{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A344EA65I2TVH7F2OF7TSHOQSD","short_pith_number":"pith:A344EA65","canonical_record":{"source":{"id":"2501.06828","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T14:45:27Z","cross_cats_sorted":[],"title_canon_sha256":"a05e9da24162589998bf1e87b3e4da382094a63f925a6a5638d5b15c09db0bda","abstract_canon_sha256":"848103081643f53ccad041bb4b8c3afdf762edd2ec04cf89f015afe795527eb4"},"schema_version":"1.0"},"canonical_sha256":"06f9c203dd46a753fcba717f391dd090f2ea3ad1a2e530caae3d40d4618f59ee","source":{"kind":"arxiv","id":"2501.06828","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06828","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06828v2","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06828","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"pith_short_12","alias_value":"A344EA65I2TV","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"pith_short_16","alias_value":"A344EA65I2TVH7F2","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"pith_short_8","alias_value":"A344EA65","created_at":"2026-07-05T10:30:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A344EA65I2TVH7F2OF7TSHOQSD","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06828","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T14:45:27Z","cross_cats_sorted":[],"title_canon_sha256":"a05e9da24162589998bf1e87b3e4da382094a63f925a6a5638d5b15c09db0bda","abstract_canon_sha256":"848103081643f53ccad041bb4b8c3afdf762edd2ec04cf89f015afe795527eb4"},"schema_version":"1.0"},"canonical_sha256":"06f9c203dd46a753fcba717f391dd090f2ea3ad1a2e530caae3d40d4618f59ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:30.052156Z","signature_b64":"cq5qbE2s2TXUA/hyXJ8seW7Y5F+vJWrv4Vfnkpq8sWIBA74WgkpwtKVxwJ/KatW/5FtuDXqoF990YHXF7UI6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06f9c203dd46a753fcba717f391dd090f2ea3ad1a2e530caae3d40d4618f59ee","last_reissued_at":"2026-07-05T10:30:30.051271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:30.051271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06828","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:30:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"289kWPksNq/NuIs2Jtk7x2uZKEdr76zBmilZv5WTgpd2KoSpTfxVzaitK+ycLvKZtsI7KLCC9yrjo9TXqii4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T08:19:20.482215Z"},"content_sha256":"3740ad849bd0d9e544098d3fd9ac33bc9e25fbb4d08acb00e2a872b7da7d475b","schema_version":"1.0","event_id":"sha256:3740ad849bd0d9e544098d3fd9ac33bc9e25fbb4d08acb00e2a872b7da7d475b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A344EA65I2TVH7F2OF7TSHOQSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Zhang, Jiaxin Chen, Ruizhe Ou, Yuan Hu, Yu Liu","submitted_at":"2025-01-12T14:45:27Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06828","kind":"arxiv","version":2},"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/2501.06828/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":"2026-07-05T10:30:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQpRC89aOrSqi9wQMx0guuUTsoXA35wK9/HXR5RI32M8+fVpttFbwdotqpq3fGHiLNCghO3YQRLmZQhEkT3xDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T08:19:20.482610Z"},"content_sha256":"dc89245babd62ef5684400361720078da44b61a6d6f069a0503dbbb7c4e240df","schema_version":"1.0","event_id":"sha256:dc89245babd62ef5684400361720078da44b61a6d6f069a0503dbbb7c4e240df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A344EA65I2TVH7F2OF7TSHOQSD/bundle.json","state_url":"https://pith.science/pith/A344EA65I2TVH7F2OF7TSHOQSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A344EA65I2TVH7F2OF7TSHOQSD/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":"2026-07-25T08:19:20Z","links":{"resolver":"https://pith.science/pith/A344EA65I2TVH7F2OF7TSHOQSD","bundle":"https://pith.science/pith/A344EA65I2TVH7F2OF7TSHOQSD/bundle.json","state":"https://pith.science/pith/A344EA65I2TVH7F2OF7TSHOQSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A344EA65I2TVH7F2OF7TSHOQSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A344EA65I2TVH7F2OF7TSHOQSD","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":"848103081643f53ccad041bb4b8c3afdf762edd2ec04cf89f015afe795527eb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T14:45:27Z","title_canon_sha256":"a05e9da24162589998bf1e87b3e4da382094a63f925a6a5638d5b15c09db0bda"},"schema_version":"1.0","source":{"id":"2501.06828","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06828","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06828v2","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06828","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"pith_short_12","alias_value":"A344EA65I2TV","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"pith_short_16","alias_value":"A344EA65I2TVH7F2","created_at":"2026-07-05T10:30:30Z"},{"alias_kind":"pith_short_8","alias_value":"A344EA65","created_at":"2026-07-05T10:30:30Z"}],"graph_snapshots":[{"event_id":"sha256:dc89245babd62ef5684400361720078da44b61a6d6f069a0503dbbb7c4e240df","target":"graph","created_at":"2026-07-05T10:30:30Z","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/2501.06828/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 achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from th","authors_text":"Fan Zhang, Jiaxin Chen, Ruizhe Ou, Yuan Hu, Yu Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T14:45:27Z","title":"GeoPix: Multi-Modal Large Language Model for Pixel-level Image Understanding in Remote Sensing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06828","kind":"arxiv","version":2},"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":"sha256:3740ad849bd0d9e544098d3fd9ac33bc9e25fbb4d08acb00e2a872b7da7d475b","target":"record","created_at":"2026-07-05T10:30:30Z","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":"848103081643f53ccad041bb4b8c3afdf762edd2ec04cf89f015afe795527eb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-12T14:45:27Z","title_canon_sha256":"a05e9da24162589998bf1e87b3e4da382094a63f925a6a5638d5b15c09db0bda"},"schema_version":"1.0","source":{"id":"2501.06828","kind":"arxiv","version":2}},"canonical_sha256":"06f9c203dd46a753fcba717f391dd090f2ea3ad1a2e530caae3d40d4618f59ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06f9c203dd46a753fcba717f391dd090f2ea3ad1a2e530caae3d40d4618f59ee","first_computed_at":"2026-07-05T10:30:30.051271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:30.051271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cq5qbE2s2TXUA/hyXJ8seW7Y5F+vJWrv4Vfnkpq8sWIBA74WgkpwtKVxwJ/KatW/5FtuDXqoF990YHXF7UI6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:30.052156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06828","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3740ad849bd0d9e544098d3fd9ac33bc9e25fbb4d08acb00e2a872b7da7d475b","sha256:dc89245babd62ef5684400361720078da44b61a6d6f069a0503dbbb7c4e240df"],"state_sha256":"4f4cdc03d007b19632db332fe23bd8820e60a73ec37c6d2d29b1db467f4749ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0RSTdXCZ8HKNLZ37h4x33QKsVVgcjufA8QOPbFrQrLZSNAJ4m2dPUiQvlN7OQWiAEZbOawkMf3gaxzgVF0qLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T08:19:20.485127Z","bundle_sha256":"e1a7b4c5e05450c70cca0b7b0fad82f80bd1e012e32f364841292efe5efa1a9c"}}