{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UN25A74EHZ6ASUFKEGESUWMT2J","short_pith_number":"pith:UN25A74E","canonical_record":{"source":{"id":"2412.03548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:45:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3ad9d789ad6201dd9b0407532d9892ebf5901da2fa28c91e66ce4a26c1afea75","abstract_canon_sha256":"256887e12fb264be8dbbd103df32fbfb9892a6bc3773e9f0bea4b5c6040be417"},"schema_version":"1.0"},"canonical_sha256":"a375d07f843e7c0950aa21892a5993d279e841450067558ac3f661daad236be1","source":{"kind":"arxiv","id":"2412.03548","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03548","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03548v2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03548","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"UN25A74EHZ6A","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"UN25A74EHZ6ASUFK","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"UN25A74E","created_at":"2026-07-05T09:45:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UN25A74EHZ6ASUFKEGESUWMT2J","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:45:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3ad9d789ad6201dd9b0407532d9892ebf5901da2fa28c91e66ce4a26c1afea75","abstract_canon_sha256":"256887e12fb264be8dbbd103df32fbfb9892a6bc3773e9f0bea4b5c6040be417"},"schema_version":"1.0"},"canonical_sha256":"a375d07f843e7c0950aa21892a5993d279e841450067558ac3f661daad236be1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:59.997716Z","signature_b64":"bisFp5icW2P7s6Y7nsWgINXLXWd+6bDQ+hJNmWLpUfqgndlSZwwqca22zGvdo0LD7I97JUsc61C7NrBZk02ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a375d07f843e7c0950aa21892a5993d279e841450067558ac3f661daad236be1","last_reissued_at":"2026-07-05T09:45:59.997181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:59.997181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03548","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":"2026-07-05T09:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Wel8dncJ0pT3sN+ST0D0QYT1zic/RNwHsiApPsFCbC4MeUtmzI9kjEZ4NCCSVmXQxMMP9mtcuaaGulklhVSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:37.550443Z"},"content_sha256":"f0c8254ea08832b697941db7dd5f77074e398eab79adc25b7325010cf3485491","schema_version":"1.0","event_id":"sha256:f0c8254ea08832b697941db7dd5f77074e398eab79adc25b7325010cf3485491"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UN25A74EHZ6ASUFKEGESUWMT2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Yu Hsieh, Dongping Chen, Ethan Shen, Linda G. Shapiro, Mahtab Bigverdi, Ranjay Krishna, Zelun Luo","submitted_at":"2024-12-04T18:45:35Z","abstract_excerpt":"Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object instances benefits from object detection. Yet, MLMs can not produce intermediate depth or boxes to reason over. Finetuning MLMs on relevant data doesn't generalize well and outsourcing computation to specialized vision tools is too compute-intensive and memory-inefficient. To address this, we introduce Perception Tokens, intrinsic image representations designed to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03548","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/2412.03548/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":"2026-07-05T09:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKBlbS1vo/Lkl8VZZmkRxcXEJ+89f7IkGD/A5WisosmfzT8pvpcMrUMkGdRrAU5RsmGUrjT0Jy7DeaD5/KhvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:01:37.550959Z"},"content_sha256":"f5a342351334c4354282d741525ce5a0ac7cc21e7c5ea56144a896fe8870c385","schema_version":"1.0","event_id":"sha256:f5a342351334c4354282d741525ce5a0ac7cc21e7c5ea56144a896fe8870c385"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UN25A74EHZ6ASUFKEGESUWMT2J/bundle.json","state_url":"https://pith.science/pith/UN25A74EHZ6ASUFKEGESUWMT2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UN25A74EHZ6ASUFKEGESUWMT2J/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":"2026-08-08T17:01:37Z","links":{"resolver":"https://pith.science/pith/UN25A74EHZ6ASUFKEGESUWMT2J","bundle":"https://pith.science/pith/UN25A74EHZ6ASUFKEGESUWMT2J/bundle.json","state":"https://pith.science/pith/UN25A74EHZ6ASUFKEGESUWMT2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UN25A74EHZ6ASUFKEGESUWMT2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UN25A74EHZ6ASUFKEGESUWMT2J","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":"256887e12fb264be8dbbd103df32fbfb9892a6bc3773e9f0bea4b5c6040be417","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:45:35Z","title_canon_sha256":"3ad9d789ad6201dd9b0407532d9892ebf5901da2fa28c91e66ce4a26c1afea75"},"schema_version":"1.0","source":{"id":"2412.03548","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03548","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03548v2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03548","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"UN25A74EHZ6A","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"UN25A74EHZ6ASUFK","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"UN25A74E","created_at":"2026-07-05T09:45:59Z"}],"graph_snapshots":[{"event_id":"sha256:f5a342351334c4354282d741525ce5a0ac7cc21e7c5ea56144a896fe8870c385","target":"graph","created_at":"2026-07-05T09:45:59Z","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/2412.03548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object instances benefits from object detection. Yet, MLMs can not produce intermediate depth or boxes to reason over. Finetuning MLMs on relevant data doesn't generalize well and outsourcing computation to specialized vision tools is too compute-intensive and memory-inefficient. To address this, we introduce Perception Tokens, intrinsic image representations designed to","authors_text":"Cheng-Yu Hsieh, Dongping Chen, Ethan Shen, Linda G. Shapiro, Mahtab Bigverdi, Ranjay Krishna, Zelun Luo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:45:35Z","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03548","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:f0c8254ea08832b697941db7dd5f77074e398eab79adc25b7325010cf3485491","target":"record","created_at":"2026-07-05T09:45:59Z","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":"256887e12fb264be8dbbd103df32fbfb9892a6bc3773e9f0bea4b5c6040be417","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:45:35Z","title_canon_sha256":"3ad9d789ad6201dd9b0407532d9892ebf5901da2fa28c91e66ce4a26c1afea75"},"schema_version":"1.0","source":{"id":"2412.03548","kind":"arxiv","version":2}},"canonical_sha256":"a375d07f843e7c0950aa21892a5993d279e841450067558ac3f661daad236be1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a375d07f843e7c0950aa21892a5993d279e841450067558ac3f661daad236be1","first_computed_at":"2026-07-05T09:45:59.997181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:59.997181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bisFp5icW2P7s6Y7nsWgINXLXWd+6bDQ+hJNmWLpUfqgndlSZwwqca22zGvdo0LD7I97JUsc61C7NrBZk02ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:59.997716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03548","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0c8254ea08832b697941db7dd5f77074e398eab79adc25b7325010cf3485491","sha256:f5a342351334c4354282d741525ce5a0ac7cc21e7c5ea56144a896fe8870c385"],"state_sha256":"bb355af1861752ccb9f63aaea11eba255221a3848c8dc7d9bf751da904055417"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BihcqcQikxdVVRF7U/GUoqYxgbZkkW0wP7vKHSfuWZE3Pg/5uKTo0b8XsHlxjyTaz6o8CLV2IqnJdENq5hEIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:01:37.556198Z","bundle_sha256":"8249ddbd3f0367a332fa5388239adcd2446f5811ea56e9dfb6dff10a905052db"}}