{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X45RC5G5LGRL3WEPYABTUJUDKF","short_pith_number":"pith:X45RC5G5","canonical_record":{"source":{"id":"2406.18591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T16:28:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7c4244e1da63d85ba8c810d7e37ce52f93ea8a23ab6be889da01bb75939ab770","abstract_canon_sha256":"bc1a73df935b1cccfab9680943f6add3d6f1593665711fadaa381dfb8305407f"},"schema_version":"1.0"},"canonical_sha256":"bf3b1174dd59a2bdd88fc0033a2683516cd9c5b68abb4f884e611dd06a98afbe","source":{"kind":"arxiv","id":"2406.18591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18591","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18591v1","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18591","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"pith_short_12","alias_value":"X45RC5G5LGRL","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"pith_short_16","alias_value":"X45RC5G5LGRL3WEP","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"pith_short_8","alias_value":"X45RC5G5","created_at":"2026-07-05T08:37:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X45RC5G5LGRL3WEPYABTUJUDKF","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T16:28:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7c4244e1da63d85ba8c810d7e37ce52f93ea8a23ab6be889da01bb75939ab770","abstract_canon_sha256":"bc1a73df935b1cccfab9680943f6add3d6f1593665711fadaa381dfb8305407f"},"schema_version":"1.0"},"canonical_sha256":"bf3b1174dd59a2bdd88fc0033a2683516cd9c5b68abb4f884e611dd06a98afbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:23.046499Z","signature_b64":"gESkc+nu9uxlFLGwkMwZrUT6b4/rn6I6+5p5niawhKW9t8gaCJXTEs7oG9o//oTy1hWaMO3HgrycbLaP0fc5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3b1174dd59a2bdd88fc0033a2683516cd9c5b68abb4f884e611dd06a98afbe","last_reissued_at":"2026-07-05T08:37:23.046008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:23.046008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18591","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":"2026-07-05T08:37:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VoTz2xiOFkrpdBXk3/sndivOnU+XNT2VAtC2hzuWUe+jUR/V7HX9IibAUfdD0chQnkA0akmHpzPPaUJzCKaHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:03:26.535272Z"},"content_sha256":"1164dfebd2f5ba645e3c8990735dc13638060a8e6bf27e5da33adb5804d9cc83","schema_version":"1.0","event_id":"sha256:1164dfebd2f5ba645e3c8990735dc13638060a8e6bf27e5da33adb5804d9cc83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X45RC5G5LGRL3WEPYABTUJUDKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Composition Vision-Language Understanding via Segment and Depth Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haotian Lin, Junchen Liu, Mingxiao Huo, Pengliang Ji, Yijun Chen, Yixiao Wang","submitted_at":"2024-06-07T16:28:06Z","abstract_excerpt":"We introduce a pioneering unified library that leverages depth anything, segment anything models to augment neural comprehension in language-vision model zero-shot understanding. This library synergizes the capabilities of the Depth Anything Model (DAM), Segment Anything Model (SAM), and GPT-4V, enhancing multimodal tasks such as vision-question-answering (VQA) and composition reasoning. Through the fusion of segmentation and depth analysis at the symbolic instance level, our library provides nuanced inputs for language models, significantly advancing image interpretation. Validated across a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18591","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/2406.18591/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":"2026-07-05T08:37:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pk8G+XdTB1IGj7STGLI2HgzuhBvEiHddY4PLvOY0mnnT4caTxQkUbHU7S5CC1EWFJcUs5sYUlx8zoLnEcCnWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:03:26.536168Z"},"content_sha256":"21244bf4daa5c6faf7817a454fbe4d31780f4772caae78214657af0f32d74f46","schema_version":"1.0","event_id":"sha256:21244bf4daa5c6faf7817a454fbe4d31780f4772caae78214657af0f32d74f46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X45RC5G5LGRL3WEPYABTUJUDKF/bundle.json","state_url":"https://pith.