{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4ZAXKMRQEX3UBNINNER7WWVLJ3","short_pith_number":"pith:4ZAXKMRQ","canonical_record":{"source":{"id":"2605.15300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T18:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"7e175ea771a9c586b737a13198eb361d0be7b9493deaa788087f9f5b5b77380d","abstract_canon_sha256":"017f88a96ca487ffa8bf0917da4183da73b1aac9cfb192fa146f4ce820b65e5e"},"schema_version":"1.0"},"canonical_sha256":"e64175323025f740b50d6923fb5aab4ee0584fd4493f7cdf02af0e3e2a6b087d","source":{"kind":"arxiv","id":"2605.15300","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15300","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15300v1","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15300","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"4ZAXKMRQEX3U","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"4ZAXKMRQEX3UBNIN","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"4ZAXKMRQ","created_at":"2026-05-20T00:00:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4ZAXKMRQEX3UBNINNER7WWVLJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T18:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"7e175ea771a9c586b737a13198eb361d0be7b9493deaa788087f9f5b5b77380d","abstract_canon_sha256":"017f88a96ca487ffa8bf0917da4183da73b1aac9cfb192fa146f4ce820b65e5e"},"schema_version":"1.0"},"canonical_sha256":"e64175323025f740b50d6923fb5aab4ee0584fd4493f7cdf02af0e3e2a6b087d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:51.496929Z","signature_b64":"B5nHjq/XcyaAVpMgKlSxaBuoiQra+kHtJzP1/uCK4G2ETY1YoXiWcLFXuJJid40HMo8XMg7kmxJWznc4M9zBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e64175323025f740b50d6923fb5aab4ee0584fd4493f7cdf02af0e3e2a6b087d","last_reissued_at":"2026-05-20T00:00:51.496070Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:51.496070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15300","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":"2026-05-20T00:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTM6y8QOK2KsYrmzJ/61u03DZ3nJomh1J9Yc6BIzv5o8aOKrDetN5PYxExFT/r6Ds6ZmJwcW7PIX+HBwjCgOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T06:58:18.399648Z"},"content_sha256":"a387ae7d50f75fb9b6fa44229757503f565beaa4d3cf38892cf109412530025d","schema_version":"1.0","event_id":"sha256:a387ae7d50f75fb9b6fa44229757503f565beaa4d3cf38892cf109412530025d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4ZAXKMRQEX3UBNINNER7WWVLJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Pre-Alignment for VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Deep Pre-Alignment replaces the ViT encoder with a small VLM perceiver to align visual features deeply with the LLM's text space.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Jun Song, Kaidong Zhang, Kechen Fang, Tianyu Yu, Yicheng Zhang, Yuan Yao, Zihao Wan","submitted_at":"2026-05-14T18:14:15Z","abstract_excerpt":"Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffers from an alignment challenge: visual features remain distant from the text space in the initial layers of the LLM, forcing the model to waste critical depth~\\cite{zhang-etal-2024-investigating,artzy-schwartz-2024-attend} on superficial modality alignment rather than deep understanding and complex reasoning. In this work, we propose Deep Pre-Alignment (DPA), a novel architecture that replaces the standard ViT encoder"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale; by offloading alignment to the perceiver, DPA achieves a 32.9% reduction in language capability forgetting over 3 text benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That feeding the LLM with features from a small VLM perceiver (rather than a standard ViT plus projector) produces sufficiently deep pre-alignment so that the LLM's initial layers no longer perform superficial modality matching, as stated in the motivation citing prior alignment analyses.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Deep Pre-Alignment replaces the ViT encoder with a small VLM perceiver to align visual features deeply with the LLM's text space.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b77465daad9f712bb5b16d8fb34950afa971880d577f02f2d36ec11cbfa92020"},"source":{"id":"2605.15300","kind":"arxiv","version":1},"verdict":{"id":"43417420-73e3-4d11-bb77-c8d5f77883a7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:22:11.479040Z","strongest_claim":"On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale; by offloading alignment to the perceiver, DPA achieves a 32.9% reduction in language capability forgetting over 3 text benchmarks.","one_line_summary":"Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That feeding the LLM with features from a small VLM perceiver (rather than a standard ViT plus projector) produces sufficiently deep pre-alignment so that the LLM's initial layers no longer perform superficial modality matching, as stated in the motivation citing prior alignment analyses.","pith_extraction_headline":"Deep Pre-Alignment replaces the ViT encoder with a small VLM perceiver to align visual features deeply with the LLM's text space."