{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LX2ZLAUENEMKJO76JZAJGZTCEE","short_pith_number":"pith:LX2ZLAUE","canonical_record":{"source":{"id":"2605.00271","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T22:14:36Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5a62fa8feda0a0bd9674b6cbd3b19ced6f16d86b8afd15d99e7a1e3a41152ea0","abstract_canon_sha256":"0eb613baf49d2f00ea973a5b1a8fadf322172b6ecd3e808e9a27cc0f643b939d"},"schema_version":"1.0"},"canonical_sha256":"5df59582846918a4bbfe4e40936662212208c14917e55c71c788c76b0bd3985e","source":{"kind":"arxiv","id":"2605.00271","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00271","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00271v3","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00271","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"LX2ZLAUENEMK","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"LX2ZLAUENEMKJO76","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"LX2ZLAUE","created_at":"2026-07-02T01:17:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LX2ZLAUENEMKJO76JZAJGZTCEE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.00271","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T22:14:36Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"5a62fa8feda0a0bd9674b6cbd3b19ced6f16d86b8afd15d99e7a1e3a41152ea0","abstract_canon_sha256":"0eb613baf49d2f00ea973a5b1a8fadf322172b6ecd3e808e9a27cc0f643b939d"},"schema_version":"1.0"},"canonical_sha256":"5df59582846918a4bbfe4e40936662212208c14917e55c71c788c76b0bd3985e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:31.890193Z","signature_b64":"9svFdvZzfZjSzEvtT7wizm25Nnly9oF3OT4krufPSx2m7/4MOwj8S3Tj/axencoAp0y7PgMwP8DJEUKADpnQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5df59582846918a4bbfe4e40936662212208c14917e55c71c788c76b0bd3985e","last_reissued_at":"2026-07-02T01:17:31.889775Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:31.889775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.00271","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsX9fOn1qwOeR9s5qWptoC9CrdjQPYZCnZ/boF252t8NY2Rih3XuEVdL0d6vfFiQeLHM/0VDg/X9IFDhQitCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:20:10.016309Z"},"content_sha256":"a194218c5fd1682c6b96e6821904e9fc2ba283f044df9f062602e512ed6c892b","schema_version":"1.0","event_id":"sha256:a194218c5fd1682c6b96e6821904e9fc2ba283f044df9f062602e512ed6c892b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LX2ZLAUENEMKJO76JZAJGZTCEE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Event data can be projected into pretrained RGB latent spaces using low-rank adaptation to enable zero-shot application of frozen image decoders to raw event streams.","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"David B. Lindell, Jonathan Kelly, Vincenzo Polizzi","submitted_at":"2026-04-30T22:14:36Z","abstract_excerpt":"Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a cross-modal framework that learns an RGB- and Event-Aligned Latent Manifold by projecting event representations into the pretrained latent space of RGB foundation models. Instead of task-specific training, we leverage low-ran"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That low-rank adaptation of frozen RGB backbones is sufficient to bridge the modality gap and unlock geometric and semantic priors for asynchronous event streams without task-specific training or substantial performance loss.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"REALM aligns event streams with RGB ViT latent spaces via LoRA, enabling zero-shot transfer of image-trained linear heads and complex decoders like MASt3R to raw event data with reported SOTA wide-baseline matching performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Event data can be projected into pretrained RGB latent spaces using low-rank adaptation to enable zero-shot application of frozen image decoders to raw event streams.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0f7c09120682ceb401fcaf098ab4afc60e92e7e2d5ca9cfd62a09bd48ecec67e"},"source":{"id":"2605.00271","kind":"arxiv","version":3},"verdict":{"id":"1cf8bf16-cda0-420f-8f8e-dabfc260067b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T19:43:34.168370Z","strongest_claim":"REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures.","one_line_summary":"REALM aligns event streams with RGB ViT latent spaces via LoRA, enabling zero-shot transfer of image-trained linear heads and complex decoders like MASt3R to raw event data with reported SOTA wide-baseline matching performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That low-rank adaptation of frozen RGB backbones is sufficient to bridge the modality gap and unlock geometric and semantic priors for asynchronous event streams without task-specific training or substantial performance loss.","pith_extraction_headline":"Event data can be projected into pretrained RGB latent spaces using low-rank adaptation to enable zero-shot application of frozen image decoders to raw event streams."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00271/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T20:35:33.042917Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:22:28.742328Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"eaa1d9ddc968446da28f0e62239da7fcb3a4de86f6f94078a5d322b8217e5c96"},"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":"1cf8bf16-cda0-420f-8f8e-dabfc260067b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-02T01:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DWygxICFnMVm9FxIupAbYQERDh8ti1mznI/yEt2WtdHc3sS1XB/TsQ8sx7x599zgJYR2GdtNqMB2pSFqJt6OBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T11:20:10.017074Z"},"content_sha256":"712aea5de5cded8001dcc77505d09aa96fb99c63c8c8db7f0945f8e3884f0aa4","schema_version":"1.0","event_id":"sha256:712aea5de5cded8001dcc77505d09aa96fb99c63c8c8db7f0945f8e3884f0aa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LX2ZLAUENEMKJO76JZAJGZTCEE/bundle.json","state_url":"https://pith.science/pith/LX2ZLAUENEMKJO76JZAJGZTCEE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LX2ZLAUENEMKJO76JZAJGZTCEE/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":"2026-08-22T11:20:10Z","links":{"resolver":"https://pith.science/pith/LX2ZLAUENEMKJO76JZAJGZTCEE","bundle":"https://pith