{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2V53CWQCA26LDD42ES726NMMOI","short_pith_number":"pith:2V53CWQC","canonical_record":{"source":{"id":"2412.19326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T18:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"2302667309091af77e42215b883d28d65ad3d4f6e56cc4b789df9c45f28f7cef","abstract_canon_sha256":"9c8fc5c449db424400b21af215898f95a371244a931f65a8ae6676ea77288123"},"schema_version":"1.0"},"canonical_sha256":"d57bb15a0206bcb18f9a24bfaf358c720f3b9a2b651898105f576ef9e22b4584","source":{"kind":"arxiv","id":"2412.19326","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19326","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19326v2","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19326","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"pith_short_12","alias_value":"2V53CWQCA26L","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"pith_short_16","alias_value":"2V53CWQCA26LDD42","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"pith_short_8","alias_value":"2V53CWQC","created_at":"2026-07-05T11:29:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2V53CWQCA26LDD42ES726NMMOI","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T18:56:05Z","cross_cats_sorted":[],"title_canon_sha256":"2302667309091af77e42215b883d28d65ad3d4f6e56cc4b789df9c45f28f7cef","abstract_canon_sha256":"9c8fc5c449db424400b21af215898f95a371244a931f65a8ae6676ea77288123"},"schema_version":"1.0"},"canonical_sha256":"d57bb15a0206bcb18f9a24bfaf358c720f3b9a2b651898105f576ef9e22b4584","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:04.952068Z","signature_b64":"jV4uUokz2hFxTf0j3T5eSPnsFb/VzSGhKGW0kv//GWFg8KbjKA+mxu3/qhHy5h4TAQxNggFS+fGh9bgjd/tNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d57bb15a0206bcb18f9a24bfaf358c720f3b9a2b651898105f576ef9e22b4584","last_reissued_at":"2026-07-05T11:29:04.951561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:04.951561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19326","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":"2026-07-05T11:29:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ykUARL8omp52rz2gqbyew2Qvbri+9JI27hrnp0Fg6Vn9o7QwkLHJS9Gyu9xzMG0BIEJOutaRHQLuRnQCWExABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:38:52.594868Z"},"content_sha256":"dbb832ad9cd901cbcdc1ac0124a5899a5ab00004ba39f8008bcf2bb5259eeda0","schema_version":"1.0","event_id":"sha256:dbb832ad9cd901cbcdc1ac0124a5899a5ab00004ba39f8008bcf2bb5259eeda0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2V53CWQCA26LDD42ES726NMMOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenting Wang, Kunchang Li, Limin Wang, Xiangyu Zeng, Xinhao Li, Yali Wang, Yinan He, Yi Wang, Yu Qiao, Zhilin Li, Ziang Yan, Zilei Wang","submitted_at":"2024-12-26T18:56:05Z","abstract_excerpt":"Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregressive framework, often at the expense of overall multimodal performance. To address this issue and enhance MLLMs with visual tasks in a scalable fashion, we propose Task Preference Optimization (TPO), a novel method that utilizes differentiable task preferences derived from typical fine-grained visual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19326","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/2412.19326/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":"2026-07-05T11:29:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZoHAIHJTlTzFQMz0y0cXGj4xlR27TiFiRe+zi/P79hJ4s2bmqrIlMGJn8gC/lBh1SEd6KV9x3nZyo93xFU2Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:38:52.595365Z"},"content_sha256":"b5b70357d0ddd7a1b5271ca1e50fad5918c93f06cc85417090f2a26c955875c6","schema_version":"1.0","event_id":"sha256:b5b70357d0ddd7a1b5271ca1e50fad5918c93f06cc85417090f2a26c955875c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2V53CWQCA26LDD42ES726NMMOI/bundle.json","state_url":"https://pith.science/pith/2V53CWQCA26LDD42ES726NMMOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2V53CWQCA26LDD42ES726NMMOI/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":"2026-08-11T07:38:52Z","links":{"resolver":"https://pith.science/pith/2V53CWQCA26LDD42ES726NMMOI","bundle":"https://pith.science/pith/2V53CWQCA26LDD42ES726NMMOI/bundle.json","state":"https://pith.science/pith/2V53CWQCA26LDD42ES726NMMOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2V53CWQCA26LDD42ES726NMMOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2V53CWQCA26LDD42ES726NMMOI","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":"9c8fc5c449db424400b21af215898f95a371244a931f65a8ae6676ea77288123","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T18:56:05Z","title_canon_sha256":"2302667309091af77e42215b883d28d65ad3d4f6e56cc4b789df9c45f28f7cef"},"schema_version":"1.0","source":{"id":"2412.19326","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19326","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19326v2","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19326","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"pith_short_12","alias_value":"2V53CWQCA26L","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"pith_short_16","alias_value":"2V53CWQCA26LDD42","created_at":"2026-07-05T11:29:04Z"},{"alias_kind":"pith_short_8","alias_value":"2V53CWQC","created_at":"2026-07-05T11:29:04Z"}],"graph_snapshots":[{"event_id":"sha256:b5b70357d0ddd7a1b5271ca1e50fad5918c93f06cc85417090f2a26c955875c6","target":"graph","created_at":"2026-07-05T11:29:04Z","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/2412.19326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregressive framework, often at the expense of overall multimodal performance. To address this issue and enhance MLLMs with visual tasks in a scalable fashion, we propose Task Preference Optimization (TPO), a novel method that utilizes differentiable task preferences derived from typical fine-grained visual","authors_text":"Chenting Wang, Kunchang Li, Limin Wang, Xiangyu Zeng, Xinhao Li, Yali Wang, Yinan He, Yi Wang, Yu Qiao, Zhilin Li, Ziang Yan, Zilei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T18:56:05Z","title":"Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19326","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:dbb832ad9cd901cbcdc1ac0124a5899a5ab00004ba39f8008bcf2bb5259eeda0","target":"record","created_at":"2026-07-05T11:29:04Z","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":"9c8fc5c449db424400b21af215898f95a371244a931f65a8ae6676ea77288123","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T18:56:05Z","title_canon_sha256":"2302667309091af77e42215b883d28d65ad3d4f6e56cc4b789df9c45f28f7cef"},"schema_version":"1.0","source":{"id":"2412.19326","kind":"arxiv","version":2}},"canonical_sha256":"d57bb15a0206bcb18f9a24bfaf358c720f3b9a2b651898105f576ef9e22b4584","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d57bb15a0206bcb18f9a24bfaf358c720f3b9a2b651898105f576ef9e22b4584","first_computed_at":"2026-07-05T11:29:04.951561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:04.951561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jV4uUokz2hFxTf0j3T5eSPnsFb/VzSGhKGW0kv//GWFg8KbjKA+mxu3/qhHy5h4TAQxNggFS+fGh9bgjd/tNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:04.952068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19326","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbb832ad9cd901cbcdc1ac0124a5899a5ab00004ba39f8008bcf2bb5259eeda0","sha256:b5b70357d0ddd7a1b5271ca1e50fad5918c93f06cc85417090f2a26c955875c6"],"state_sha256":"1c5e9de61638e241280d4048367977d5bce15b2dd375c457876f4f0e5be983e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFL8jYDbyHxXnXUhtdSNiQvgctVMjWEhKO5TEkAdKqjj2XbnGpZ4qRtCjIwF6uQ87vGUIYyo/FF1CqvxjV+LDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T07:38:52.599891Z","bundle_sha256":"a20fbd297f53219e9dc654024e10ee0f61fa70484e72ab9e085cea0e6163d28e"}}