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15300/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:36:04.197308Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.354990Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:41:54.229768Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.780645Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ad96a4f6fbe2a125ba7e09d379bc87aa1ff82d87e1bc43cc05c15a79938b428c"},"references":{"count":172,"sample":[{"doi":"","year":2023,"title":"International conference on machine learning , pages=","work_id":"99465f33-3e19-4fa9-8062-a629551b3315","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Flamingo: a visual language model for few-shot learning , author=. NeurIPS , volume=","work_id":"51b120de-c683-4609-8bae-7b6f4e485c79","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Changpinyo, Soravit and Sharma, Piyush and Ding, Nan and Soricut, Radu , booktitle=","work_id":"66d362ea-4f8a-4ef5-aceb-7bf05d542c72","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Byeon, Minwoo and Park, Beomhee and Kim, Haecheon and Lee, Sungjun and Baek, Woonhyuk and Kim, Saehoon , year =","work_id":"a7db0b62-446b-4fb5-b3d9-c23305eee65a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Schuhmann, Christoph and Beaumont, Romain and Vencu, Richard and Gordon, Cade and Wightman, Ross and Cherti, Mehdi and Coombes, Theo and Katta, Aarush and Mullis, Clayton and Wortsman, Mitchell and ot","work_id":"c077101d-93a9-47bb-87af-d51c03cde237","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":172,"snapshot_sha256":"07a5382c0ba6ff713333afd313871102121e1770c29a22bcf2dc95c0bc5acc4e","internal_anchors":29},"formal_canon":{"evidence_count":2,"snapshot_sha256":"beb7c8506bdc7246677a083d000e68d4d48be25cf3c0b8111bff86024a81ae54"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"43417420-73e3-4d11-bb77-c8d5f77883a7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hhSBqilPtp3fRpWMdNqZpZETeE+sihz8LTWN/RlL+Ymy+yTuatfaPn+gXxG7mIi5ytZLOPjFqLoJviOJeGjTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T06:58:18.400259Z"},"content_sha256":"adc6ec206a6b4129fd8285ae434cb5f328020762e8294620e24cce03fd1edd07","schema_version":"1.0","event_id":"sha256:adc6ec206a6b4129fd8285ae434cb5f328020762e8294620e24cce03fd1edd07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3/bundle.json","state_url":"https://pith.science/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3/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":"2026-05-20T06:58:18Z","links":{"resolver":"https://pith.science/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3","bundle":"https://pith.science/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3/bundle.json","state":"https://pith.science/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZAXKMRQEX3UBNINNER7WWVLJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ZAXKMRQEX3UBNINNER7WWVLJ3","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":"017f88a96ca487ffa8bf0917da4183da73b1aac9cfb192fa146f4ce820b65e5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T18:14:15Z","title_canon_sha256":"7e175ea771a9c586b737a13198eb361d0be7b9493deaa788087f9f5b5b77380d"},"schema_version":"1.0","source":{"id":"2605.15300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15300","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15300v1","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15300","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"4ZAXKMRQEX3U","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"4ZAXKMRQEX3UBNIN","created_at":"2026-05-20T00:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"4ZAXKMRQ","created_at":"2026-05-20T00:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:adc6ec206a6b4129fd8285ae434cb5f328020762e8294620e24cce03fd1edd07","target":"graph","created_at":"2026-05-20T00:00:51Z","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":"On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale; by offloading alignment to the perceiver, DPA achieves a 32.9% reduction in language capability forgetting over 3 text benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That feeding the LLM with features from a small VLM perceiver (rather than a standard ViT plus projector) produces sufficiently deep pre-alignment so that the LLM's initial layers no longer perform superficial modality matching, as stated in the motivation citing prior alignment analyses."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Deep Pre-Alignment replaces the ViT encoder with a small VLM perceiver to align visual features deeply with the LLM's text space."