{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GDXKQ4C5XCLFI3NME7DOZD5SOU","short_pith_number":"pith:GDXKQ4C5","canonical_record":{"source":{"id":"2506.11155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T15:11:37Z","cross_cats_sorted":[],"title_canon_sha256":"b0e73c2ea7c684d55237cb25dc98e88d5c8a56a827d404943cef22056c6be8f8","abstract_canon_sha256":"acf70b079c49ff598c1bb09bc89a33a80d5fbda0e11ae3035e5a580579d6e641"},"schema_version":"1.0"},"canonical_sha256":"30eea8705db896546dac27c6ec8fb2750e7e8420d634ee5cf887afed7de8cb95","source":{"kind":"arxiv","id":"2506.11155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11155","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11155v1","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11155","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"GDXKQ4C5XCLF","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_16","alias_value":"GDXKQ4C5XCLFI3NM","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_8","alias_value":"GDXKQ4C5","created_at":"2026-07-05T11:21:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GDXKQ4C5XCLFI3NME7DOZD5SOU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T15:11:37Z","cross_cats_sorted":[],"title_canon_sha256":"b0e73c2ea7c684d55237cb25dc98e88d5c8a56a827d404943cef22056c6be8f8","abstract_canon_sha256":"acf70b079c49ff598c1bb09bc89a33a80d5fbda0e11ae3035e5a580579d6e641"},"schema_version":"1.0"},"canonical_sha256":"30eea8705db896546dac27c6ec8fb2750e7e8420d634ee5cf887afed7de8cb95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:00.412477Z","signature_b64":"mYCNftpAIDZhSfBQyMzMCuSt0xfoOymVYIE1i7s31l0sBsNO+075cxLOc3MVA9iv1hBShd7QCwiVBqQIL3EPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30eea8705db896546dac27c6ec8fb2750e7e8420d634ee5cf887afed7de8cb95","last_reissued_at":"2026-07-05T11:21:00.412010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:00.412010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11155","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiM+VclpG/ag2X7f3nC+QX8Hry3QKmK+mgDrbRftDgJZQaFCETJ/nPahQRZTxGIfZM4J/HrOWYxQLdgiRYJKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:30:10.804094Z"},"content_sha256":"a1fc131d3f49c8451bace81e367462060f8bc5bc372355aac75e424f8dcc8d58","schema_version":"1.0","event_id":"sha256:a1fc131d3f49c8451bace81e367462060f8bc5bc372355aac75e424f8dcc8d58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GDXKQ4C5XCLFI3NME7DOZD5SOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Sun, Deyi Xiong, Fanheng Kong, Fuzheng Zhang, Hongzhi Zhang, Jingyuan Zhang, Linhao Yu, V. W., Xinguang Ji, Yahui Liu","submitted_at":"2025-06-11T15:11:37Z","abstract_excerpt":"Video captioning can be used to assess the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, existing benchmarks and evaluation protocols suffer from crucial issues, such as inadequate or homogeneous creation of key points, exorbitant cost of data creation, and limited evaluation scopes. To address these issues, we propose an automatic framework, named AutoCaption, which leverages Monte Carlo Tree Search (MCTS) to construct numerous and diverse descriptive sentences (\\textit{i.e.}, key points) that thoroughly represent video content in an iterative way. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11155","kind":"arxiv","version":1},"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/2506.11155/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":"2026-07-05T11:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGhVeV4ETelM9/lmKZydapbmW8H+t4uaVs4qeRW14OmYAjSAu2x8RgYRszKgLGLD330W7kngyfM0Q4jCLTXCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:30:10.804591Z"},"content_sha256":"2ba6cfe8bdaa3af19fb51c0b9b15ea413b7c436e61f8805eccbd8477059f391c","schema_version":"1.0","event_id":"sha256:2ba6cfe8bdaa3af19fb51c0b9b15ea413b7c436e61f8805eccbd8477059f391c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU/bundle.json","state_url":"https://pith.science/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU/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":"2026-08-09T06:30:10Z","links":{"resolver":"https://pith.science/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU","bundle":"https://pith.science/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU/bundle.json","state":"https://pith.science/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDXKQ4C5XCLFI3NME7DOZD5SOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GDXKQ4C5XCLFI3NME7DOZD5SOU","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":"acf70b079c49ff598c1bb09bc89a33a80d5fbda0e11ae3035e5a580579d6e641","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T15:11:37Z","title_canon_sha256":"b0e73c2ea7c684d55237cb25dc98e88d5c8a56a827d404943cef22056c6be8f8"},"schema_version":"1.0","source":{"id":"2506.11155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11155","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11155v1","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11155","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"GDXKQ4C5XCLF","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_16","alias_value":"GDXKQ4C5XCLFI3NM","created_at":"2026-07-05T11:21:00Z"},{"alias_kind":"pith_short_8","alias_value":"GDXKQ4C5","created_at":"2026-07-05T11:21:00Z"}],"graph_snapshots":[{"event_id":"sha256:2ba6cfe8bdaa3af19fb51c0b9b15ea413b7c436e61f8805eccbd8477059f391c","target":"graph","created_at":"2026-07-05T11:21:00Z","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/2506.11155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning can be used to assess the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, existing benchmarks and evaluation protocols suffer from crucial issues, such as inadequate or homogeneous creation of key points, exorbitant cost of data creation, and limited evaluation scopes. To address these issues, we propose an automatic framework, named AutoCaption, which leverages Monte Carlo Tree Search (MCTS) to construct numerous and diverse descriptive sentences (\\textit{i.e.}, key points) that thoroughly represent video content in an iterative way. Thi","authors_text":"Chenxi Sun, Deyi Xiong, Fanheng Kong, Fuzheng Zhang, Hongzhi Zhang, Jingyuan Zhang, Linhao Yu, V. W., Xinguang Ji, Yahui Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T15:11:37Z","title":"Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11155","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:a1fc131d3f49c8451bace81e367462060f8bc5bc372355aac75e424f8dcc8d58","target":"record","created_at":"2026-07-05T11:21:00Z","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":"acf70b079c49ff598c1bb09bc89a33a80d5fbda0e11ae3035e5a580579d6e641","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T15:11:37Z","title_canon_sha256":"b0e73c2ea7c684d55237cb25dc98e88d5c8a56a827d404943cef22056c6be8f8"},"schema_version":"1.0","source":{"id":"2506.11155","kind":"arxiv","version":1}},"canonical_sha256":"30eea8705db896546dac27c6ec8fb2750e7e8420d634ee5cf887afed7de8cb95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30eea8705db896546dac27c6ec8fb2750e7e8420d634ee5cf887afed7de8cb95","first_computed_at":"2026-07-05T11:21:00.412010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:00.412010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mYCNftpAIDZhSfBQyMzMCuSt0xfoOymVYIE1i7s31l0sBsNO+075cxLOc3MVA9iv1hBShd7QCwiVBqQIL3EPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:00.412477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1fc131d3f49c8451bace81e367462060f8bc5bc372355aac75e424f8dcc8d58","sha256:2ba6cfe8bdaa3af19fb51c0b9b15ea413b7c436e61f8805eccbd8477059f391c"],"state_sha256":"7ff11e939a4ece1a24bc68ef0017b1bb2f21ceadf477808a0a4700322847d88d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8q2Tt0Al+tJFeky4YHxs5W7D7b9Ms1UDgcs+154Cd+w6xYlgu7qqhlBcz8P/WMV9xLNbVF864nppMAdmsX5ADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:30:10.809181Z","bundle_sha256":"a8725a2562660b4d30e4f98d01ca34af29231f6c2288ef468328c5d5b28f4e83"}}