{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KSU3HVFROVYNFL3BFHNTYEXBF6","short_pith_number":"pith:KSU3HVFR","canonical_record":{"source":{"id":"2411.14901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T12:46:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c12fa06eab22a81bb54af5ec2fb4a190051e56df4563ec0434e339aa754a3353","abstract_canon_sha256":"453ddb1826ba255a32b8d26bb19a611f3960ec9fb9da88c27571c75251c6dbde"},"schema_version":"1.0"},"canonical_sha256":"54a9b3d4b17570d2af6129db3c12e12f8e2ba9f51d2b4313db8170174e58dbfe","source":{"kind":"arxiv","id":"2411.14901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14901","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14901v1","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14901","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"KSU3HVFROVYN","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"KSU3HVFROVYNFL3B","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"KSU3HVFR","created_at":"2026-07-05T09:39:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KSU3HVFROVYNFL3BFHNTYEXBF6","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T12:46:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c12fa06eab22a81bb54af5ec2fb4a190051e56df4563ec0434e339aa754a3353","abstract_canon_sha256":"453ddb1826ba255a32b8d26bb19a611f3960ec9fb9da88c27571c75251c6dbde"},"schema_version":"1.0"},"canonical_sha256":"54a9b3d4b17570d2af6129db3c12e12f8e2ba9f51d2b4313db8170174e58dbfe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:13.517160Z","signature_b64":"QTXzA6jbdwHGWl9PuvnVhuRButk+uRSSo1fIg2lknso9TboAf1mCC9iKQYwvHALqpEfeokf+aPDmXFqtayKKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a9b3d4b17570d2af6129db3c12e12f8e2ba9f51d2b4313db8170174e58dbfe","last_reissued_at":"2026-07-05T09:39:13.516745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:13.516745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14901","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":"2026-07-05T09:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6ywx2nRT7P/cZLmCHzhHEGL0dgib/NWBDGV3JT5EEqMNsEehWoncktfE63JdvrO8rjbHltgiSJawE80xPleCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T06:36:11.824640Z"},"content_sha256":"efbf980153d33e8cd79386bc9166b8c9d948a78381e4e307756c8a272abbc208","schema_version":"1.0","event_id":"sha256:efbf980153d33e8cd79386bc9166b8c9d948a78381e4e307756c8a272abbc208"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KSU3HVFROVYNFL3BFHNTYEXBF6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Jindong Gu, Md Mohaiminul Islam, Tanveer Hannan, Thomas Seidl","submitted_at":"2024-11-22T12:46:50Z","abstract_excerpt":"Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are constrained by frame limitations, often losing essential temporal details needed for accurate event localization in extended video content. We propose ReVisionLLM, a recursive vision-language model designed to locate events in hour-long videos. Inspired by human search strategies, our model initially targets broad segments of interest, progressively revising its focu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14901","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/2411.14901/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":"2026-07-05T09:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K23dAhFwS6hPS9pfusCQ4htsTB0u38+7TsfCw0r2CYK+kwEydS2NJK5lKjvXxpQvjBPwyc7oT1iyeq/6IbEhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T06:36:11.825171Z"},"content_sha256":"bc04ec44804fad47c138d7d17d3a7027b1ccfe0c4035d60209a028a3c8d6ff04","schema_version":"1.0","event_id":"sha256:bc04ec44804fad47c138d7d17d3a7027b1ccfe0c4035d60209a028a3c8d6ff04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSU3HVFROVYNFL3BFHNTYEXBF6/bundle.json","state_url":"https://pith.science/pith/KSU3HVFROVYNFL3BFHNTYEXBF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSU3HVFROVYNFL3BFHNTYEXBF6/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":"2026-08-13T06:36:11Z","links":{"resolver":"https://pith.science/pith/KSU3HVFROVYNFL3BFHNTYEXBF6","bundle":"https://pith.science/pith/KSU3HVFROVYNFL3BFHNTYEXBF6/bundle.json","state":"https://pith.science/pith/KSU3HVFROVYNFL3BFHNTYEXBF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSU3HVFROVYNFL3BFHNTYEXBF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KSU3HVFROVYNFL3BFHNTYEXBF6","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":"453ddb1826ba255a32b8d26bb19a611f3960ec9fb9da88c27571c75251c6dbde","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T12:46:50Z","title_canon_sha256":"c12fa06eab22a81bb54af5ec2fb4a190051e56df4563ec0434e339aa754a3353"},"schema_version":"1.0","source":{"id":"2411.14901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14901","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14901v1","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14901","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"KSU3HVFROVYN","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"KSU3HVFROVYNFL3B","created_at":"2026-07-05T09:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"KSU3HVFR","created_at":"2026-07-05T09:39:13Z"}],"graph_snapshots":[{"event_id":"sha256:bc04ec44804fad47c138d7d17d3a7027b1ccfe0c4035d60209a028a3c8d6ff04","target":"graph","created_at":"2026-07-05T09:39:13Z","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/2411.14901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are constrained by frame limitations, often losing essential temporal details needed for accurate event localization in extended video content. We propose ReVisionLLM, a recursive vision-language model designed to locate events in hour-long videos. Inspired by human search strategies, our model initially targets broad segments of interest, progressively revising its focu","authors_text":"Gedas Bertasius, Jindong Gu, Md Mohaiminul Islam, Tanveer Hannan, Thomas Seidl","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T12:46:50Z","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14901","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:efbf980153d33e8cd79386bc9166b8c9d948a78381e4e307756c8a272abbc208","target":"record","created_at":"2026-07-05T09:39:13Z","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":"453ddb1826ba255a32b8d26bb19a611f3960ec9fb9da88c27571c75251c6dbde","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T12:46:50Z","title_canon_sha256":"c12fa06eab22a81bb54af5ec2fb4a190051e56df4563ec0434e339aa754a3353"},"schema_version":"1.0","source":{"id":"2411.14901","kind":"arxiv","version":1}},"canonical_sha256":"54a9b3d4b17570d2af6129db3c12e12f8e2ba9f51d2b4313db8170174e58dbfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54a9b3d4b17570d2af6129db3c12e12f8e2ba9f51d2b4313db8170174e58dbfe","first_computed_at":"2026-07-05T09:39:13.516745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:13.516745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QTXzA6jbdwHGWl9PuvnVhuRButk+uRSSo1fIg2lknso9TboAf1mCC9iKQYwvHALqpEfeokf+aPDmXFqtayKKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:13.517160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efbf980153d33e8cd79386bc9166b8c9d948a78381e4e307756c8a272abbc208","sha256:bc04ec44804fad47c138d7d17d3a7027b1ccfe0c4035d60209a028a3c8d6ff04"],"state_sha256":"ffa4da7edd59fe004d16ce9edecb2f3c31f5683dd5c489b1f620e2baed0c2d03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vtb2t8v1TnedAL8y+YhGWUJ7pX0OnW7hyvzSS8X//+AHiCVSBEmOojm7/qAK/07tmHIKijDG4HUd3aZe6N7/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T06:36:11.830041Z","bundle_sha256":"08d7e06962f44c017ecd06e1bc580f8d2beb4e6e7b37106d3285de14cdb771b0"}}