{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UQSPJI3FLHHWPUSHRLKZMEQOXU","short_pith_number":"pith:UQSPJI3F","canonical_record":{"source":{"id":"2403.16558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T09:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"b15edd7179a49efb02d0666dbf6b42a53100f8fcbf5acece213e585286effa9e","abstract_canon_sha256":"af1d64da1f0494d7ba0b9b40562a52d32c76e5738a08f3d822eaf9fdef45436b"},"schema_version":"1.0"},"canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","source":{"kind":"arxiv","id":"2403.16558","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16558","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16558v2","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16558","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"UQSPJI3FLHHW","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"UQSPJI3FLHHWPUSH","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"UQSPJI3F","created_at":"2026-07-05T08:02:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UQSPJI3FLHHWPUSHRLKZMEQOXU","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16558","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T09:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"b15edd7179a49efb02d0666dbf6b42a53100f8fcbf5acece213e585286effa9e","abstract_canon_sha256":"af1d64da1f0494d7ba0b9b40562a52d32c76e5738a08f3d822eaf9fdef45436b"},"schema_version":"1.0"},"canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:06.389917Z","signature_b64":"LRrMXuf+QCHu1bYaT90TGwCN5NrblV0FqdkqhA1i479s24YTkHMFySf+z+U2uhdip+vNdKZdUhZKD4TrKiumAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","last_reissued_at":"2026-07-05T08:02:06.389484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:06.389484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16558","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":"2026-07-05T08:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXLqhmCeBASmgdQthr2Opt6tAByDRvd4yiDLjJkpiN1IVptDh7ENcHAG4Ff/07OROpjmRyjTZUVDTCbGQ1TxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:40.932507Z"},"content_sha256":"5be2ead110362b789f1a37e39e569f203f704a4237d9c3ef62c81291264b9dbe","schema_version":"1.0","event_id":"sha256:5be2ead110362b789f1a37e39e569f203f704a4237d9c3ef62c81291264b9dbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UQSPJI3FLHHWPUSHRLKZMEQOXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Elysium: Exploring Object-level Perception in Videos via MLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Huang, Han Wang, Yanjie Wang, YongJie Ye, Yuxiang Nie","submitted_at":"2024-03-25T09:17:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16558","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/2403.16558/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":"2026-07-05T08:02:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMpK7tDws/vZIbNCU0BNQN6nqrM6lF37m8VJ+Z1UmsbfObSAH8jfIeS9AYh5+WWAMurfKbVTs4bah0sE5P4VAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:40.933021Z"},"content_sha256":"134563e771e5599485d33e844243c3a02f9f665cd3dbd267424c023c92e5f0fc","schema_version":"1.0","event_id":"sha256:134563e771e5599485d33e844243c3a02f9f665cd3dbd267424c023c92e5f0fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/bundle.json","state_url":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/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":"2026-08-05T17:18:40Z","links":{"resolver":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU","bundle":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/bundle.json","state":"https://pith.science/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQSPJI3FLHHWPUSHRLKZMEQOXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UQSPJI3FLHHWPUSHRLKZMEQOXU","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":"af1d64da1f0494d7ba0b9b40562a52d32c76e5738a08f3d822eaf9fdef45436b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T09:17:15Z","title_canon_sha256":"b15edd7179a49efb02d0666dbf6b42a53100f8fcbf5acece213e585286effa9e"},"schema_version":"1.0","source":{"id":"2403.16558","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16558","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16558v2","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16558","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"pith_short_12","alias_value":"UQSPJI3FLHHW","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"pith_short_16","alias_value":"UQSPJI3FLHHWPUSH","created_at":"2026-07-05T08:02:06Z"},{"alias_kind":"pith_short_8","alias_value":"UQSPJI3F","created_at":"2026-07-05T08:02:06Z"}],"graph_snapshots":[{"event_id":"sha256:134563e771e5599485d33e844243c3a02f9f665cd3dbd267424c023c92e5f0fc","target":"graph","created_at":"2026-07-05T08:02:06Z","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/2403.16558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied. This lack of exploration is primarily due to two key challenges. Firstly, extensive pretraining on large-scale video datasets is required to equip MLLMs with the capability to perceive objects across multiple frames and understand inter-frame relationships. Secondly, processing a large number of frames within the context window of Large Language Models (LLMs) can impose a significant computati","authors_text":"Can Huang, Han Wang, Yanjie Wang, YongJie Ye, Yuxiang Nie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T09:17:15Z","title":"Elysium: Exploring Object-level Perception in Videos via MLLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16558","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":"sha256:5be2ead110362b789f1a37e39e569f203f704a4237d9c3ef62c81291264b9dbe","target":"record","created_at":"2026-07-05T08:02:06Z","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":"af1d64da1f0494d7ba0b9b40562a52d32c76e5738a08f3d822eaf9fdef45436b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T09:17:15Z","title_canon_sha256":"b15edd7179a49efb02d0666dbf6b42a53100f8fcbf5acece213e585286effa9e"},"schema_version":"1.0","source":{"id":"2403.16558","kind":"arxiv","version":2}},"canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a424f4a36559cf67d2478ad596120ebd3fddb6c2d3f1b3dab805d995d202e91a","first_computed_at":"2026-07-05T08:02:06.389484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:06.389484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRrMXuf+QCHu1bYaT90TGwCN5NrblV0FqdkqhA1i479s24YTkHMFySf+z+U2uhdip+vNdKZdUhZKD4TrKiumAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:06.389917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16558","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5be2ead110362b789f1a37e39e569f203f704a4237d9c3ef62c81291264b9dbe","sha256:134563e771e5599485d33e844243c3a02f9f665cd3dbd267424c023c92e5f0fc"],"state_sha256":"fd6b7f8cee086729cc359a48742c7aacf5699c73642cf79a75dd7741333d644a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yLZZxfv4jr/7nj7xfWVIOr+sE1le0pDY3T964nMARqBSI9wX0ujjzGaFSvt2DvSjfcW/JO3sR/IvDjMZwJkkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:18:40.936912Z","bundle_sha256":"9e8d82ddd2e01bc1048339d6b293863fb52e79060a61855c155d044fc8cc45b9"}}