{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RLZI2BRXN4EVAHN32FV62FBIDS","short_pith_number":"pith:RLZI2BRX","canonical_record":{"source":{"id":"2507.02946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T15:24:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2411f0489247f042db3f23b4178041cc292e9fa14cb4e035132dfe7be2d8eb6e","abstract_canon_sha256":"cf4b997aa9c3f2bf7c4001c68434b7129c850b7c7cf9d314cc7939dd141cb33f"},"schema_version":"1.0"},"canonical_sha256":"8af28d06376f09501dbbd16bed14281caa416bdecf92cdfdcddf13eb7c7a4983","source":{"kind":"arxiv","id":"2507.02946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02946","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02946v1","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02946","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"RLZI2BRXN4EV","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"RLZI2BRXN4EVAHN3","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"RLZI2BRX","created_at":"2026-07-05T11:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RLZI2BRXN4EVAHN32FV62FBIDS","target":"record","payload":{"canonical_record":{"source":{"id":"2507.02946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T15:24:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2411f0489247f042db3f23b4178041cc292e9fa14cb4e035132dfe7be2d8eb6e","abstract_canon_sha256":"cf4b997aa9c3f2bf7c4001c68434b7129c850b7c7cf9d314cc7939dd141cb33f"},"schema_version":"1.0"},"canonical_sha256":"8af28d06376f09501dbbd16bed14281caa416bdecf92cdfdcddf13eb7c7a4983","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:49.306623Z","signature_b64":"1GvFLJXicWLmlm1JtErxN1Em6D2kMnvG9p1kmwGJoPuCqgorNM9Kl1qvszya5C+qTBJlDVCk+LSH7Y/X+CI0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af28d06376f09501dbbd16bed14281caa416bdecf92cdfdcddf13eb7c7a4983","last_reissued_at":"2026-07-05T11:31:49.306132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:49.306132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.02946","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":"2026-07-05T11:31:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CI6LHcBQo0ugC/UTy6Jz06WxwiqvW5lFIS/4GDZaGQyDwHPvYH5LZG0hia2VlUXM3HA/kneo/OgSFpTVBfnpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:19:49.490116Z"},"content_sha256":"800d7b4bf2b3a8d7de0712255cc12641505cdad10f511afa66b3e95a7cf29f22","schema_version":"1.0","event_id":"sha256:800d7b4bf2b3a8d7de0712255cc12641505cdad10f511afa66b3e95a7cf29f22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RLZI2BRXN4EVAHN32FV62FBIDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenglin Li, fengtao, Qianglong Chen, Yin Zhang","submitted_at":"2025-06-28T15:24:05Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an inefficient perception of temporal intervals. Unlike humans, who can dynamically adjust their temporal focus to locate query-relevant moments, current MLLMs often rely on dense, uniform sampling across the video timeline, leading to high memory consumption and a risk of missing crucial information. To address this challenge, we introduce Temporal Search, a training-free framework that enables MLLMs to explore temporal region"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02946","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/2507.02946/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":"2026-07-05T11:31:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEGke5CpqWIDt0AqNMkgfLvZTUxufiWt5yX5xG1yEqK6pf6yX6Wj9vpoQxJxrNvo2jhZVOs64Qbs29raru+hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:19:49.490500Z"},"content_sha256":"392518cae61e61dab93f74d92ee5a8a0f2fe67ca32f0867aca96971ea0ab038d","schema_version":"1.0","event_id":"sha256:392518cae61e61dab93f74d92ee5a8a0f2fe67ca32f0867aca96971ea0ab038d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLZI2BRXN4EVAHN32FV62FBIDS/bundle.json","state_url":"https://pith.science/pith/RLZI2BRXN4EVAHN32FV62FBIDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLZI2BRXN4EVAHN32FV62FBIDS/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":"2026-08-07T08:19:49Z","links":{"resolver":"https://pith.science/pith/RLZI2BRXN4EVAHN32FV62FBIDS","bundle":"https://pith.science/pith/RLZI2BRXN4EVAHN32FV62FBIDS/bundle.json","state":"https://pith.science/pith/RLZI2BRXN4EVAHN32FV62FBIDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLZI2BRXN4EVAHN32FV62FBIDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RLZI2BRXN4EVAHN32FV62FBIDS","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":"cf4b997aa9c3f2bf7c4001c68434b7129c850b7c7cf9d314cc7939dd141cb33f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T15:24:05Z","title_canon_sha256":"2411f0489247f042db3f23b4178041cc292e9fa14cb4e035132dfe7be2d8eb6e"},"schema_version":"1.0","source":{"id":"2507.02946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02946","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02946v1","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02946","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"RLZI2BRXN4EV","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"RLZI2BRXN4EVAHN3","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"RLZI2BRX","created_at":"2026-07-05T11:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:392518cae61e61dab93f74d92ee5a8a0f2fe67ca32f0867aca96971ea0ab038d","target":"graph","created_at":"2026-07-05T11:31:49Z","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/2507.02946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an inefficient perception of temporal intervals. Unlike humans, who can dynamically adjust their temporal focus to locate query-relevant moments, current MLLMs often rely on dense, uniform sampling across the video timeline, leading to high memory consumption and a risk of missing crucial information. To address this challenge, we introduce Temporal Search, a training-free framework that enables MLLMs to explore temporal region","authors_text":"Chenglin Li, fengtao, Qianglong Chen, Yin Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T15:24:05Z","title":"Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02946","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":"sha256:800d7b4bf2b3a8d7de0712255cc12641505cdad10f511afa66b3e95a7cf29f22","target":"record","created_at":"2026-07-05T11:31:49Z","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":"cf4b997aa9c3f2bf7c4001c68434b7129c850b7c7cf9d314cc7939dd141cb33f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-28T15:24:05Z","title_canon_sha256":"2411f0489247f042db3f23b4178041cc292e9fa14cb4e035132dfe7be2d8eb6e"},"schema_version":"1.0","source":{"id":"2507.02946","kind":"arxiv","version":1}},"canonical_sha256":"8af28d06376f09501dbbd16bed14281caa416bdecf92cdfdcddf13eb7c7a4983","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8af28d06376f09501dbbd16bed14281caa416bdecf92cdfdcddf13eb7c7a4983","first_computed_at":"2026-07-05T11:31:49.306132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:49.306132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1GvFLJXicWLmlm1JtErxN1Em6D2kMnvG9p1kmwGJoPuCqgorNM9Kl1qvszya5C+qTBJlDVCk+LSH7Y/X+CI0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:49.306623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:800d7b4bf2b3a8d7de0712255cc12641505cdad10f511afa66b3e95a7cf29f22","sha256:392518cae61e61dab93f74d92ee5a8a0f2fe67ca32f0867aca96971ea0ab038d"],"state_sha256":"a3d34464a864e6c3fb505ba8f7d3a1caf8c8e17faf9909b09345069882c39f7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DNlDpCl364/T3AkchTXfKJ9d59oKegNRGIFJh6hVHRLWv7UVyqhiud+iPuWLa7OCtQxPzqnf4Qy/ZWiLq6CJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:19:49.493270Z","bundle_sha256":"f59d3f3dffe7c90dcbdfb85a4dad4d31f4ca9b2462169887b2802b66a5b8e723"}}