{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3TN6ZRNZJKI5G73GLGYKZW74JR","short_pith_number":"pith:3TN6ZRNZ","canonical_record":{"source":{"id":"2411.10332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:32:34Z","cross_cats_sorted":[],"title_canon_sha256":"33e5de45087a1cfac6883d19e87e80f2c433054703c043aef3d2e36a04eb8e23","abstract_canon_sha256":"df844677330f5f8a5f31ab5c9b7102f2bdd01bcc94268958f26fcc0ffca96b34"},"schema_version":"1.0"},"canonical_sha256":"dcdbecc5b94a91d37f6659b0acdbfc4c6870252da48d16cba1e3e6d8508c941d","source":{"kind":"arxiv","id":"2411.10332","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10332","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10332v3","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10332","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"3TN6ZRNZJKI5","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"3TN6ZRNZJKI5G73G","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"3TN6ZRNZ","created_at":"2026-07-05T10:36:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3TN6ZRNZJKI5G73GLGYKZW74JR","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10332","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:32:34Z","cross_cats_sorted":[],"title_canon_sha256":"33e5de45087a1cfac6883d19e87e80f2c433054703c043aef3d2e36a04eb8e23","abstract_canon_sha256":"df844677330f5f8a5f31ab5c9b7102f2bdd01bcc94268958f26fcc0ffca96b34"},"schema_version":"1.0"},"canonical_sha256":"dcdbecc5b94a91d37f6659b0acdbfc4c6870252da48d16cba1e3e6d8508c941d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:31.558688Z","signature_b64":"nGT1V8RwQYQvxZBvRSZez2BEk547JdTi4SKgZcOFlmakgmsuguN+Yh8QFyjBL6sFGXioYWi06UknQDMUBVd1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcdbecc5b94a91d37f6659b0acdbfc4c6870252da48d16cba1e3e6d8508c941d","last_reissued_at":"2026-07-05T10:36:31.558193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:31.558193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10332","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xPCwFMpa7YRFmLihKqOt4jk7WzY8tj6quzwrGNvHP87xmhQC5rSWRy8DrSnoRuddutBA0HTOzoNLFSjZKTb+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:27:51.887781Z"},"content_sha256":"2d75b8cbbdfcd6c77d3f70dddd72a211a6173d0bb268383607483ee12dfdf7ec","schema_version":"1.0","event_id":"sha256:2d75b8cbbdfcd6c77d3f70dddd72a211a6173d0bb268383607483ee12dfdf7ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3TN6ZRNZJKI5G73GLGYKZW74JR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Number it: Temporal Grounding Videos like Flipping Manga","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Fengyun Rao, Wenbo Zhu, Xinting Hu, Xu Yang, Yizhou Zhou, Yongliang Wu, Yuyang Sun","submitted_at":"2024-11-15T16:32:34Z","abstract_excerpt":"Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as Video Temporal Grounding (VTG). To address this gap, we introduce Number-Prompt (NumPro), a novel method that empowers Vid-LLMs to bridge visual comprehension with temporal grounding by adding unique numerical identifiers to each video frame. Treating a video as a sequence of numbered frame images, NumPro transforms VTG into an intuitive process: flipping thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10332","kind":"arxiv","version":3},"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/2411.10332/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":"2026-07-05T10:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxqY4lDZ+Se8AzB7VRSjBCKxNY71p59y4J/L0w+XMCLVT+6ObekPkHW5Lo+4vROQ9sS8WAWAE2MQHE6T0F6nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:27:51.888385Z"},"content_sha256":"d4cfdfce49dc6f8614b8405314a068202060ac870eab531701c011c806ba2132","schema_version":"1.0","event_id":"sha256:d4cfdfce49dc6f8614b8405314a068202060ac870eab531701c011c806ba2132"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TN6ZRNZJKI5G73GLGYKZW74JR/bundle.json","state_url":"https://pith.science/pith/3TN6ZRNZJKI5G73GLGYKZW74JR