{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NA3HUZEUKEBRQNIPV25WRRIDF6","short_pith_number":"pith:NA3HUZEU","canonical_record":{"source":{"id":"2511.14143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T05:03:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37b81a3621c8972569e92910a9139b0959f77029c3e013043724c2345c1982c3","abstract_canon_sha256":"f0f121fc6b9ae3ecf10d9202c61bde9e1c0cfaac0c5df3b34442b40499dd030b"},"schema_version":"1.0"},"canonical_sha256":"68367a6494510318350faebb68c5032fb160650a9081058de7fc3086c2246bb3","source":{"kind":"arxiv","id":"2511.14143","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.14143","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2511.14143v2","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14143","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"NA3HUZEUKEBR","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"NA3HUZEUKEBRQNIP","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"NA3HUZEU","created_at":"2026-06-09T02:07:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NA3HUZEUKEBRQNIPV25WRRIDF6","target":"record","payload":{"canonical_record":{"source":{"id":"2511.14143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T05:03:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37b81a3621c8972569e92910a9139b0959f77029c3e013043724c2345c1982c3","abstract_canon_sha256":"f0f121fc6b9ae3ecf10d9202c61bde9e1c0cfaac0c5df3b34442b40499dd030b"},"schema_version":"1.0"},"canonical_sha256":"68367a6494510318350faebb68c5032fb160650a9081058de7fc3086c2246bb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:13.276770Z","signature_b64":"5Yug7afnO5v9kHwROVhoqMdBkl3vuV3yg1l8RhIkMvA78TpCeoVb8UYTdx9d/4NHbq2iaDdGQBL4qaCOcP/xBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68367a6494510318350faebb68c5032fb160650a9081058de7fc3086c2246bb3","last_reissued_at":"2026-06-09T02:07:13.275873Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:13.275873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.14143","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":"2026-06-09T02:07:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzEvO95X00IzSMS86yOyFMQmowdF2S3AywedDYsBsMRghnBFNA889Uo1wZVizE4Z+8AOOE/fx3ES8+fglJxECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:12:08.191587Z"},"content_sha256":"739f6683273b3f0d6e29991d48ed5ef67072783a0153170815ed8fc46868c372","schema_version":"1.0","event_id":"sha256:739f6683273b3f0d6e29991d48ed5ef67072783a0153170815ed8fc46868c372"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NA3HUZEUKEBRQNIPV25WRRIDF6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"An Yu, Felix X.-F. Ye, Jian Li, Ming-Ching Chang, Weiheng Lu, Yunhang Shen, Zhenfei Zhang","submitted_at":"2025-11-18T05:03:17Z","abstract_excerpt":"Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both traditional techniques and Multimodal Large Language Models (MLLM), most existing methods still rely on coarse temporal understanding and a single visual modality, limiting performance on complex videos. To address this, we introduce \\textit{S}hot-aware \\textit{M}ultimodal \\textit{A}udio-enhanced \\textit{R}etrieval of \\textit{T}emporal \\textit{S}egments (SMART), an ML"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14143","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/2511.14143/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":"2026-06-09T02:07:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0oYlWFjlEX40PWflukyjPUo8ufnAmF2+yFI21+dL0gwGJE/uS2HnN6e50w1E/RbKKgEeiArAXQVoGJfMHHYOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T07:12:08.192404Z"},"content_sha256":"f58b43f64cdbce181c7b85a08a6831503688039926abd46dab3044bdf2f20197","schema_version":"1.0","event_id":"sha256:f58b43f64cdbce181c7b85a08a6831503688039926abd46dab3044bdf2f20197"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NA3HUZEUKEBRQNIPV25WRRIDF6/bundle.json","state_url":"https://pith.science/pith/NA3HUZEUKEBRQNIPV25WRRIDF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NA3HUZEUKEBRQNIPV25WRRIDF6/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":"2026-06-10T07:12:08Z","links":{"resolver":"https://pith.science/pith/NA3HUZEUKEBRQNIPV25WRRIDF6","bundle":"https://pith.science/pith/NA3HUZEUKEBRQNIPV25WRRIDF6/bundle.json","state":"https://pith.science/pith/NA3HUZEUKEBRQNIPV25WRRIDF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NA3HUZEUKEBRQNIPV25WRRIDF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NA3HUZEUKEBRQNIPV25WRRIDF6","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":"f0f121fc6b9ae3ecf10d9202c61bde9e1c0cfaac0c5df3b34442b40499dd030b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T05:03:17Z","title_canon_sha256":"37b81a3621c8972569e92910a9139b0959f77029c3e013043724c2345c1982c3"},"schema_version":"1.0","source":{"id":"2511.14143","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.14143","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"arxiv_version","alias_value":"2511.14143v2","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.14143","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"pith_short_12","alias_value":"NA3HUZEUKEBR","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"pith_short_16","alias_value":"NA3HUZEUKEBRQNIP","created_at":"2026-06-09T02:07:13Z"},{"alias_kind":"pith_short_8","alias_value":"NA3HUZEU","created_at":"2026-06-09T02:07:13Z"}],"graph_snapshots":[{"event_id":"sha256:f58b43f64cdbce181c7b85a08a6831503688039926abd46dab3044bdf2f20197","target":"graph","created_at":"2026-06-09T02:07:13Z","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/2511.14143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both traditional techniques and Multimodal Large Language Models (MLLM), most existing methods still rely on coarse temporal understanding and a single visual modality, limiting performance on complex videos. To address this, we introduce \\textit{S}hot-aware \\textit{M}ultimodal \\textit{A}udio-enhanced \\textit{R}etrieval of \\textit{T}emporal \\textit{S}egments (SMART), an ML","authors_text":"An Yu, Felix X.-F. Ye, Jian Li, Ming-Ching Chang, Weiheng Lu, Yunhang Shen, Zhenfei Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T05:03:17Z","title":"SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.14143","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":"sha256:739f6683273b3f0d6e29991d48ed5ef67072783a0153170815ed8fc46868c372","target":"record","created_at":"2026-06-09T02:07:13Z","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":"f0f121fc6b9ae3ecf10d9202c61bde9e1c0cfaac0c5df3b34442b40499dd030b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-18T05:03:17Z","title_canon_sha256":"37b81a3621c8972569e92910a9139b0959f77029c3e013043724c2345c1982c3"},"schema_version":"1.0","source":{"id":"2511.14143","kind":"arxiv","version":2}},"canonical_sha256":"68367a6494510318350faebb68c5032fb160650a9081058de7fc3086c2246bb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68367a6494510318350faebb68c5032fb160650a9081058de7fc3086c2246bb3","first_computed_at":"2026-06-09T02:07:13.275873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:13.275873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Yug7afnO5v9kHwROVhoqMdBkl3vuV3yg1l8RhIkMvA78TpCeoVb8UYTdx9d/4NHbq2iaDdGQBL4qaCOcP/xBQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:13.276770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.14143","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:739f6683273b3f0d6e29991d48ed5ef67072783a0153170815ed8fc46868c372","sha256:f58b43f64cdbce181c7b85a08a6831503688039926abd46dab3044bdf2f20197"],"state_sha256":"b055183cb691a73e3aebbc86a1dbb088d3663761f23738f7f3a60e64a439e8be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VF0jf6N3enYJBKRdXm+n+4ekLfLj1p1VOmaOCzRAg2hsW3bWoDRZVJGqWqWUpv5sV5jpLCXjnLJ0bBLVS/DWCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T07:12:08.196906Z","bundle_sha256":"996a0484f5bed8a8fc8ee6b484291997908ec79f421ab9f88e4b2b472aa88547"}}