{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IOFN2F3PYZZXUUJJT2F3Z7YCX2","short_pith_number":"pith:IOFN2F3P","canonical_record":{"source":{"id":"2506.18943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T23:48:02Z","cross_cats_sorted":[],"title_canon_sha256":"3eb19365d05135372e7b4369b32e534f64108943d10677d187836446e3a2ba8c","abstract_canon_sha256":"b494771b004a313fa5e84ae43f97b2da1d067d5bcc5cd749f3b59e19ab0dc4f6"},"schema_version":"1.0"},"canonical_sha256":"438add176fc6737a51299e8bbcff02beb00a2662f28a8d885f499fde14a9a91b","source":{"kind":"arxiv","id":"2506.18943","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18943","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18943v1","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18943","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"IOFN2F3PYZZX","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"IOFN2F3PYZZXUUJJ","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"IOFN2F3P","created_at":"2026-07-05T11:26:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IOFN2F3PYZZXUUJJT2F3Z7YCX2","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T23:48:02Z","cross_cats_sorted":[],"title_canon_sha256":"3eb19365d05135372e7b4369b32e534f64108943d10677d187836446e3a2ba8c","abstract_canon_sha256":"b494771b004a313fa5e84ae43f97b2da1d067d5bcc5cd749f3b59e19ab0dc4f6"},"schema_version":"1.0"},"canonical_sha256":"438add176fc6737a51299e8bbcff02beb00a2662f28a8d885f499fde14a9a91b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:06.928440Z","signature_b64":"1YrtsG5oexEAiKsDGQ9BFyf4qDvld/a68gQ7V+MqXGNq5mRtf8ks0l4Zvq6gNTTPM8KZ/WmDMFd6DJowlpCkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"438add176fc6737a51299e8bbcff02beb00a2662f28a8d885f499fde14a9a91b","last_reissued_at":"2026-07-05T11:26:06.927845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:06.927845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18943","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":"2026-07-05T11:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8/eTRBXlg9k4lRnjHmikEWoBoY00JSC1IYkfoqay+ANIeXfCuDJozVVzrQwnGGZAv6/N8595Yd/v4Z11UQaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:28:30.217715Z"},"content_sha256":"6e0047605df92c06d5608b0c02e53fff7842616383445c7c1a13f5e0c0a1a4e0","schema_version":"1.0","event_id":"sha256:6e0047605df92c06d5608b0c02e53fff7842616383445c7c1a13f5e0c0a1a4e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IOFN2F3PYZZXUUJJT2F3Z7YCX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Kiruluta, Priscilla Burity","submitted_at":"2025-06-22T23:48:02Z","abstract_excerpt":"Vision-language models (VLMs) unify computer vision and natural language processing in a single architecture capable of interpreting and describing images. Most state-of-the-art systems rely on two computationally intensive components: convolutions in the vision encoder and quadratic self-attention for multimodal fusion. This work removes both by introducing a spectral dictionary token mixer, which represents each image patch or wordpiece as a sparse combination of learnable frequency atoms. Our 1.1B-parameter prototype, SDict-VLM, achieves BLEU-4 of 39.2, CIDEr of 127.5, and SPICE of 27.0 on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18943","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/2506.18943/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":"2026-07-05T11:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6MuXIZC1/Zr4BTsYIeDYd5NLEwYSH54+y9M1YcwvTsb/AcJm6XopLOgeuaElIq5yWNUykK/ebeixadSMLfJQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:28:30.218088Z"},"content_sha256":"eb0ad89fc98379892c28c8854579b17376ca08983726072e8016098a1ace9b9a","schema_version":"1.0","event_id":"sha256:eb0ad89fc98379892c28c8854579b17376ca08983726072e8016098a1ace9b9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2/bundle.json","state_url":"https://pith.science/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2/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":"2026-08-17T12:28:30Z","links":{"resolver":"https://pith.science/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2","bundle":"https://pith.science/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2/bundle.json","state":"https://pith.science/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOFN2F3PYZZXUUJJT2F3Z7YCX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IOFN2F3PYZZXUUJJT2F3Z7YCX2","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":"b494771b004a313fa5e84ae43f97b2da1d067d5bcc5cd749f3b59e19ab0dc4f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T23:48:02Z","title_canon_sha256":"3eb19365d05135372e7b4369b32e534f64108943d10677d187836446e3a2ba8c"},"schema_version":"1.0","source":{"id":"2506.18943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18943","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18943v1","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18943","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"IOFN2F3PYZZX","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"IOFN2F3PYZZXUUJJ","created_at":"2026-07-05T11:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"IOFN2F3P","created_at":"2026-07-05T11:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:eb0ad89fc98379892c28c8854579b17376ca08983726072e8016098a1ace9b9a","target":"graph","created_at":"2026-07-05T11:26:06Z","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/2506.18943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) unify computer vision and natural language processing in a single architecture capable of interpreting and describing images. Most state-of-the-art systems rely on two computationally intensive components: convolutions in the vision encoder and quadratic self-attention for multimodal fusion. This work removes both by introducing a spectral dictionary token mixer, which represents each image patch or wordpiece as a sparse combination of learnable frequency atoms. Our 1.1B-parameter prototype, SDict-VLM, achieves BLEU-4 of 39.2, CIDEr of 127.5, and SPICE of 27.0 on ","authors_text":"Andrew Kiruluta, Priscilla Burity","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T23:48:02Z","title":"From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18943","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":"sha256:6e0047605df92c06d5608b0c02e53fff7842616383445c7c1a13f5e0c0a1a4e0","target":"record","created_at":"2026-07-05T11:26:06Z","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":"b494771b004a313fa5e84ae43f97b2da1d067d5bcc5cd749f3b59e19ab0dc4f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-22T23:48:02Z","title_canon_sha256":"3eb19365d05135372e7b4369b32e534f64108943d10677d187836446e3a2ba8c"},"schema_version":"1.0","source":{"id":"2506.18943","kind":"arxiv","version":1}},"canonical_sha256":"438add176fc6737a51299e8bbcff02beb00a2662f28a8d885f499fde14a9a91b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"438add176fc6737a51299e8bbcff02beb00a2662f28a8d885f499fde14a9a91b","first_computed_at":"2026-07-05T11:26:06.927845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:06.927845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1YrtsG5oexEAiKsDGQ9BFyf4qDvld/a68gQ7V+MqXGNq5mRtf8ks0l4Zvq6gNTTPM8KZ/WmDMFd6DJowlpCkDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:06.928440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e0047605df92c06d5608b0c02e53fff7842616383445c7c1a13f5e0c0a1a4e0","sha256:eb0ad89fc98379892c28c8854579b17376ca08983726072e8016098a1ace9b9a"],"state_sha256":"64ed1fcb6996c96d0ecc3cab0e3238a7f8897826b9c6472fcb8bb51fed13009b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ut8ZjpA3GwlTQSnWhjirNehZJpuoPAkjS6T8ocDqBccdAKV7Sk8NEsYx152wupzRlcj1i4wiCaNsYfWdSt4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:28:30.220470Z","bundle_sha256":"0d027d25edb931640100b9fc41efeae8e48a650a6c63af8072d6e31fe9aaf661"}}