{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SSV4M5DL5QOWTZ552GTQZUOTE2","short_pith_number":"pith:SSV4M5DL","canonical_record":{"source":{"id":"2411.11066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T13:08:29Z","cross_cats_sorted":[],"title_canon_sha256":"181509ea25ec91b3a982bfd8f269cfbd13ab8b0c155d1c39e678fc7487f3fe32","abstract_canon_sha256":"a00d737ac0eb2748adec7cf8ee734b323890d6b7dd15244807fbd17d3bb45106"},"schema_version":"1.0"},"canonical_sha256":"94abc6746bec1d69e7bdd1a70cd1d326b21bb65411b7168ae05c1737575d65a3","source":{"kind":"arxiv","id":"2411.11066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11066","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11066v1","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11066","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"SSV4M5DL5QOW","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"SSV4M5DL5QOWTZ55","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"SSV4M5DL","created_at":"2026-07-05T09:36:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SSV4M5DL5QOWTZ552GTQZUOTE2","target":"record","payload":{"canonical_record":{"source":{"id":"2411.11066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T13:08:29Z","cross_cats_sorted":[],"title_canon_sha256":"181509ea25ec91b3a982bfd8f269cfbd13ab8b0c155d1c39e678fc7487f3fe32","abstract_canon_sha256":"a00d737ac0eb2748adec7cf8ee734b323890d6b7dd15244807fbd17d3bb45106"},"schema_version":"1.0"},"canonical_sha256":"94abc6746bec1d69e7bdd1a70cd1d326b21bb65411b7168ae05c1737575d65a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:28.207264Z","signature_b64":"+WqEPWSHKCWi5VdM8phAwLCatk0RMVFSF+MP1kYvf/TQ+ig3nN8YN7HvqGuoKvHzK2s21Y5PXntYO9pm6dKPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94abc6746bec1d69e7bdd1a70cd1d326b21bb65411b7168ae05c1737575d65a3","last_reissued_at":"2026-07-05T09:36:28.206793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:28.206793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.11066","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":"2026-07-05T09:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRDHhApH0CqWsZnpf+xGblJ3pCdEcb+YgrVqY2HbrQKQ8FLfJXI4MC0+enrmob+Ruj8rBvd9GBsVibPbtImgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T22:31:07.006304Z"},"content_sha256":"fbd74407d1743470167a6cfbe01b6672afbca04e82dde11d7b1749ba21f71551","schema_version":"1.0","event_id":"sha256:fbd74407d1743470167a6cfbe01b6672afbca04e82dde11d7b1749ba21f71551"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SSV4M5DL5QOWTZ552GTQZUOTE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marie-Francine Moens, Mingxiao Li, Tingyu Qu, Tinne Tuytelaars","submitted_at":"2024-11-17T13:08:29Z","abstract_excerpt":"Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In contrast, paired image-text data are much easier to obtain, and there is substantial similarity between images and videos. Consequently, extending image LLMs for video understanding tasks presents an appealing alternative. Developing effective strategies for compressing visual tokens from multiple frames is a promising way "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11066","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/2411.11066/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":"2026-07-05T09:36:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7bSnOsuWloW6BLQLeCOi5MuucfosBalM/75mrD2nNK8kqDcpt4+QaZmsfvpk2wD+onZwbLQAk0wQGjcrtMqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T22:31:07.006827Z"},"content_sha256":"8822e1c3f154ac61596ebf19ea99c271fa5866c8048fe519004b500bf6e17cfc","schema_version":"1.0","event_id":"sha256:8822e1c3f154ac61596ebf19ea99c271fa5866c8048fe519004b500bf6e17cfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SSV4M5DL5QOWTZ552GTQZUOTE2/bundle.json","state_url":"https://pith.science/pith/SSV4M5DL5QOWTZ552GTQZUOTE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SSV4M5DL5QOWTZ552GTQZUOTE2/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":"2026-07-31T22:31:07Z","links":{"resolver":"https://pith.science/pith/SSV4M5DL5QOWTZ552GTQZUOTE2","bundle":"https://pith.science/pith/SSV4M5DL5QOWTZ552GTQZUOTE2/bundle.json","state":"https://pith.science/pith/SSV4M5DL5QOWTZ552GTQZUOTE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SSV4M5DL5QOWTZ552GTQZUOTE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SSV4M5DL5QOWTZ552GTQZUOTE2","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":"a00d737ac0eb2748adec7cf8ee734b323890d6b7dd15244807fbd17d3bb45106","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T13:08:29Z","title_canon_sha256":"181509ea25ec91b3a982bfd8f269cfbd13ab8b0c155d1c39e678fc7487f3fe32"},"schema_version":"1.0","source":{"id":"2411.11066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11066","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11066v1","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11066","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"pith_short_12","alias_value":"SSV4M5DL5QOW","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"pith_short_16","alias_value":"SSV4M5DL5QOWTZ55","created_at":"2026-07-05T09:36:28Z"},{"alias_kind":"pith_short_8","alias_value":"SSV4M5DL","created_at":"2026-07-05T09:36:28Z"}],"graph_snapshots":[{"event_id":"sha256:8822e1c3f154ac61596ebf19ea99c271fa5866c8048fe519004b500bf6e17cfc","target":"graph","created_at":"2026-07-05T09:36:28Z","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/2411.11066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In contrast, paired image-text data are much easier to obtain, and there is substantial similarity between images and videos. Consequently, extending image LLMs for video understanding tasks presents an appealing alternative. Developing effective strategies for compressing visual tokens from multiple frames is a promising way ","authors_text":"Marie-Francine Moens, Mingxiao Li, Tingyu Qu, Tinne Tuytelaars","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T13:08:29Z","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11066","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:fbd74407d1743470167a6cfbe01b6672afbca04e82dde11d7b1749ba21f71551","target":"record","created_at":"2026-07-05T09:36:28Z","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":"a00d737ac0eb2748adec7cf8ee734b323890d6b7dd15244807fbd17d3bb45106","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T13:08:29Z","title_canon_sha256":"181509ea25ec91b3a982bfd8f269cfbd13ab8b0c155d1c39e678fc7487f3fe32"},"schema_version":"1.0","source":{"id":"2411.11066","kind":"arxiv","version":1}},"canonical_sha256":"94abc6746bec1d69e7bdd1a70cd1d326b21bb65411b7168ae05c1737575d65a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94abc6746bec1d69e7bdd1a70cd1d326b21bb65411b7168ae05c1737575d65a3","first_computed_at":"2026-07-05T09:36:28.206793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:28.206793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+WqEPWSHKCWi5VdM8phAwLCatk0RMVFSF+MP1kYvf/TQ+ig3nN8YN7HvqGuoKvHzK2s21Y5PXntYO9pm6dKPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:28.207264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbd74407d1743470167a6cfbe01b6672afbca04e82dde11d7b1749ba21f71551","sha256:8822e1c3f154ac61596ebf19ea99c271fa5866c8048fe519004b500bf6e17cfc"],"state_sha256":"5d762552d8b4eadfc31d98bc07215542eb146fa16bf15857f8b8215c6568761e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D3nQTeETxDxAbzDej3IVdGNUI/nyqu2OO3Vw8E6NfXBRqAWrElpMTpUdj5DTSOcxE/UbFCbn8Wje9G0EdfDYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T22:31:07.010873Z","bundle_sha256":"f01721d0dfa4d0873d11cf4da4d4e3d5dec273854ef1e1fb2dcfca3411f9973e"}}