{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:55MCT7OLPKDFII4WLQLLUVOZEI","short_pith_number":"pith:55MCT7OL","canonical_record":{"source":{"id":"2608.02109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"0f415df6bf7909e852fdfd11b757bd4a66b3150c88d10d14e25345c15d6e60aa","abstract_canon_sha256":"009bb8e02be93e1f9b1cc4af315dd4bef48ca2d9625982f671901de854c3d4a1"},"schema_version":"1.0"},"canonical_sha256":"ef5829fdcb7a865423965c16ba55d922339ae2a7c2a3cf2442c83dae3d778f04","source":{"kind":"arxiv","id":"2608.02109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02109","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02109v1","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02109","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"55MCT7OLPKDF","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"55MCT7OLPKDFII4W","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"55MCT7OL","created_at":"2026-08-04T02:10:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:55MCT7OLPKDFII4WLQLLUVOZEI","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"0f415df6bf7909e852fdfd11b757bd4a66b3150c88d10d14e25345c15d6e60aa","abstract_canon_sha256":"009bb8e02be93e1f9b1cc4af315dd4bef48ca2d9625982f671901de854c3d4a1"},"schema_version":"1.0"},"canonical_sha256":"ef5829fdcb7a865423965c16ba55d922339ae2a7c2a3cf2442c83dae3d778f04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:52.136570Z","signature_b64":"1DFt8mwD4N4qTCpePL9rfopjkvg0ndbKiieFzTNdEE4ifQIpyrXtv4SKIPzN045o+xJ9DU10dRXfhhQCGiW4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef5829fdcb7a865423965c16ba55d922339ae2a7c2a3cf2442c83dae3d778f04","last_reissued_at":"2026-08-04T02:10:52.135017Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:52.135017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02109","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":"2026-08-04T02:10:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wN47k8qBWk4VTB8vnuXrPW7AQFpqTGdUdlGXqiHiXdOdgM4Kn1JQtkA52na6VqNYS3TKls5PhTrODagn9swDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:48:40.680878Z"},"content_sha256":"2b3756ddfa64fbbdf48f11a0d78f62cdd3f753df8e19f290af82c360eac3fb35","schema_version":"1.0","event_id":"sha256:2b3756ddfa64fbbdf48f11a0d78f62cdd3f753df8e19f290af82c360eac3fb35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:55MCT7OLPKDFII4WLQLLUVOZEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongxing Mao, Tianyu Liang, Xiangxi Zheng, Yilin Wang","submitted_at":"2026-08-03T12:08:56Z","abstract_excerpt":"Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens into far fewer visual tokens. However, since the ViT is pretrained predominantly on natural images, it captures visual attributes (glyphs, font sizes, layout) rather than linguistic semantics, causing rendered-image representations to diverge from native-text representations. We term this cross-path inconsistency and show, via rendering perturbation experiments, that it is a critical yet overlooked bottleneck of VTC. We propose SPIRAL (Self-improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02109","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/2608.02109/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":"2026-08-04T02:10:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S6frf35A0i/vpuxB3UA1Rl2Y30fRd1DumLcaxcWNQLPEs7vgmdP/jQeHDygqJskmxOfHFPyRfMiAx/GJaKSiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:48:40.681377Z"},"content_sha256":"749d29e5b1c96bafc179e9962591cd1233cccb0eb6617f32cc16f8516903ee79","schema_version":"1.0","event_id":"sha256:749d29e5b1c96bafc179e9962591cd1233cccb0eb6617f32cc16f8516903ee79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55MCT7OLPKDFII4WLQLLUVOZEI/bundle.json","state_url":"https://pith.science/pith/55MCT7OLPKDFII4WLQLLUVOZEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55MCT7OLPKDFII4WLQLLUVOZEI/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":"2026-08-15T22:48:40Z","links":{"resolver":"https://pith.science/pith/55MCT7OLPKDFII4WLQLLUVOZEI","bundle":"https://pith.science/pith/55MCT7OLPKDFII4WLQLLUVOZEI/bundle.json","state":"https://pith.science/pith/55MCT7OLPKDFII4WLQLLUVOZEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55MCT7OLPKDFII4WLQLLUVOZEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:55MCT7OLPKDFII4WLQLLUVOZEI","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":"009bb8e02be93e1f9b1cc4af315dd4bef48ca2d9625982f671901de854c3d4a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:08:56Z","title_canon_sha256":"0f415df6bf7909e852fdfd11b757bd4a66b3150c88d10d14e25345c15d6e60aa"},"schema_version":"1.0","source":{"id":"2608.02109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02109","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02109v1","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02109","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"pith_short_12","alias_value":"55MCT7OLPKDF","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"pith_short_16","alias_value":"55MCT7OLPKDFII4W","created_at":"2026-08-04T02:10:52Z"},{"alias_kind":"pith_short_8","alias_value":"55MCT7OL","created_at":"2026-08-04T02:10:52Z"}],"graph_snapshots":[{"event_id":"sha256:749d29e5b1c96bafc179e9962591cd1233cccb0eb6617f32cc16f8516903ee79","target":"graph","created_at":"2026-08-04T02:10:52Z","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/2608.02109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens into far fewer visual tokens. However, since the ViT is pretrained predominantly on natural images, it captures visual attributes (glyphs, font sizes, layout) rather than linguistic semantics, causing rendered-image representations to diverge from native-text representations. We term this cross-path inconsistency and show, via rendering perturbation experiments, that it is a critical yet overlooked bottleneck of VTC. We propose SPIRAL (Self-improv","authors_text":"Dongxing Mao, Tianyu Liang, Xiangxi Zheng, Yilin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:08:56Z","title":"Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02109","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":"sha256:2b3756ddfa64fbbdf48f11a0d78f62cdd3f753df8e19f290af82c360eac3fb35","target":"record","created_at":"2026-08-04T02:10:52Z","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":"009bb8e02be93e1f9b1cc4af315dd4bef48ca2d9625982f671901de854c3d4a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:08:56Z","title_canon_sha256":"0f415df6bf7909e852fdfd11b757bd4a66b3150c88d10d14e25345c15d6e60aa"},"schema_version":"1.0","source":{"id":"2608.02109","kind":"arxiv","version":1}},"canonical_sha256":"ef5829fdcb7a865423965c16ba55d922339ae2a7c2a3cf2442c83dae3d778f04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef5829fdcb7a865423965c16ba55d922339ae2a7c2a3cf2442c83dae3d778f04","first_computed_at":"2026-08-04T02:10:52.135017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:10:52.135017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DFt8mwD4N4qTCpePL9rfopjkvg0ndbKiieFzTNdEE4ifQIpyrXtv4SKIPzN045o+xJ9DU10dRXfhhQCGiW4AQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:10:52.136570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b3756ddfa64fbbdf48f11a0d78f62cdd3f753df8e19f290af82c360eac3fb35","sha256:749d29e5b1c96bafc179e9962591cd1233cccb0eb6617f32cc16f8516903ee79"],"state_sha256":"0e14dc1faaca6c17566aba54cc6a2cfe070c7afa261cc7be004be2b944edf63e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rzIm6obsnXIvVszxHfNciPB+rwqEXOTb3xQTUj/q4sDH56liyePwlxqKIcgyF8OcT/vJ7pXt5htopTSNFr0zCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:48:40.685704Z","bundle_sha256":"c115c1145bd6444939bf25bdd3b0d55cf532a179946303f0a0b675fb6272aa18"}}