{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O7KZVJB2V37MX5EHPZFN47MW2M","short_pith_number":"pith:O7KZVJB2","canonical_record":{"source":{"id":"2405.20339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"8b3baf24c9e092313f2c1621da6669b79ea110046d3255734d128ee840489f34","abstract_canon_sha256":"af727b53dacc6123493dbf374fbd37fbaffd46a2297848bd4c426494624300fc"},"schema_version":"1.0"},"canonical_sha256":"77d59aa43aaefecbf4877e4ade7d96d307f87740ad0a448ff9f8f92513750c25","source":{"kind":"arxiv","id":"2405.20339","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20339","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20339v1","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20339","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"O7KZVJB2V37M","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"O7KZVJB2V37MX5EH","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"O7KZVJB2","created_at":"2026-07-05T08:25:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O7KZVJB2V37MX5EHPZFN47MW2M","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"8b3baf24c9e092313f2c1621da6669b79ea110046d3255734d128ee840489f34","abstract_canon_sha256":"af727b53dacc6123493dbf374fbd37fbaffd46a2297848bd4c426494624300fc"},"schema_version":"1.0"},"canonical_sha256":"77d59aa43aaefecbf4877e4ade7d96d307f87740ad0a448ff9f8f92513750c25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:24.554228Z","signature_b64":"pKdo+/d3HHLirgf9wTTDOJKeS7gOP9mxNVupLct3+L8q0ZqkUHXmVHKtIeiDHBKVmfXX9ETYYCIPAQteq9O/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d59aa43aaefecbf4877e4ade7d96d307f87740ad0a448ff9f8f92513750c25","last_reissued_at":"2026-07-05T08:25:24.553704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:24.553704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20339","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":"2026-07-05T08:25:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95q4q8JsvuQTNg6css4weluoI3TmXj/ZLi7lXPrzqqGfBIpghXB4FNPQ1pz2yfEihWwdYMkwE+n4e6hYWugTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:19:21.714161Z"},"content_sha256":"ecf45a1fd7272997505d721612aa68bb4ac02a61548c933ec93f2dc12446f98e","schema_version":"1.0","event_id":"sha256:ecf45a1fd7272997505d721612aa68bb4ac02a61548c933ec93f2dc12446f98e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O7KZVJB2V37MX5EHPZFN47MW2M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Perception by Large Language Model's Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feipeng Ma, Fengyun Rao, Guangting Wang, Hongwei Xue, Mike Zheng Shou, Shilin Yan, Siying Wu, Xiaoyan Sun, Yizhou Zhou, Yueyi Zhang","submitted_at":"2024-05-30T17:59:47Z","abstract_excerpt":"Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs), and concatenating visual tokens with text tokens to form a unified sequence input for LLMs. These methods demonstrate promising results on various vision-language tasks but are limited by the high computational effort due to the extended input sequence resulting from the involvement of visual tokens. In this paper, instead of input space alignment, we propose a novel parameter space alignment paradigm that repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20339","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/2405.20339/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":"2026-07-05T08:25:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kYdKWJR/oMeog17cWQLjvuRYYalV9VgcdMEwRzjkFAFWunN4bxVTNQHCZT+LwjwR15TzqgTBX+j/EUyEgmUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:19:21.715043Z"},"content_sha256":"9ff2ee25760031b6fc4ef6af038c2ceff1c5ad6e6adf3ac28bd489262f007422","schema_version":"1.0","event_id":"sha256:9ff2ee25760031b6fc4ef6af038c2ceff1c5ad6e6adf3ac28bd489262f007422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7KZVJB2V37MX5EHPZFN47MW2M/bundle.json","state_url":"https://pith.science/pith/O7KZVJB2V37MX5EHPZFN47MW2M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7KZVJB2V37MX5EHPZFN47MW2M/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":"2026-08-08T17:19:21Z","links":{"resolver":"https://pith.science/pith/O7KZVJB2V37MX5EHPZFN47MW2M","bundle":"https://pith.science/pith/O7KZVJB2V37MX5EHPZFN47MW2M/bundle.json","state":"https://pith.science/pith/O7KZVJB2V37MX5EHPZFN47MW2M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7KZVJB2V37MX5EHPZFN47MW2M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O7KZVJB2V37MX5EHPZFN47MW2M","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":"af727b53dacc6123493dbf374fbd37fbaffd46a2297848bd4c426494624300fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:59:47Z","title_canon_sha256":"8b3baf24c9e092313f2c1621da6669b79ea110046d3255734d128ee840489f34"},"schema_version":"1.0","source":{"id":"2405.20339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20339","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20339v1","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20339","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"O7KZVJB2V37M","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"O7KZVJB2V37MX5EH","created_at":"2026-07-05T08:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"O7KZVJB2","created_at":"2026-07-05T08:25:24Z"}],"graph_snapshots":[{"event_id":"sha256:9ff2ee25760031b6fc4ef6af038c2ceff1c5ad6e6adf3ac28bd489262f007422","target":"graph","created_at":"2026-07-05T08:25:24Z","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/2405.20339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs), and concatenating visual tokens with text tokens to form a unified sequence input for LLMs. These methods demonstrate promising results on various vision-language tasks but are limited by the high computational effort due to the extended input sequence resulting from the involvement of visual tokens. In this paper, instead of input space alignment, we propose a novel parameter space alignment paradigm that repr","authors_text":"Feipeng Ma, Fengyun Rao, Guangting Wang, Hongwei Xue, Mike Zheng Shou, Shilin Yan, Siying Wu, Xiaoyan Sun, Yizhou Zhou, Yueyi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:59:47Z","title":"Visual Perception by Large Language Model's Weights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20339","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:ecf45a1fd7272997505d721612aa68bb4ac02a61548c933ec93f2dc12446f98e","target":"record","created_at":"2026-07-05T08:25:24Z","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":"af727b53dacc6123493dbf374fbd37fbaffd46a2297848bd4c426494624300fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:59:47Z","title_canon_sha256":"8b3baf24c9e092313f2c1621da6669b79ea110046d3255734d128ee840489f34"},"schema_version":"1.0","source":{"id":"2405.20339","kind":"arxiv","version":1}},"canonical_sha256":"77d59aa43aaefecbf4877e4ade7d96d307f87740ad0a448ff9f8f92513750c25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77d59aa43aaefecbf4877e4ade7d96d307f87740ad0a448ff9f8f92513750c25","first_computed_at":"2026-07-05T08:25:24.553704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:24.553704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKdo+/d3HHLirgf9wTTDOJKeS7gOP9mxNVupLct3+L8q0ZqkUHXmVHKtIeiDHBKVmfXX9ETYYCIPAQteq9O/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:24.554228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecf45a1fd7272997505d721612aa68bb4ac02a61548c933ec93f2dc12446f98e","sha256:9ff2ee25760031b6fc4ef6af038c2ceff1c5ad6e6adf3ac28bd489262f007422"],"state_sha256":"58cc893f75e4c30f1c3102637d00770ffbb327ad1186159e938aaf66c8ee611a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Vz91EghLoahZnqphaWXEMn7PISqWOjfANXh0qin/Z/TepnYtj2Ht8Eq0n4n6PPKynollCl+G4toj0+e/phCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:19:21.720362Z","bundle_sha256":"63e944877a88aba48040384dc8ecad8ef2ec62fc963f1674f1f44d02288ba0ef"}}