{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BCSR5P3XXX3OSFIFCQG523Q74N","short_pith_number":"pith:BCSR5P3X","canonical_record":{"source":{"id":"2407.06723","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T09:55:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c738ab7164e4037399017f3ba563ea97e9897f766bd792a54eeb72a6869cf711","abstract_canon_sha256":"37dc0badf4e867a6bde9940b9e863ed4c52a656f9558a7450f4ff421f6062521"},"schema_version":"1.0"},"canonical_sha256":"08a51ebf77bdf6e91505140ddd6e1fe35d320a3e463828d97280a7c54933a863","source":{"kind":"arxiv","id":"2407.06723","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06723","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06723v2","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06723","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"BCSR5P3XXX3O","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"BCSR5P3XXX3OSFIF","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"BCSR5P3X","created_at":"2026-07-05T10:20:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BCSR5P3XXX3OSFIFCQG523Q74N","target":"record","payload":{"canonical_record":{"source":{"id":"2407.06723","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T09:55:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c738ab7164e4037399017f3ba563ea97e9897f766bd792a54eeb72a6869cf711","abstract_canon_sha256":"37dc0badf4e867a6bde9940b9e863ed4c52a656f9558a7450f4ff421f6062521"},"schema_version":"1.0"},"canonical_sha256":"08a51ebf77bdf6e91505140ddd6e1fe35d320a3e463828d97280a7c54933a863","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:38.479264Z","signature_b64":"yaLVnCyxrTgMHpFfS82MCquKsfXx04dqpzHdO/pYfxRrVa2LScPBT1KPHXkbYYvxkqFhsfrPpRIB+Rl2I2FKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08a51ebf77bdf6e91505140ddd6e1fe35d320a3e463828d97280a7c54933a863","last_reissued_at":"2026-07-05T10:20:38.478675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:38.478675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.06723","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":"2026-07-05T10:20:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YB2tlPMAdcia27zIEU7Bjp7KBJe4hyC1cCGXaUFAl/IA2+SW3drVQdahL9d4RuVYKlYd+vlmlt+nzeAq0qv8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:32.497060Z"},"content_sha256":"c01c29ddcbd4d70639aa792711280e9bc80dd4f9ce2dac5b31946ac36167fb46","schema_version":"1.0","event_id":"sha256:c01c29ddcbd4d70639aa792711280e9bc80dd4f9ce2dac5b31946ac36167fb46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BCSR5P3XXX3OSFIFCQG523Q74N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Yu Hsieh, Chun-Liang Li, Hadi Pour Ansari, Louis B\\'ethune, Marco Cuturi, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Ranjay Krishna, Shih-Ying Yeh, Yu-Guan Hsieh","submitted_at":"2024-07-09T09:55:04Z","abstract_excerpt":"Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is not reflected yet in existing datasets which, for the most part, still use plain text to describe images. In this work, we propose a new annotation strategy, graph-based captioning (GBC) that describes an image using a labeled graph structure, with nodes of various types. The nodes in GBC are created through a two-stage process: first, identifying and describi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06723","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/2407.06723/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":"2026-07-05T10:20:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQCloLMGHvLdzd90HAqK9tm8vgvWViWr+PBprlFWUAdzFs7ajGbPCl27hbZyIDe+p9eP3aBfv64nWNxD2HFwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:32.497583Z"},"content_sha256":"796363ff3326319bc66f8ca26a96a17671af400b3f1798d8eb8a7a3d2b9bb281","schema_version":"1.0","event_id":"sha256:796363ff3326319bc66f8ca26a96a17671af400b3f1798d8eb8a7a3d2b9bb281"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCSR5P3XXX3OSFIFCQG523Q74N/bundle.json","state_url":"https://pith.science/pith/BCSR5P3XXX3OSFIFCQG523Q74N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCSR5P3XXX3OSFIFCQG523Q74N/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":"2026-08-05T20:46:32Z","links":{"resolver":"https://pith.science/pith/BCSR5P3XXX3OSFIFCQG523Q74N","bundle":"https://pith.science/pith/BCSR5P3XXX3OSFIFCQG523Q74N/bundle.json","state":"https://pith.science/pith/BCSR5P3XXX3OSFIFCQG523Q74N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCSR5P3XXX3OSFIFCQG523Q74N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BCSR5P3XXX3OSFIFCQG523Q74N","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":"37dc0badf4e867a6bde9940b9e863ed4c52a656f9558a7450f4ff421f6062521","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T09:55:04Z","title_canon_sha256":"c738ab7164e4037399017f3ba563ea97e9897f766bd792a54eeb72a6869cf711"},"schema_version":"1.0","source":{"id":"2407.06723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06723","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06723v2","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06723","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"BCSR5P3XXX3O","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"BCSR5P3XXX3OSFIF","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"BCSR5P3X","created_at":"2026-07-05T10:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:796363ff3326319bc66f8ca26a96a17671af400b3f1798d8eb8a7a3d2b9bb281","target":"graph","created_at":"2026-07-05T10:20:38Z","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/2407.06723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is not reflected yet in existing datasets which, for the most part, still use plain text to describe images. In this work, we propose a new annotation strategy, graph-based captioning (GBC) that describes an image using a labeled graph structure, with nodes of various types. The nodes in GBC are created through a two-stage process: first, identifying and describi","authors_text":"Cheng-Yu Hsieh, Chun-Liang Li, Hadi Pour Ansari, Louis B\\'ethune, Marco Cuturi, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Ranjay Krishna, Shih-Ying Yeh, Yu-Guan Hsieh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T09:55:04Z","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06723","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:c01c29ddcbd4d70639aa792711280e9bc80dd4f9ce2dac5b31946ac36167fb46","target":"record","created_at":"2026-07-05T10:20:38Z","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":"37dc0badf4e867a6bde9940b9e863ed4c52a656f9558a7450f4ff421f6062521","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T09:55:04Z","title_canon_sha256":"c738ab7164e4037399017f3ba563ea97e9897f766bd792a54eeb72a6869cf711"},"schema_version":"1.0","source":{"id":"2407.06723","kind":"arxiv","version":2}},"canonical_sha256":"08a51ebf77bdf6e91505140ddd6e1fe35d320a3e463828d97280a7c54933a863","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08a51ebf77bdf6e91505140ddd6e1fe35d320a3e463828d97280a7c54933a863","first_computed_at":"2026-07-05T10:20:38.478675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:38.478675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yaLVnCyxrTgMHpFfS82MCquKsfXx04dqpzHdO/pYfxRrVa2LScPBT1KPHXkbYYvxkqFhsfrPpRIB+Rl2I2FKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:38.479264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c01c29ddcbd4d70639aa792711280e9bc80dd4f9ce2dac5b31946ac36167fb46","sha256:796363ff3326319bc66f8ca26a96a17671af400b3f1798d8eb8a7a3d2b9bb281"],"state_sha256":"5b5d2b5d8a54b50c4c58db7ce8743958da19656b7ed02d7adcece4473d6f85aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xTPy7uYYhTZlBPbjDljqV9XK4SkqVAKc3cvMJ00DX9BLCTCNj7mIsiGFHYpB3AVdONjgKVd5rHZEiRZUNQ78Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:46:32.503292Z","bundle_sha256":"6daf8fe1607c3bc27bceaf945cc3c95e5dc600af1b979673f0cea62de8e1c8cf"}}