{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2Q5YFT6XKUZERZWBNDTOC6FMFC","short_pith_number":"pith:2Q5YFT6X","canonical_record":{"source":{"id":"2411.03312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:54:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d8f858c42419ea7f600810effd128fac517aa093cbff348f0a5caa437d1b5396","abstract_canon_sha256":"7c5ada671e3e2f5fbc721907e08983ba7c9789df08b6421c9aa6c77f16182b0a"},"schema_version":"1.0"},"canonical_sha256":"d43b82cfd7553248e6c168e6e178ac28816686e4cc42a8affe4650e9a64637ad","source":{"kind":"arxiv","id":"2411.03312","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03312","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03312v2","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03312","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"2Q5YFT6XKUZE","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"2Q5YFT6XKUZERZWB","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"2Q5YFT6X","created_at":"2026-07-05T10:51:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2Q5YFT6XKUZERZWBNDTOC6FMFC","target":"record","payload":{"canonical_record":{"source":{"id":"2411.03312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:54:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d8f858c42419ea7f600810effd128fac517aa093cbff348f0a5caa437d1b5396","abstract_canon_sha256":"7c5ada671e3e2f5fbc721907e08983ba7c9789df08b6421c9aa6c77f16182b0a"},"schema_version":"1.0"},"canonical_sha256":"d43b82cfd7553248e6c168e6e178ac28816686e4cc42a8affe4650e9a64637ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:27.954500Z","signature_b64":"s2BvprBr9D5ZSP9u5OcWY7VoLCxHvKvx1KOO/4F79/IwWisoS2cdmANYuNuSfU8k9zcLyJvf+zJ6lmVP4cH9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43b82cfd7553248e6c168e6e178ac28816686e4cc42a8affe4650e9a64637ad","last_reissued_at":"2026-07-05T10:51:27.954006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:27.954006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.03312","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":"2026-07-05T10:51:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j07mbGLlkEqsnhEbuSvFFz6Cj93268ZfOjSjrjhu/W4H278HAf+5HjWGei2+OvMJySwXQ7niHD0ZMSGXpScsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:09:53.040049Z"},"content_sha256":"f6f88293c6f93e109e5e98861da12342bba0ac0cd6f303f8a9b7e58d0014b25c","schema_version":"1.0","event_id":"sha256:f6f88293c6f93e109e5e98861da12342bba0ac0cd6f303f8a9b7e58d0014b25c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2Q5YFT6XKUZERZWBNDTOC6FMFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Joao D. Semedo, J. Zico Kolter, Kevin Y. Li, Sachin Goyal","submitted_at":"2024-11-05T18:54:21Z","abstract_excerpt":"Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks, driven by incorporating image representations into the token inputs of Large Language Models (LLMs). However, their real-world deployment is often constrained by high latency during inference due to the substantial compute required by the LLM to process the large number of input tokens, predominantly arising from the image. To reduce inference costs, one can either downsize the LLM or reduce the number of input tokens needed to represent the image, the latter of which ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03312","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/2411.03312/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":"2026-07-05T10:51:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2S69Cgd2e7XMhe42ZDyuKOxXir1JATRaJsTvetjoXNLDAldDSdz6mA7eVm1aH79lTOqSnigf8WmRmroXyPtfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:09:53.041350Z"},"content_sha256":"1c3c01d66704933cf92f6760b681c325b68d8c2682ccee226c422606f6df9c54","schema_version":"1.0","event_id":"sha256:1c3c01d66704933cf92f6760b681c325b68d8c2682ccee226c422606f6df9c54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC/bundle.json","state_url":"https://pith.science/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC/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":"2026-08-20T06:09:53Z","links":{"resolver":"https://pith.science/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC","bundle":"https://pith.science/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC/bundle.json","state":"https://pith.science/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Q5YFT6XKUZERZWBNDTOC6FMFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2Q5YFT6XKUZERZWBNDTOC6FMFC","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":"7c5ada671e3e2f5fbc721907e08983ba7c9789df08b6421c9aa6c77f16182b0a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:54:21Z","title_canon_sha256":"d8f858c42419ea7f600810effd128fac517aa093cbff348f0a5caa437d1b5396"},"schema_version":"1.0","source":{"id":"2411.03312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03312","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03312v2","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03312","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_12","alias_value":"2Q5YFT6XKUZE","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_16","alias_value":"2Q5YFT6XKUZERZWB","created_at":"2026-07-05T10:51:27Z"},{"alias_kind":"pith_short_8","alias_value":"2Q5YFT6X","created_at":"2026-07-05T10:51:27Z"}],"graph_snapshots":[{"event_id":"sha256:1c3c01d66704933cf92f6760b681c325b68d8c2682ccee226c422606f6df9c54","target":"graph","created_at":"2026-07-05T10:51:27Z","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/2411.03312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks, driven by incorporating image representations into the token inputs of Large Language Models (LLMs). However, their real-world deployment is often constrained by high latency during inference due to the substantial compute required by the LLM to process the large number of input tokens, predominantly arising from the image. To reduce inference costs, one can either downsize the LLM or reduce the number of input tokens needed to represent the image, the latter of which ha","authors_text":"Joao D. Semedo, J. Zico Kolter, Kevin Y. Li, Sachin Goyal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:54:21Z","title":"Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03312","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:f6f88293c6f93e109e5e98861da12342bba0ac0cd6f303f8a9b7e58d0014b25c","target":"record","created_at":"2026-07-05T10:51:27Z","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":"7c5ada671e3e2f5fbc721907e08983ba7c9789df08b6421c9aa6c77f16182b0a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:54:21Z","title_canon_sha256":"d8f858c42419ea7f600810effd128fac517aa093cbff348f0a5caa437d1b5396"},"schema_version":"1.0","source":{"id":"2411.03312","kind":"arxiv","version":2}},"canonical_sha256":"d43b82cfd7553248e6c168e6e178ac28816686e4cc42a8affe4650e9a64637ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d43b82cfd7553248e6c168e6e178ac28816686e4cc42a8affe4650e9a64637ad","first_computed_at":"2026-07-05T10:51:27.954006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:27.954006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s2BvprBr9D5ZSP9u5OcWY7VoLCxHvKvx1KOO/4F79/IwWisoS2cdmANYuNuSfU8k9zcLyJvf+zJ6lmVP4cH9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:27.954500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6f88293c6f93e109e5e98861da12342bba0ac0cd6f303f8a9b7e58d0014b25c","sha256:1c3c01d66704933cf92f6760b681c325b68d8c2682ccee226c422606f6df9c54"],"state_sha256":"e5935b2e6b29a720884a5bd37453caa63432fc422dda256d241150fd8700a1bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qW1gwALPNXfj5I7U8qT8e72UcTJyjLhhk1yZgNncHZVQPUfQPpHTYaGFlWpTwo1lzd2+82od8ekvK1gXeboBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:09:53.046950Z","bundle_sha256":"af1e657e3c5a7277c2d5be22d24e79cff05269490812cfbd9669bc9e2b6dd322"}}