{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2H2N26LNO47JFHOMIVQ6D24ATL","short_pith_number":"pith:2H2N26LN","canonical_record":{"source":{"id":"2401.17862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T14:21:49Z","cross_cats_sorted":[],"title_canon_sha256":"cbee800e63ac80c24fbd5d8fe16fed2d0a76bbe9be6878cfa1880da9ed449b07","abstract_canon_sha256":"b6f9d22e02088d7cefd48fd6ad3970b65aad52acecf7af7d3d1eae7ef0fc204a"},"schema_version":"1.0"},"canonical_sha256":"d1f4dd796d773e929dcc4561e1eb809ac99a2cfbc7d6688a95ada8a118c309a1","source":{"kind":"arxiv","id":"2401.17862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17862","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17862v1","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17862","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"pith_short_12","alias_value":"2H2N26LNO47J","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"pith_short_16","alias_value":"2H2N26LNO47JFHOM","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"pith_short_8","alias_value":"2H2N26LN","created_at":"2026-07-05T07:39:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2H2N26LNO47JFHOMIVQ6D24ATL","target":"record","payload":{"canonical_record":{"source":{"id":"2401.17862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T14:21:49Z","cross_cats_sorted":[],"title_canon_sha256":"cbee800e63ac80c24fbd5d8fe16fed2d0a76bbe9be6878cfa1880da9ed449b07","abstract_canon_sha256":"b6f9d22e02088d7cefd48fd6ad3970b65aad52acecf7af7d3d1eae7ef0fc204a"},"schema_version":"1.0"},"canonical_sha256":"d1f4dd796d773e929dcc4561e1eb809ac99a2cfbc7d6688a95ada8a118c309a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:43.542396Z","signature_b64":"98OsOzdSW9YSHPA1Q2UyrJg7J3osi/sHfEQVyaIP3LSOefmHtfRqBWF5PrMEbY9HHISRyGcSjUFfDycB/Ny+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1f4dd796d773e929dcc4561e1eb809ac99a2cfbc7d6688a95ada8a118c309a1","last_reissued_at":"2026-07-05T07:39:43.541887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:43.541887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.17862","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":"2026-07-05T07:39:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWRz3gv7piqB4wElifLQ1cHTBYKDNDFhueryw4dB+CJHWq9JYPeUSEZNKIbxnGpVMzpafP0Y5XRxObGr33gTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:14:01.812801Z"},"content_sha256":"5d433358bc494446844aa2efdd3cf256db6445324d3965329c59961c19884f5c","schema_version":"1.0","event_id":"sha256:5d433358bc494446844aa2efdd3cf256db6445324d3965329c59961c19884f5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2H2N26LNO47JFHOMIVQ6D24ATL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianing Li, Li Du, Ming Lu, Shanghang Zhang, Xi Nan","submitted_at":"2024-01-31T14:21:49Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have demonstrated remarkable vision-language capabilities, primarily due to the exceptional in-context understanding and multi-task learning strengths of large language models (LLMs). The advent of visual instruction tuning has further enhanced MLLMs' performance in vision-language understanding. However, while existing MLLMs adeptly recognize \\textit{what} objects are in an image, they still face challenges in effectively discerning \\textit{where} these objects are, particularly along the distance (scene depth) axis. To overcome this limitation in MLL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17862","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/2401.17862/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":"2026-07-05T07:39:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYA9rzui9u8xN/ji9MzmkY4L7jOSVLIZ7dkatVVnbTF+FUQpBopPbkSVuHopcfKWOEGRUTwm1zl2tA77YqYHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:14:01.813245Z"},"content_sha256":"eb99a527e1d31787c4862d66dc9a4a3eda5aa95a32a18bd85e9a3e465863d849","schema_version":"1.0","event_id":"sha256:eb99a527e1d31787c4862d66dc9a4a3eda5aa95a32a18bd85e9a3e465863d849"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2H2N26LNO47JFHOMIVQ6D24ATL/bundle.json","state_url