{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UP3LW4KDF5ES57AX62VLY2U3BL","short_pith_number":"pith:UP3LW4KD","canonical_record":{"source":{"id":"2311.17043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc3cf1b493ca012651a188f784fe21839ef2f19978274c2d1d47297ea2198394","abstract_canon_sha256":"a1c51d62780ff91da2bb06084ab7dc69d51c9cf61db8823c3524d1dab119ac6a"},"schema_version":"1.0"},"canonical_sha256":"a3f6bb71432f492efc17f6aabc6a9b0af45c8a486c2c8709851e116a15560553","source":{"kind":"arxiv","id":"2311.17043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17043","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17043v1","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17043","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"UP3LW4KDF5ES","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"UP3LW4KDF5ES57AX","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"UP3LW4KD","created_at":"2026-07-05T07:17:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UP3LW4KDF5ES57AX62VLY2U3BL","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc3cf1b493ca012651a188f784fe21839ef2f19978274c2d1d47297ea2198394","abstract_canon_sha256":"a1c51d62780ff91da2bb06084ab7dc69d51c9cf61db8823c3524d1dab119ac6a"},"schema_version":"1.0"},"canonical_sha256":"a3f6bb71432f492efc17f6aabc6a9b0af45c8a486c2c8709851e116a15560553","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:49.985597Z","signature_b64":"Iac6M3VDHsawonnG1pXejrSvERowDitC7y/PKqwdtAa5az0BDV3h5RNsdRClXI1ARDvRHz3AaHBZU3U/mmOkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3f6bb71432f492efc17f6aabc6a9b0af45c8a486c2c8709851e116a15560553","last_reissued_at":"2026-07-05T07:17:49.985004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:49.985004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17043","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":"2026-07-05T07:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6/Y8PUiuZkG1iiMU34YBWOdJznM2ZSZGwDAvTVRNuNbtMYzEHrxtGuyWssM9MnU/32m8Q+ACykpzZlVjhuYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:40:09.725381Z"},"content_sha256":"6dac9220fd85cf27e9e2d27c0ccfb738e4b2a3624a7462000e481570c4123ba6","schema_version":"1.0","event_id":"sha256:6dac9220fd85cf27e9e2d27c0ccfb738e4b2a3624a7462000e481570c4123ba6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UP3LW4KDF5ES57AX62VLY2U3BL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengyao Wang, Jiaya Jia, Yanwei Li","submitted_at":"2023-11-28T18:53:43Z","abstract_excerpt":"In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17043","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/2311.17043/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":"2026-07-05T07:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QviCKV1S7Y4fYV5rpSqpfuQzRdOyZ1vqCrCUG2cvkJVBMOt05rSE84baJRPEGhyA9OzUm7F3HOSE3lULxlYRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:40:09.725939Z"},"content_sha256":"b7262a600de461da78226db8997756939a749266e8709c92af076d5b75126677","schema_version":"1.0","event_id":"sha256:b7262a600de461da78226db8997756939a749266e8709c92af076d5b75126677"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UP3LW4KDF5ES57AX62VLY2U3BL/bundle.json","state_url":"https://pith.science/pith/UP3LW4KDF5ES57AX62VLY2U3BL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UP3LW4KDF5ES57AX62VLY2U3BL/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":"2026-08-06T22:40:09Z","links":{"resolver":"https://pith.science/pith/UP3LW4KDF5ES57AX62VLY2U3BL","bundle":"https://pith.science/pith/UP3LW4KDF5ES57AX62VLY2U3BL/bundle.json","state":"https://pith.science/pith/UP3LW4KDF5ES57AX62VLY2U3BL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UP3LW4KDF5ES57AX62VLY2U3BL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UP3LW4KDF5ES57AX62VLY2U3BL","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":"a1c51d62780ff91da2bb06084ab7dc69d51c9cf61db8823c3524d1dab119ac6a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:43Z","title_canon_sha256":"bc3cf1b493ca012651a188f784fe21839ef2f19978274c2d1d47297ea2198394"},"schema_version":"1.0","source":{"id":"2311.17043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17043","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17043v1","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17043","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"UP3LW4KDF5ES","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"UP3LW4KDF5ES57AX","created_at":"2026-07-05T07:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"UP3LW4KD","created_at":"2026-07-05T07:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:b7262a600de461da78226db8997756939a749266e8709c92af076d5b75126677","target":"graph","created_at":"2026-07-05T07:17:49Z","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/2311.17043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues i","authors_text":"Chengyao Wang, Jiaya Jia, Yanwei Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:43Z","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17043","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":"sha256:6dac9220fd85cf27e9e2d27c0ccfb738e4b2a3624a7462000e481570c4123ba6","target":"record","created_at":"2026-07-05T07:17:49Z","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":"a1c51d62780ff91da2bb06084ab7dc69d51c9cf61db8823c3524d1dab119ac6a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:53:43Z","title_canon_sha256":"bc3cf1b493ca012651a188f784fe21839ef2f19978274c2d1d47297ea2198394"},"schema_version":"1.0","source":{"id":"2311.17043","kind":"arxiv","version":1}},"canonical_sha256":"a3f6bb71432f492efc17f6aabc6a9b0af45c8a486c2c8709851e116a15560553","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3f6bb71432f492efc17f6aabc6a9b0af45c8a486c2c8709851e116a15560553","first_computed_at":"2026-07-05T07:17:49.985004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:49.985004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iac6M3VDHsawonnG1pXejrSvERowDitC7y/PKqwdtAa5az0BDV3h5RNsdRClXI1ARDvRHz3AaHBZU3U/mmOkCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:49.985597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dac9220fd85cf27e9e2d27c0ccfb738e4b2a3624a7462000e481570c4123ba6","sha256:b7262a600de461da78226db8997756939a749266e8709c92af076d5b75126677"],"state_sha256":"1c724d5b6992d92d84e7412beaef3dfa476d69f364d62da84ab600da2346bc4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csoXo7VZ+KVxyD8zfnlaqq3kjxtz7jHHsS1qlm343ezuhTobKeSdot4z767p0iwTbM/EBDQGUJ+Wrdzvbx4zDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:40:09.729708Z","bundle_sha256":"36c8d3d86c1fbd80319804f5b53b76cc3f91be47cb66ce46034661f7eecb0dda"}}