{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LZNX5N5MZK543KC6CYWJEHA2PA","short_pith_number":"pith:LZNX5N5M","canonical_record":{"source":{"id":"2607.05716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:00:51Z","cross_cats_sorted":[],"title_canon_sha256":"482c39d6615b4a0edb693cb8b4192db682d7a0a3802e991a0c468011399f96b4","abstract_canon_sha256":"e89f90511808396997d111511d3a01b50d77372144b6f53fb5223eb9e7fde664"},"schema_version":"1.0"},"canonical_sha256":"5e5b7eb7accabbcda85e162c921c1a7829944c2e454ce4f2f13499a751f2b416","source":{"kind":"arxiv","id":"2607.05716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05716","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05716v1","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05716","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"LZNX5N5MZK54","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"LZNX5N5MZK543KC6","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"LZNX5N5M","created_at":"2026-07-08T01:18:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LZNX5N5MZK543KC6CYWJEHA2PA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:00:51Z","cross_cats_sorted":[],"title_canon_sha256":"482c39d6615b4a0edb693cb8b4192db682d7a0a3802e991a0c468011399f96b4","abstract_canon_sha256":"e89f90511808396997d111511d3a01b50d77372144b6f53fb5223eb9e7fde664"},"schema_version":"1.0"},"canonical_sha256":"5e5b7eb7accabbcda85e162c921c1a7829944c2e454ce4f2f13499a751f2b416","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:42.287768Z","signature_b64":"Z1iCndyCgoTfGNQbOsithe5s8pW/MKUpNr/UZ8dR8HuJuHUk2aEHihH+cCvTzTIh1l9ZEIZNIdd3NwcVDRYcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e5b7eb7accabbcda85e162c921c1a7829944c2e454ce4f2f13499a751f2b416","last_reissued_at":"2026-07-08T01:18:42.287278Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:42.287278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05716","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":"2026-07-08T01:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OAbueqaCycJFnSDohocoU2IndMtdqVJebZgLXvitTYAxyEu8+p8YJAai8XhVAUElc2zMWRFwPfnFQ5qxwluCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:57:42.289616Z"},"content_sha256":"0ab2c01845a3af9f1f3dfbbf8d5ea8fe9941c8b202c89fc5c2d210a5011604a6","schema_version":"1.0","event_id":"sha256:0ab2c01845a3af9f1f3dfbbf8d5ea8fe9941c8b202c89fc5c2d210a5011604a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LZNX5N5MZK543KC6CYWJEHA2PA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ke Yan, Nan Zhang, Shouhong Ding, Yuanchen Wu, Yucong Meng, Zhiwei Yang","submitted_at":"2026-07-07T01:00:51Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05716","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/2607.05716/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":"2026-07-08T01:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zzUZGqalsQmG/ecBKJJn7NChlwQdwewoSf6qY4vtjhluetyJc8SGV4MAQjuZueFNQmbzXJH4PzuEamqM4y9WDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:57:42.290187Z"},"content_sha256":"3167fccb3b0f28ff05a0d0749a2dfb5dca408ff3e5fb99d36b606bcda6ec12ca","schema_version":"1.0","event_id":"sha256:3167fccb3b0f28ff05a0d0749a2dfb5dca408ff3e5fb99d36b606bcda6ec12ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZNX5N5MZK543KC6CYWJEHA2PA/bundle.json","state_url":"https://pith.science/pith/LZNX5N5MZK543KC6CYWJEHA2PA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZNX5N5MZK543KC6CYWJEHA2PA/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":"2026-08-14T14:57:42Z","links":{"resolver":"https://pith.science/pith/LZNX5N5MZK543KC6CYWJEHA2PA","bundle":"https://pith.science/pith/LZNX5N5MZK543KC6CYWJEHA2PA/bundle.json","state":"https://pith.science/pith/LZNX5N5MZK543KC6CYWJEHA2PA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZNX5N5MZK543KC6CYWJEHA2PA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LZNX5N5MZK543KC6CYWJEHA2PA","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":"e89f90511808396997d111511d3a01b50d77372144b6f53fb5223eb9e7fde664","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:00:51Z","title_canon_sha256":"482c39d6615b4a0edb693cb8b4192db682d7a0a3802e991a0c468011399f96b4"},"schema_version":"1.0","source":{"id":"2607.05716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05716","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05716v1","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05716","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"LZNX5N5MZK54","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"LZNX5N5MZK543KC6","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"LZNX5N5M","created_at":"2026-07-08T01:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:3167fccb3b0f28ff05a0d0749a2dfb5dca408ff3e5fb99d36b606bcda6ec12ca","target":"graph","created_at":"2026-07-08T01:18:42Z","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/2607.05716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graph","authors_text":"Ke Yan, Nan Zhang, Shouhong Ding, Yuanchen Wu, Yucong Meng, Zhiwei Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:00:51Z","title":"Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05716","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":"sha256:0ab2c01845a3af9f1f3dfbbf8d5ea8fe9941c8b202c89fc5c2d210a5011604a6","target":"record","created_at":"2026-07-08T01:18:42Z","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":"e89f90511808396997d111511d3a01b50d77372144b6f53fb5223eb9e7fde664","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:00:51Z","title_canon_sha256":"482c39d6615b4a0edb693cb8b4192db682d7a0a3802e991a0c468011399f96b4"},"schema_version":"1.0","source":{"id":"2607.05716","kind":"arxiv","version":1}},"canonical_sha256":"5e5b7eb7accabbcda85e162c921c1a7829944c2e454ce4f2f13499a751f2b416","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e5b7eb7accabbcda85e162c921c1a7829944c2e454ce4f2f13499a751f2b416","first_computed_at":"2026-07-08T01:18:42.287278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:42.287278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z1iCndyCgoTfGNQbOsithe5s8pW/MKUpNr/UZ8dR8HuJuHUk2aEHihH+cCvTzTIh1l9ZEIZNIdd3NwcVDRYcAg==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:42.287768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ab2c01845a3af9f1f3dfbbf8d5ea8fe9941c8b202c89fc5c2d210a5011604a6","sha256:3167fccb3b0f28ff05a0d0749a2dfb5dca408ff3e5fb99d36b606bcda6ec12ca"],"state_sha256":"5a8b7c0481a7741ed287081f5ad678c6777bc6ba376a76c5a7cb4816f30a8b4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGgNladCE1T9aFuNQQyGVppnggb/BWOdvEdWx+z9GxBrQUyI7GjWqcW7L0iO3IE/R3ZcYogbzIStfpBtjoPeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:57:42.294054Z","bundle_sha256":"cf5255023f808d32c6297914394fcf77d5143f81ef35e211a26a00593d12a486"}}