":"https://pith.science/pith/2H2N26LNO47JFHOMIVQ6D24ATL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2H2N26LNO47JFHOMIVQ6D24ATL/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":"2026-07-07T15:14:01Z","links":{"resolver":"https://pith.science/pith/2H2N26LNO47JFHOMIVQ6D24ATL","bundle":"https://pith.science/pith/2H2N26LNO47JFHOMIVQ6D24ATL/bundle.json","state":"https://pith.science/pith/2H2N26LNO47JFHOMIVQ6D24ATL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2H2N26LNO47JFHOMIVQ6D24ATL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2H2N26LNO47JFHOMIVQ6D24ATL","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":"b6f9d22e02088d7cefd48fd6ad3970b65aad52acecf7af7d3d1eae7ef0fc204a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T14:21:49Z","title_canon_sha256":"cbee800e63ac80c24fbd5d8fe16fed2d0a76bbe9be6878cfa1880da9ed449b07"},"schema_version":"1.0","source":{"id":"2401.17862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17862","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17862v1","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17862","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"pith_short_12","alias_value":"2H2N26LNO47J","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"pith_short_16","alias_value":"2H2N26LNO47JFHOM","created_at":"2026-07-05T07:39:43Z"},{"alias_kind":"pith_short_8","alias_value":"2H2N26LN","created_at":"2026-07-05T07:39:43Z"}],"graph_snapshots":[{"event_id":"sha256:eb99a527e1d31787c4862d66dc9a4a3eda5aa95a32a18bd85e9a3e465863d849","target":"graph","created_at":"2026-07-05T07:39:43Z","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/2401.17862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) have demonstrated remarkable vision-language capabilities, primarily due to the exceptional in-context understanding and multi-task learning strengths of large language models (LLMs). The advent of visual instruction tuning has further enhanced MLLMs' performance in vision-language understanding. However, while existing MLLMs adeptly recognize \\textit{what} objects are in an image, they still face challenges in effectively discerning \\textit{where} these objects are, particularly along the distance (scene depth) axis. To overcome this limitation in MLL","authors_text":"Jianing Li, Li Du, Ming Lu, Shanghang Zhang, Xi Nan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T14:21:49Z","title":"Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17862","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":"sha256:5d433358bc494446844aa2efdd3cf256db6445324d3965329c59961c19884f5c","target":"record","created_at":"2026-07-05T07:39:43Z","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":"b6f9d22e02088d7cefd48fd6ad3970b65aad52acecf7af7d3d1eae7ef0fc204a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T14:21:49Z","title_canon_sha256":"cbee800e63ac80c24fbd5d8fe16fed2d0a76bbe9be6878cfa1880da9ed449b07"},"schema_version":"1.0","source":{"id":"2401.17862","kind":"arxiv","version":1}},"canonical_sha256":"d1f4dd796d773e929dcc4561e1eb809ac99a2cfbc7d6688a95ada8a118c309a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1f4dd796d773e929dcc4561e1eb809ac99a2cfbc7d6688a95ada8a118c309a1","first_computed_at":"2026-07-05T07:39:43.541887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:43.541887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"98OsOzdSW9YSHPA1Q2UyrJg7J3osi/sHfEQVyaIP3LSOefmHtfRqBWF5PrMEbY9HHISRyGcSjUFfDycB/Ny+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:43.542396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d433358bc494446844aa2efdd3cf256db6445324d3965329c59961c19884f5c","sha256:eb99a527e1d31787c4862d66dc9a4a3eda5aa95a32a18bd85e9a3e465863d849"],"state_sha256":"dc18648cae94c5e6d8bc597ef455e5e73f1a953c1347ff40acfe1ba9daa14b29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vL8mzdjGWR4PmTfIJHG0e+2OGqLs8XSgJYV3oH7+d3oWmmMqjRRBVIsZYVXy87r08bqFtMnj0y0jGBIqcHSMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:14:01.815228Z","bundle_sha256":"299800586b1b78194a1271f36f765d91369aa3185c268f5e6f6fe53a10209f2b"}}