.science/pith/LX2ZLAUENEMKJO76JZAJGZTCEE/bundle.json","state":"https://pith.science/pith/LX2ZLAUENEMKJO76JZAJGZTCEE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LX2ZLAUENEMKJO76JZAJGZTCEE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LX2ZLAUENEMKJO76JZAJGZTCEE","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":"0eb613baf49d2f00ea973a5b1a8fadf322172b6ecd3e808e9a27cc0f643b939d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T22:14:36Z","title_canon_sha256":"5a62fa8feda0a0bd9674b6cbd3b19ced6f16d86b8afd15d99e7a1e3a41152ea0"},"schema_version":"1.0","source":{"id":"2605.00271","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00271","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00271v3","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00271","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"LX2ZLAUENEMK","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"LX2ZLAUENEMKJO76","created_at":"2026-07-02T01:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"LX2ZLAUE","created_at":"2026-07-02T01:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:712aea5de5cded8001dcc77505d09aa96fb99c63c8c8db7f0945f8e3884f0aa4","target":"graph","created_at":"2026-07-02T01:17:31Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That low-rank adaptation of frozen RGB backbones is sufficient to bridge the modality gap and unlock geometric and semantic priors for asynchronous event streams without task-specific training or substantial performance loss."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"REALM aligns event streams with RGB ViT latent spaces via LoRA, enabling zero-shot transfer of image-trained linear heads and complex decoders like MASt3R to raw event data with reported SOTA wide-baseline matching performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Event data can be projected into pretrained RGB latent spaces using low-rank adaptation to enable zero-shot application of frozen image decoders to raw event streams."}],"snapshot_sha256":"0f7c09120682ceb401fcaf098ab4afc60e92e7e2d5ca9cfd62a09bd48ecec67e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T20:35:33.042917Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:22:28.742328Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.00271/integrity.json","findings":[],"snapshot_sha256":"eaa1d9ddc968446da28f0e62239da7fcb3a4de86f6f94078a5d322b8217e5c96","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Event cameras provide several unique advantages over standard frame-based sensors, including high temporal resolution, low latency, and robustness to extreme lighting. However, existing learning-based approaches for event processing are typically confined to narrow, task-specific silos and lack the ability to generalize across modalities. We address this gap with REALM, a cross-modal framework that learns an RGB- and Event-Aligned Latent Manifold by projecting event representations into the pretrained latent space of RGB foundation models. Instead of task-specific training, we leverage low-ran","authors_text":"David B. Lindell, Jonathan Kelly, Vincenzo Polizzi","cross_cats":["cs.AI","cs.RO"],"headline":"Event data can be projected into pretrained RGB latent spaces using low-rank adaptation to enable zero-shot application of frozen image decoders to raw event streams.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T22:14:36Z","title":"REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.00271","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-09T19:43:34.168370Z","id":"1cf8bf16-cda0-420f-8f8e-dabfc260067b","model_set":{"reader":"grok-4.3"},"one_line_summary":"REALM aligns event streams with RGB ViT latent spaces via LoRA, enabling zero-shot transfer of image-trained linear heads and complex decoders like MASt3R to raw event data with reported SOTA wide-baseline matching performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Event data can be projected into pretrained RGB latent spaces using low-rank adaptation to enable zero-shot application of frozen image decoders to raw event streams.","strongest_claim":"REALM enables the direct, zero-shot application of complex, frozen image-trained decoders, such as MASt3R, to raw event data. We demonstrate state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized architectures.","weakest_assumption":"That low-rank adaptation of frozen RGB backbones is sufficient to bridge the modality gap and unlock geometric and semantic priors for asynchronous event streams without task-specific training or substantial performance loss."}},"verdict_id":"1cf8bf16-cda0-420f-8f8e-dabfc260067b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a194218c5fd1682c6b96e6821904e9fc2ba283f044df9f062602e512ed6c892b","target":"record","created_at":"2026-07-02T01:17:31Z","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":"0eb613baf49d2f00ea973a5b1a8fadf322172b6ecd3e808e9a27cc0f643b939d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T22:14:36Z","title_canon_sha256":"5a62fa8feda0a0bd9674b6cbd3b19ced6f16d86b8afd15d99e7a1e3a41152ea0"},"schema_version":"1.0","source":{"id":"2605.00271","kind":"arxiv","version":3}},"canonical_sha256":"5df59582846918a4bbfe4e40936662212208c14917e55c71c788c76b0bd3985e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5df59582846918a4bbfe4e40936662212208c14917e55c71c788c76b0bd3985e","first_computed_at":"2026-07-02T01:17:31.889775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:31.889775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9svFdvZzfZjSzEvtT7wizm25Nnly9oF3OT4krufPSx2m7/4MOwj8S3Tj/axencoAp0y7PgMwP8DJEUKADpnQAA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:31.890193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.00271","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a194218c5fd1682c6b96e6821904e9fc2ba283f044df9f062602e512ed6c892b","sha256:712aea5de5cded8001dcc77505d09aa96fb99c63c8c8db7f0945f8e3884f0aa4"],"state_sha256":"e8bc715df662852a9e69f1cbec631efcb7b1b69850f80add68975bea1c5e5054"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7mcNMLMNdPTKIEOIV40XmmfvVwVNIgFuQktUAAadGQ+Ybkahw3Yu18ITQRuS+IAqeesdPh5JKqyONU9713x+AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T11:20:10.021407Z","bundle_sha256":"3f59a11af467f02257d3d6dc43631fb193505fdcbfdd5805cb60b26a586643ac"}}