{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MOXSPI7IAQEUV6CW2MXHVNKKBO","short_pith_number":"pith:MOXSPI7I","canonical_record":{"source":{"id":"2501.15513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T13:10:12Z","cross_cats_sorted":[],"title_canon_sha256":"c356b28d023934e05a09cc63d4cb86d3e875cebb86b1dd37e17a2f78192e38e7","abstract_canon_sha256":"cbda01cb2e06a56f3bd6c2edfeb9014bf7483facab53c986c6107306699200ac"},"schema_version":"1.0"},"canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","source":{"kind":"arxiv","id":"2501.15513","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15513","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15513v2","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15513","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"MOXSPI7IAQEU","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"MOXSPI7IAQEUV6CW","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"MOXSPI7I","created_at":"2026-07-05T11:19:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MOXSPI7IAQEUV6CW2MXHVNKKBO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T13:10:12Z","cross_cats_sorted":[],"title_canon_sha256":"c356b28d023934e05a09cc63d4cb86d3e875cebb86b1dd37e17a2f78192e38e7","abstract_canon_sha256":"cbda01cb2e06a56f3bd6c2edfeb9014bf7483facab53c986c6107306699200ac"},"schema_version":"1.0"},"canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:02.939700Z","signature_b64":"i67u2XNLkkd9t6xDM0CsBjuinE7sB60U5mjX3Sg+8+zHD3ZB4/IokJ6uLa526DIsMxOK8EJNXLJh+j+1v35NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","last_reissued_at":"2026-07-05T11:19:02.939244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:02.939244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15513","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":"2026-07-05T11:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QAK6d4U80R/321Sjm84ERpRlQVqhqLLWU9LWfM87zY2yhrOusbZ4tHfCnV5eYZZT/yNZyKk8HqGI0BZLb6DrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:16:48.126962Z"},"content_sha256":"b70114bf4f3a3e81a8b4420eb5f1a4de80d7c40778bed10e39546f654af0ae0c","schema_version":"1.0","event_id":"sha256:b70114bf4f3a3e81a8b4420eb5f1a4de80d7c40778bed10e39546f654af0ae0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MOXSPI7IAQEUV6CW2MXHVNKKBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Huang, Wenjun Wu, Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan","submitted_at":"2025-01-26T13:10:12Z","abstract_excerpt":"Video behavior recognition and scene understanding are fundamental tasks in multimodal intelligence, serving as critical building blocks for numerous real-world applications. Through large multimodal models (LMMs) have achieved remarkable progress in video understanding, most existing open-source models rely on over 7B parameters and require large-scale datasets for training, making them resource-intensive and inaccessible to many researchers. Furthermore, lightweight models face persistent challenges in effectively processing long visual sequences and temporal understanding. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15513","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/2501.15513/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":"2026-07-05T11:19:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xmxl5O4z7hYb5C93B5Q4bA/qHMrj47IsebnD67gZJ2q/Lv8RN/zVfnkd/s9oBjEtJaLT3lQG2BXFuUd1MpM2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:16:48.127969Z"},"content_sha256":"725dd9eadaa1d21292e94427c556110b7b60972b2ecc06928ffba78fcaf0284c","schema_version":"1.0","event_id":"sha256:725dd9eadaa1d21292e94427c556110b7b60972b2ecc06928ffba78fcaf0284c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/bundle.json","state_url":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/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":"2026-08-04T16:16:48Z","links":{"resolver":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO","bundle":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/bundle.json","state":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MOXSPI7IAQEUV6CW2MXHVNKKBO","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":"cbda01cb2e06a56f3bd6c2edfeb9014bf7483facab53c986c6107306699200ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T13:10:12Z","title_canon_sha256":"c356b28d023934e05a09cc63d4cb86d3e875cebb86b1dd37e17a2f78192e38e7"},"schema_version":"1.0","source":{"id":"2501.15513","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15513","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15513v2","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15513","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"MOXSPI7IAQEU","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"MOXSPI7IAQEUV6CW","created_at":"2026-07-05T11:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"MOXSPI7I","created_at":"2026-07-05T11:19:02Z"}],"graph_snapshots":[{"event_id":"sha256:725dd9eadaa1d21292e94427c556110b7b60972b2ecc06928ffba78fcaf0284c","target":"graph","created_at":"2026-07-05T11:19:02Z","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/2501.15513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video behavior recognition and scene understanding are fundamental tasks in multimodal intelligence, serving as critical building blocks for numerous real-world applications. Through large multimodal models (LMMs) have achieved remarkable progress in video understanding, most existing open-source models rely on over 7B parameters and require large-scale datasets for training, making them resource-intensive and inaccessible to many researchers. Furthermore, lightweight models face persistent challenges in effectively processing long visual sequences and temporal understanding. In this work, we ","authors_text":"Lei Huang, Wenjun Wu, Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T13:10:12Z","title":"TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15513","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:b70114bf4f3a3e81a8b4420eb5f1a4de80d7c40778bed10e39546f654af0ae0c","target":"record","created_at":"2026-07-05T11:19:02Z","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":"cbda01cb2e06a56f3bd6c2edfeb9014bf7483facab53c986c6107306699200ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T13:10:12Z","title_canon_sha256":"c356b28d023934e05a09cc63d4cb86d3e875cebb86b1dd37e17a2f78192e38e7"},"schema_version":"1.0","source":{"id":"2501.15513","kind":"arxiv","version":2}},"canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","first_computed_at":"2026-07-05T11:19:02.939244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:02.939244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i67u2XNLkkd9t6xDM0CsBjuinE7sB60U5mjX3Sg+8+zHD3ZB4/IokJ6uLa526DIsMxOK8EJNXLJh+j+1v35NAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:02.939700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15513","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b70114bf4f3a3e81a8b4420eb5f1a4de80d7c40778bed10e39546f654af0ae0c","sha256:725dd9eadaa1d21292e94427c556110b7b60972b2ecc06928ffba78fcaf0284c"],"state_sha256":"f9b1300064eac25939b4f6a430ffb2214570830d991e59c1588d417100d04cf8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eM90nxw0u5QcgA2ngMcyqUtcPKXAUOeWCzTdWT+X8+QHonWh4Zbc3/Kx2UhFO3V87mJ7wl9TOA5IikRm6D5XAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:16:48.139610Z","bundle_sha256":"e45edfa9345d4d90cfdff7432dc84e2653134d4bf03e369c284986e0d4caf5d2"}}