}],"snapshot_sha256":"b77465daad9f712bb5b16d8fb34950afa971880d577f02f2d36ec11cbfa92020"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"beb7c8506bdc7246677a083d000e68d4d48be25cf3c0b8111bff86024a81ae54"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:36:04.197308Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.354990Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:41:54.229768Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.780645Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15300/integrity.json","findings":[],"snapshot_sha256":"ad96a4f6fbe2a125ba7e09d379bc87aa1ff82d87e1bc43cc05c15a79938b428c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffers from an alignment challenge: visual features remain distant from the text space in the initial layers of the LLM, forcing the model to waste critical depth~\\cite{zhang-etal-2024-investigating,artzy-schwartz-2024-attend} on superficial modality alignment rather than deep understanding and complex reasoning. In this work, we propose Deep Pre-Alignment (DPA), a novel architecture that replaces the standard ViT encoder","authors_text":"Bo Zheng, Jun Song, Kaidong Zhang, Kechen Fang, Tianyu Yu, Yicheng Zhang, Yuan Yao, Zihao Wan","cross_cats":[],"headline":"Deep Pre-Alignment replaces the ViT encoder with a small VLM perceiver to align visual features deeply with the LLM's text space.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T18:14:15Z","title":"Deep Pre-Alignment for VLMs"},"references":{"count":172,"internal_anchors":29,"resolved_work":172,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"International conference on machine learning , pages=","work_id":"99465f33-3e19-4fa9-8062-a629551b3315","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Flamingo: a visual language model for few-shot learning , author=. NeurIPS , volume=","work_id":"51b120de-c683-4609-8bae-7b6f4e485c79","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Changpinyo, Soravit and Sharma, Piyush and Ding, Nan and Soricut, Radu , booktitle=","work_id":"66d362ea-4f8a-4ef5-aceb-7bf05d542c72","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Byeon, Minwoo and Park, Beomhee and Kim, Haecheon and Lee, Sungjun and Baek, Woonhyuk and Kim, Saehoon , year =","work_id":"a7db0b62-446b-4fb5-b3d9-c23305eee65a","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Schuhmann, Christoph and Beaumont, Romain and Vencu, Richard and Gordon, Cade and Wightman, Ross and Cherti, Mehdi and Coombes, Theo and Katta, Aarush and Mullis, Clayton and Wortsman, Mitchell and ot","work_id":"c077101d-93a9-47bb-87af-d51c03cde237","year":null}],"snapshot_sha256":"07a5382c0ba6ff713333afd313871102121e1770c29a22bcf2dc95c0bc5acc4e"},"source":{"id":"2605.15300","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T16:22:11.479040Z","id":"43417420-73e3-4d11-bb77-c8d5f77883a7","model_set":{"reader":"grok-4.3"},"one_line_summary":"Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Deep Pre-Alignment replaces the ViT encoder with a small VLM perceiver to align visual features deeply with the LLM's text space.","strongest_claim":"On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale; by offloading alignment to the perceiver, DPA achieves a 32.9% reduction in language capability forgetting over 3 text benchmarks.","weakest_assumption":"That feeding the LLM with features from a small VLM perceiver (rather than a standard ViT plus projector) produces sufficiently deep pre-alignment so that the LLM's initial layers no longer perform superficial modality matching, as stated in the motivation citing prior alignment analyses."}},"verdict_id":"43417420-73e3-4d11-bb77-c8d5f77883a7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a387ae7d50f75fb9b6fa44229757503f565beaa4d3cf38892cf109412530025d","target":"record","created_at":"2026-05-20T00:00:51Z","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":"017f88a96ca487ffa8bf0917da4183da73b1aac9cfb192fa146f4ce820b65e5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T18:14:15Z","title_canon_sha256":"7e175ea771a9c586b737a13198eb361d0be7b9493deaa788087f9f5b5b77380d"},"schema_version":"1.0","source":{"id":"2605.15300","kind":"arxiv","version":1}},"canonical_sha256":"e64175323025f740b50d6923fb5aab4ee0584fd4493f7cdf02af0e3e2a6b087d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e64175323025f740b50d6923fb5aab4ee0584fd4493f7cdf02af0e3e2a6b087d","first_computed_at":"2026-05-20T00:00:51.496070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:51.496070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B5nHjq/XcyaAVpMgKlSxaBuoiQra+kHtJzP1/uCK4G2ETY1YoXiWcLFXuJJid40HMo8XMg7kmxJWznc4M9zBDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:51.496929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a387ae7d50f75fb9b6fa44229757503f565beaa4d3cf38892cf109412530025d","sha256:adc6ec206a6b4129fd8285ae434cb5f328020762e8294620e24cce03fd1edd07"],"state_sha256":"bb6c581304020fbb792cae3409ab4a66efed54c735aec1071b5fbb804e1a4f5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwkcMk2B38Y8/sV9vQliTjfPP9bbfyfD9AEasfbms08ApT/22i0JmxAqoh2rMTBDPlbfpbynedG0LKW5FIhzCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T06:58:18.404282Z","bundle_sha256":"28e01eae4b78e783ac35bc401658b76873610b85e8995b0b4a7a2788dae2a3e1"}}