{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3KZ4SDGSCXD66UZDFKS4G2T5DU","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":"224b839bf86a31fa203d7d906c7d29ce68f3a0b360a3f0c1f3b49221904ae6f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T14:01:07Z","title_canon_sha256":"f033370b4da49e7888ea7d66c04cbd9168b1f03a125fad1227af3fde5820ff0d"},"schema_version":"1.0","source":{"id":"2607.12786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12786","created_at":"2026-07-15T01:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12786v1","created_at":"2026-07-15T01:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12786","created_at":"2026-07-15T01:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"3KZ4SDGSCXD6","created_at":"2026-07-15T01:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"3KZ4SDGSCXD66UZD","created_at":"2026-07-15T01:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"3KZ4SDGS","created_at":"2026-07-15T01:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:ec650b741a4ab15d1de5f7a6fdf6fb675d8e3eee18e1475f56d21c918f1d60b3","target":"graph","created_at":"2026-07-15T01:22:17Z","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/2607.12786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally consistent reasoning. We present CoRe, a unified framework for this problem. CoRe includes: (i) CoRe-20K, a large-scale triplet-based training set automatically constructed from structured visual metadata through a multi-expert collaborative pipeline, covering counting, depth, distance, and spatial relations; (ii) TriSR, a structured reward framework that jointly supervises attribute grounding, judgment alignment, and","authors_text":"Cong Wan, Lin Peng, SongLin Dong, Yihong Gong, Zeyu Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T14:01:07Z","title":"CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12786","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:b08d3fcbf591f0c40b71066dd8362d4ec32b819b253cca381ac3a86dfb30aa62","target":"record","created_at":"2026-07-15T01:22:17Z","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":"224b839bf86a31fa203d7d906c7d29ce68f3a0b360a3f0c1f3b49221904ae6f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T14:01:07Z","title_canon_sha256":"f033370b4da49e7888ea7d66c04cbd9168b1f03a125fad1227af3fde5820ff0d"},"schema_version":"1.0","source":{"id":"2607.12786","kind":"arxiv","version":1}},"canonical_sha256":"dab3c90cd215c7ef53232aa5c36a7d1d0f7464f94e531dcc1f2b5d2b879e3a0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dab3c90cd215c7ef53232aa5c36a7d1d0f7464f94e531dcc1f2b5d2b879e3a0f","first_computed_at":"2026-07-15T01:22:17.858391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:22:17.858391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xPpyeAb/H5h3DDLoaQZkoX0aXKO0jj6aOvSTLKcLMV2KdFd843OZhcxqZrWSIKacqZ8Ux19LKPGaSt8MkufFCw==","signature_status":"signed_v1","signed_at":"2026-07-15T01:22:17.859327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b08d3fcbf591f0c40b71066dd8362d4ec32b819b253cca381ac3a86dfb30aa62","sha256:ec650b741a4ab15d1de5f7a6fdf6fb675d8e3eee18e1475f56d21c918f1d60b3"],"state_sha256":"56056219b11ee6ba3a5169c40c36c7f351a46ee66e5dd61543372d3b5c498dfe"}