{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JURUABU2K3E7EQW6UFPC3CHKED","short_pith_number":"pith:JURUABU2","canonical_record":{"source":{"id":"2310.00582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-01T05:53:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22ae7907a1ed171f3b237f81ae345bfe0f7ad75acc67399e4dbbec2b16ec1d31","abstract_canon_sha256":"5c77bdee8a22bc081ee3beddcf0cc27a2ebf61234cb8cdc4d37a996f6a644ff2"},"schema_version":"1.0"},"canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","source":{"kind":"arxiv","id":"2310.00582","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00582","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00582v3","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00582","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_12","alias_value":"JURUABU2K3E7","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_16","alias_value":"JURUABU2K3E7EQW6","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_8","alias_value":"JURUABU2","created_at":"2026-07-05T07:55:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JURUABU2K3E7EQW6UFPC3CHKED","target":"record","payload":{"canonical_record":{"source":{"id":"2310.00582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-01T05:53:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22ae7907a1ed171f3b237f81ae345bfe0f7ad75acc67399e4dbbec2b16ec1d31","abstract_canon_sha256":"5c77bdee8a22bc081ee3beddcf0cc27a2ebf61234cb8cdc4d37a996f6a644ff2"},"schema_version":"1.0"},"canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:24.807366Z","signature_b64":"q1aiO3AYsDWajSdkb33F3IL0KVFza6GV77z942iEKygmdaCUaeGlWO0yED5mfw7u9aYnjDby8FXfK6BrEAY5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","last_reissued_at":"2026-07-05T07:55:24.806882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:24.806882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.00582","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:55:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ak0MvJGXpUedHMVi80+Bnwsd9kHHT+sqKUzTCNEQijtMhtigkVCsR0Gvr2wEHSQGvB84zrotyB7YgqyVvWoMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T16:02:41.176906Z"},"content_sha256":"eb6ee15edeb9428e754cb5c5ddc3303c6ba24679bb20cc46dd246c620fa57c07","schema_version":"1.0","event_id":"sha256:eb6ee15edeb9428e754cb5c5ddc3303c6ba24679bb20cc46dd246c620fa57c07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JURUABU2K3E7EQW6UFPC3CHKED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ming Yang, Qingpei Guo, Shiliang Zhang, Shiyu Xuan","submitted_at":"2023-10-01T05:53:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00582","kind":"arxiv","version":3},"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/2310.00582/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":"2026-07-05T07:55:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PyJu52k0cB8pnQO/yvd8+UqZeW9uz2VMXffXG3q7QyWLSrCvphdrxSPw7v0GmuN8H6lrMRuhkYtgofT4YWDGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T16:02:41.178029Z"},"content_sha256":"6beae905f85b24a6d0cd161a5077152f83a92e4930a6d8bee1cbd99843c6146c","schema_version":"1.0","event_id":"sha256:6beae905f85b24a6d0cd161a5077152f83a92e4930a6d8bee1cbd99843c6146c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/bundle.json","state_url":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JURUABU2K3E7EQW6UFPC3CHKED/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":"2026-08-14T16:02:41Z","links":{"resolver":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED","bundle":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/bundle.json","state":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JURUABU2K3E7EQW6UFPC3CHKED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JURUABU2K3E7EQW6UFPC3CHKED","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":"5c77bdee8a22bc081ee3beddcf0cc27a2ebf61234cb8cdc4d37a996f6a644ff2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-01T05:53:15Z","title_canon_sha256":"22ae7907a1ed171f3b237f81ae345bfe0f7ad75acc67399e4dbbec2b16ec1d31"},"schema_version":"1.0","source":{"id":"2310.00582","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00582","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00582v3","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00582","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_12","alias_value":"JURUABU2K3E7","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_16","alias_value":"JURUABU2K3E7EQW6","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_8","alias_value":"JURUABU2","created_at":"2026-07-05T07:55:24Z"}],"graph_snapshots":[{"event_id":"sha256:6beae905f85b24a6d0cd161a5077152f83a92e4930a6d8bee1cbd99843c6146c","target":"graph","created_at":"2026-07-05T07:55:24Z","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/2310.00582/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 shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referr","authors_text":"Ming Yang, Qingpei Guo, Shiliang Zhang, Shiyu Xuan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-01T05:53:15Z","title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00582","kind":"arxiv","version":3},"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:eb6ee15edeb9428e754cb5c5ddc3303c6ba24679bb20cc46dd246c620fa57c07","target":"record","created_at":"2026-07-05T07:55:24Z","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":"5c77bdee8a22bc081ee3beddcf0cc27a2ebf61234cb8cdc4d37a996f6a644ff2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-01T05:53:15Z","title_canon_sha256":"22ae7907a1ed171f3b237f81ae345bfe0f7ad75acc67399e4dbbec2b16ec1d31"},"schema_version":"1.0","source":{"id":"2310.00582","kind":"arxiv","version":3}},"canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","first_computed_at":"2026-07-05T07:55:24.806882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:24.806882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q1aiO3AYsDWajSdkb33F3IL0KVFza6GV77z942iEKygmdaCUaeGlWO0yED5mfw7u9aYnjDby8FXfK6BrEAY5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:24.807366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00582","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb6ee15edeb9428e754cb5c5ddc3303c6ba24679bb20cc46dd246c620fa57c07","sha256:6beae905f85b24a6d0cd161a5077152f83a92e4930a6d8bee1cbd99843c6146c"],"state_sha256":"cd9bbe930b056e128aa5410d8c25f24a27567ae0bc0e8c3263a7a496d88eb607"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kPSXJAThSD9yymOsw2mGHKE5nRJzSW8dkEPUe74xj1FYQgmQxMN5DUK1AxxO8rqB2KqRekMM/kLStPKCFZdjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T16:02:41.205671Z","bundle_sha256":"c43bb29bf3d9f9355712ed395bff11c6b43ad59d3fbc333404c5aceecbe81881"}}