submitted_at":"2024-10-25T17:19:55Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a high-quality video dataset for grounded tuning of MLLMs, and a carefully-designed instruction tuning task to explicitly incorporate the grounding supervision in the traditional QA format. Specifically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19702","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/2410.19702/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":"2026-07-05T10:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Swh3xiBl9QOyoB03z1qs/WlzxuWO++PznbSG57WROABC+j9s3yCtN9DkVD+7vqgIBh27yt6yfAREPeCfwlSuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:11:12.576699Z"},"content_sha256":"e575d3ba98cf313112917624ee1e9b6f059b71739d8dba94c4feeaf96ae93fd1","schema_version":"1.0","event_id":"sha256:e575d3ba98cf313112917624ee1e9b6f059b71739d8dba94c4feeaf96ae93fd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTXSYXSGEN3V66M352E2ECHDS6/bundle.json","state_url":"https://pith.science/pith/LTXSYXSGEN3V66M352E2ECHDS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTXSYXSGEN3V66M352E2ECHDS6/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":"2026-08-04T09:11:12Z","links":{"resolver":"https://pith.science/pith/LTXSYXSGEN3V66M352E2ECHDS6","bundle":"https://pith.science/pith/LTXSYXSGEN3V66M352E2ECHDS6/bundle.json","state":"https://pith.science/pith/LTXSYXSGEN3V66M352E2ECHDS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTXSYXSGEN3V66M352E2ECHDS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LTXSYXSGEN3V66M352E2ECHDS6","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":"fecfb611ff3a54d914707e1d6ee2317d69d22bb70b6d21f96fe945e399cd73e1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T17:19:55Z","title_canon_sha256":"c2df90cb5d7e916075b61ec13d7fb53b88d7e9c24cf029d7023b9d5744f17a7a"},"schema_version":"1.0","source":{"id":"2410.19702","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19702","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19702v2","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19702","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"LTXSYXSGEN3V","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"LTXSYXSGEN3V66M3","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"LTXSYXSG","created_at":"2026-07-05T10:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:e575d3ba98cf313112917624ee1e9b6f059b71739d8dba94c4feeaf96ae93fd1","target":"graph","created_at":"2026-07-05T10:13:04Z","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/2410.19702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a high-quality video dataset for grounded tuning of MLLMs, and a carefully-designed instruction tuning task to explicitly incorporate the grounding supervision in the traditional QA format. Specifically","authors_text":"Chenting Wang, Kunchang Li, Limin Wang, Songze Li, Tianxiang Jiang, Xiangyu Zeng, Xinhao Li, Yali Wang, Yansong Shi, Yi Wang, Yu Qiao, Zhengrong Yue, Ziang Yan","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T17:19:55Z","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19702","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:d8267f42aec55ac0be771e0546be17fefc51596a9557e2eca724ca26be990a00","target":"record","created_at":"2026-07-05T10:13:04Z","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":"fecfb611ff3a54d914707e1d6ee2317d69d22bb70b6d21f96fe945e399cd73e1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T17:19:55Z","title_canon_sha256":"c2df90cb5d7e916075b61ec13d7fb53b88d7e9c24cf029d7023b9d5744f17a7a"},"schema_version":"1.0","source":{"id":"2410.19702","kind":"arxiv","version":2}},"canonical_sha256":"5cef2c5e4623775f799bee89a208e397b63b372c05863d1973e8a9ce42cc3623","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cef2c5e4623775f799bee89a208e397b63b372c05863d1973e8a9ce42cc3623","first_computed_at":"2026-07-05T10:13:04.934572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:04.934572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uJtTzef6GF2D1ijTxf5nkfeGRJbhfbAZ/jMFI05kd9Ef0KwUpVcIekLWkFnHB32FnLyTi/J65XzUxPPN1nb8DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:04.935032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19702","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8267f42aec55ac0be771e0546be17fefc51596a9557e2eca724ca26be990a00","sha256:e575d3ba98cf313112917624ee1e9b6f059b71739d8dba94c4feeaf96ae93fd1"],"state_sha256":"f57b1d60355df460836f6f35d67cef8086457c86db6af9de4f82819a275a333b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TfZcLS3OJgSeCFb/IM+S0TecjMLAmOFbkdRfM7kjqpB7BFq2VdUTwYb5qmHTVfjFLphjCN2hkKmk5BNvb0p7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:11:12.580683Z","bundle_sha256":"e15d3749d43c8ddb44ab37dd6574bc8fa3b84c4184ca5e20f68e53175fb7bc06"}}