{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NHHHA7W6UPKQIC2BQI652UU54D","short_pith_number":"pith:NHHHA7W6","canonical_record":{"source":{"id":"2605.26038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:05:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d2d1aee5c3fc3d91f62283d717434144e25d2ee6dfb677e295414a66523d9c4","abstract_canon_sha256":"28b981f12a6c6ba72d38fecf5581dcf53200a1b480894389270481bf950da94d"},"schema_version":"1.0"},"canonical_sha256":"69ce707edea3d5040b41823ddd529de0ce835cf6e8b4e1815116313738989d98","source":{"kind":"arxiv","id":"2605.26038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26038","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26038v1","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26038","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"NHHHA7W6UPKQ","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"NHHHA7W6UPKQIC2B","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"NHHHA7W6","created_at":"2026-05-26T02:05:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NHHHA7W6UPKQIC2BQI652UU54D","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:05:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d2d1aee5c3fc3d91f62283d717434144e25d2ee6dfb677e295414a66523d9c4","abstract_canon_sha256":"28b981f12a6c6ba72d38fecf5581dcf53200a1b480894389270481bf950da94d"},"schema_version":"1.0"},"canonical_sha256":"69ce707edea3d5040b41823ddd529de0ce835cf6e8b4e1815116313738989d98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:24.491189Z","signature_b64":"3M7lkPJGH5wGJkeoWDhOEk62+Y2VrBXbS+WHzTuVXaNHyxTSKqVjm0k2ATck6KCpYBp92Rfa31hnKrv/G9bLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69ce707edea3d5040b41823ddd529de0ce835cf6e8b4e1815116313738989d98","last_reissued_at":"2026-05-26T02:05:24.490395Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:24.490395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26038","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":"2026-05-26T02:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+6bGEoOnUMLmiQiEDPgp8HtPyjx4MdiWwuyxyfUDkpXTh9H4AYRrjg13ZlrVdgujWTMxlzuDtdAF60fY6yJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:00:15.909938Z"},"content_sha256":"68bdf63766f41a66027e2e7bca696d702ac60faada8925791146e90a0b6dc016","schema_version":"1.0","event_id":"sha256:68bdf63766f41a66027e2e7bca696d702ac60faada8925791146e90a0b6dc016"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NHHHA7W6UPKQIC2BQI652UU54D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anqi Li, Jianze Li, Kai Liu, Xinrui Shi, Yulun Zhang, Ziqing Zhang","submitted_at":"2026-05-25T17:05:52Z","abstract_excerpt":"Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objects, attributes, and relations must be jointly grounded and resolved through multi-step inference. Such capability is critical for real-world applications where models must reliably interpret cluttered environments. Yet existing training signals provide no explicit grounding between reasoning steps and the underlying visual entities and relations, leaving lightweight models free to generate fluent but visually unanchored reasoning chains. To addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26038","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/2605.26038/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":"2026-05-26T02:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HVCwhs3rMOB5/VDyaXxy8MzggRAEWr6Kzxj1VLoTVssmV3calridHbi91gE1hihY1BovpGltKcWYHUkS+Y/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:00:15.910748Z"},"content_sha256":"986462251c75a156af555803a96df7527277cba59c0ae3f56d60ec72071e689c","schema_version":"1.0","event_id":"sha256:986462251c75a156af555803a96df7527277cba59c0ae3f56d60ec72071e689c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHHHA7W6UPKQIC2BQI652UU54D/bundle.json","state_url":"https://pith.science/pith/NHHHA7W6UPKQIC2BQI652UU54D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHHHA7W6UPKQIC2BQI652UU54D/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":"2026-06-05T23:00:15Z","links":{"resolver":"https://pith.science/pith/NHHHA7W6UPKQIC2BQI652UU54D","bundle":"https://pith.science/pith/NHHHA7W6UPKQIC2BQI652UU54D/bundle.json","state":"https://pith.science/pith/NHHHA7W6UPKQIC2BQI652UU54D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHHHA7W6UPKQIC2BQI652UU54D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NHHHA7W6UPKQIC2BQI652UU54D","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":"28b981f12a6c6ba72d38fecf5581dcf53200a1b480894389270481bf950da94d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:05:52Z","title_canon_sha256":"4d2d1aee5c3fc3d91f62283d717434144e25d2ee6dfb677e295414a66523d9c4"},"schema_version":"1.0","source":{"id":"2605.26038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26038","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26038v1","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26038","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"NHHHA7W6UPKQ","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"NHHHA7W6UPKQIC2B","created_at":"2026-05-26T02:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"NHHHA7W6","created_at":"2026-05-26T02:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:986462251c75a156af555803a96df7527277cba59c0ae3f56d60ec72071e689c","target":"graph","created_at":"2026-05-26T02:05:24Z","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/2605.26038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objects, attributes, and relations must be jointly grounded and resolved through multi-step inference. Such capability is critical for real-world applications where models must reliably interpret cluttered environments. Yet existing training signals provide no explicit grounding between reasoning steps and the underlying visual entities and relations, leaving lightweight models free to generate fluent but visually unanchored reasoning chains. To addre","authors_text":"Anqi Li, Jianze Li, Kai Liu, Xinrui Shi, Yulun Zhang, Ziqing Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:05:52Z","title":"DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26038","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":"sha256:68bdf63766f41a66027e2e7bca696d702ac60faada8925791146e90a0b6dc016","target":"record","created_at":"2026-05-26T02:05:24Z","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":"28b981f12a6c6ba72d38fecf5581dcf53200a1b480894389270481bf950da94d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:05:52Z","title_canon_sha256":"4d2d1aee5c3fc3d91f62283d717434144e25d2ee6dfb677e295414a66523d9c4"},"schema_version":"1.0","source":{"id":"2605.26038","kind":"arxiv","version":1}},"canonical_sha256":"69ce707edea3d5040b41823ddd529de0ce835cf6e8b4e1815116313738989d98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69ce707edea3d5040b41823ddd529de0ce835cf6e8b4e1815116313738989d98","first_computed_at":"2026-05-26T02:05:24.490395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:24.490395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3M7lkPJGH5wGJkeoWDhOEk62+Y2VrBXbS+WHzTuVXaNHyxTSKqVjm0k2ATck6KCpYBp92Rfa31hnKrv/G9bLBg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:24.491189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68bdf63766f41a66027e2e7bca696d702ac60faada8925791146e90a0b6dc016","sha256:986462251c75a156af555803a96df7527277cba59c0ae3f56d60ec72071e689c"],"state_sha256":"8f1c694ac88a74e1bc1cb4c0e5922fb3397b36bfe895884b90cb6cec65812c98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHjQ1QPDlwZlWDtDM4P7Dnw/ehl828HriDyX7IbqOYF+V77wWZmN5uwrw6QXd2cgLahqhdqqn5YW8zDObonICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T23:00:15.915439Z","bundle_sha256":"49daffa9de8b2182dca0486b0d0cc4180d8f2b9e7b537a0aecf6911831939c5a"}}