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TN6ZRNZJKI5G73GLGYKZW74JR/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":"2026-08-05T02:27:51Z","links":{"resolver":"https://pith.science/pith/3TN6ZRNZJKI5G73GLGYKZW74JR","bundle":"https://pith.science/pith/3TN6ZRNZJKI5G73GLGYKZW74JR/bundle.json","state":"https://pith.science/pith/3TN6ZRNZJKI5G73GLGYKZW74JR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TN6ZRNZJKI5G73GLGYKZW74JR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3TN6ZRNZJKI5G73GLGYKZW74JR","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":"df844677330f5f8a5f31ab5c9b7102f2bdd01bcc94268958f26fcc0ffca96b34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:32:34Z","title_canon_sha256":"33e5de45087a1cfac6883d19e87e80f2c433054703c043aef3d2e36a04eb8e23"},"schema_version":"1.0","source":{"id":"2411.10332","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10332","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10332v3","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10332","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"3TN6ZRNZJKI5","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"3TN6ZRNZJKI5G73G","created_at":"2026-07-05T10:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"3TN6ZRNZ","created_at":"2026-07-05T10:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:d4cfdfce49dc6f8614b8405314a068202060ac870eab531701c011c806ba2132","target":"graph","created_at":"2026-07-05T10:36:31Z","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/2411.10332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as Video Temporal Grounding (VTG). To address this gap, we introduce Number-Prompt (NumPro), a novel method that empowers Vid-LLMs to bridge visual comprehension with temporal grounding by adding unique numerical identifiers to each video frame. Treating a video as a sequence of numbered frame images, NumPro transforms VTG into an intuitive process: flipping thr","authors_text":"Bernt Schiele, Fengyun Rao, Wenbo Zhu, Xinting Hu, Xu Yang, Yizhou Zhou, Yongliang Wu, Yuyang Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:32:34Z","title":"Number it: Temporal Grounding Videos like Flipping Manga"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10332","kind":"arxiv","version":3},"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":"sha256:2d75b8cbbdfcd6c77d3f70dddd72a211a6173d0bb268383607483ee12dfdf7ec","target":"record","created_at":"2026-07-05T10:36:31Z","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":"df844677330f5f8a5f31ab5c9b7102f2bdd01bcc94268958f26fcc0ffca96b34","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:32:34Z","title_canon_sha256":"33e5de45087a1cfac6883d19e87e80f2c433054703c043aef3d2e36a04eb8e23"},"schema_version":"1.0","source":{"id":"2411.10332","kind":"arxiv","version":3}},"canonical_sha256":"dcdbecc5b94a91d37f6659b0acdbfc4c6870252da48d16cba1e3e6d8508c941d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcdbecc5b94a91d37f6659b0acdbfc4c6870252da48d16cba1e3e6d8508c941d","first_computed_at":"2026-07-05T10:36:31.558193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:31.558193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nGT1V8RwQYQvxZBvRSZez2BEk547JdTi4SKgZcOFlmakgmsuguN+Yh8QFyjBL6sFGXioYWi06UknQDMUBVd1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:31.558688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10332","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d75b8cbbdfcd6c77d3f70dddd72a211a6173d0bb268383607483ee12dfdf7ec","sha256:d4cfdfce49dc6f8614b8405314a068202060ac870eab531701c011c806ba2132"],"state_sha256":"851df2b9d0d7a4dd9e94a859fbc1751251047d3654aa28e3845166725dbc069f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAOZaa7mI/5TW8IRzPL+G+fS/vKjq4qTREDOqtLELYzz/bEe9ApBoxNzfXcu3bLu00LOfxgdwj9lKDXOjGdzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:27:51.892459Z","bundle_sha256":"c903c8a6432010f0742d972b994e9ef6aea900cfcafa8f075c9994e6acd9634a"}}