science/pith/X45RC5G5LGRL3WEPYABTUJUDKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X45RC5G5LGRL3WEPYABTUJUDKF/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":"2026-08-11T18:03:26Z","links":{"resolver":"https://pith.science/pith/X45RC5G5LGRL3WEPYABTUJUDKF","bundle":"https://pith.science/pith/X45RC5G5LGRL3WEPYABTUJUDKF/bundle.json","state":"https://pith.science/pith/X45RC5G5LGRL3WEPYABTUJUDKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X45RC5G5LGRL3WEPYABTUJUDKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X45RC5G5LGRL3WEPYABTUJUDKF","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":"bc1a73df935b1cccfab9680943f6add3d6f1593665711fadaa381dfb8305407f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T16:28:06Z","title_canon_sha256":"7c4244e1da63d85ba8c810d7e37ce52f93ea8a23ab6be889da01bb75939ab770"},"schema_version":"1.0","source":{"id":"2406.18591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18591","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18591v1","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18591","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"pith_short_12","alias_value":"X45RC5G5LGRL","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"pith_short_16","alias_value":"X45RC5G5LGRL3WEP","created_at":"2026-07-05T08:37:23Z"},{"alias_kind":"pith_short_8","alias_value":"X45RC5G5","created_at":"2026-07-05T08:37:23Z"}],"graph_snapshots":[{"event_id":"sha256:21244bf4daa5c6faf7817a454fbe4d31780f4772caae78214657af0f32d74f46","target":"graph","created_at":"2026-07-05T08:37:23Z","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/2406.18591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a pioneering unified library that leverages depth anything, segment anything models to augment neural comprehension in language-vision model zero-shot understanding. This library synergizes the capabilities of the Depth Anything Model (DAM), Segment Anything Model (SAM), and GPT-4V, enhancing multimodal tasks such as vision-question-answering (VQA) and composition reasoning. Through the fusion of segmentation and depth analysis at the symbolic instance level, our library provides nuanced inputs for language models, significantly advancing image interpretation. Validated across a s","authors_text":"Haotian Lin, Junchen Liu, Mingxiao Huo, Pengliang Ji, Yijun Chen, Yixiao Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T16:28:06Z","title":"Composition Vision-Language Understanding via Segment and Depth Anything Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18591","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":"sha256:1164dfebd2f5ba645e3c8990735dc13638060a8e6bf27e5da33adb5804d9cc83","target":"record","created_at":"2026-07-05T08:37:23Z","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":"bc1a73df935b1cccfab9680943f6add3d6f1593665711fadaa381dfb8305407f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T16:28:06Z","title_canon_sha256":"7c4244e1da63d85ba8c810d7e37ce52f93ea8a23ab6be889da01bb75939ab770"},"schema_version":"1.0","source":{"id":"2406.18591","kind":"arxiv","version":1}},"canonical_sha256":"bf3b1174dd59a2bdd88fc0033a2683516cd9c5b68abb4f884e611dd06a98afbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf3b1174dd59a2bdd88fc0033a2683516cd9c5b68abb4f884e611dd06a98afbe","first_computed_at":"2026-07-05T08:37:23.046008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:23.046008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gESkc+nu9uxlFLGwkMwZrUT6b4/rn6I6+5p5niawhKW9t8gaCJXTEs7oG9o//oTy1hWaMO3HgrycbLaP0fc5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:23.046499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1164dfebd2f5ba645e3c8990735dc13638060a8e6bf27e5da33adb5804d9cc83","sha256:21244bf4daa5c6faf7817a454fbe4d31780f4772caae78214657af0f32d74f46"],"state_sha256":"50a1fb2b448a75e9f2f268600f98cd5afc9ca9ea1b2b68c9ee780b3e7983db82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRMDsg6sg028Ohkw9Fy9XUAj2l0dwjfDM5fDqsBA8JKjL00HtBvB6F6r/79iLvmK2OW8bTeeyeMIoYoI6QTuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:03:26.542665Z","bundle_sha256":"9d8024b22fc1f9a5edbd8888ed1d5915db4711a08bce306910b79135890aeceb"}}