{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LVZYF2XWNM6K4KL2MJTYGR5AXM","short_pith_number":"pith:LVZYF2XW","canonical_record":{"source":{"id":"2312.04837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-08T05:23:50Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"b9114744e4a51af4b4d3f1282c1653552893cdbae7f1f61a67f62b786a98503a","abstract_canon_sha256":"f6fd6feb1bb3d9aa1482dcc73e26cd88e92ca53f4416111af984ccf1890f10e5"},"schema_version":"1.0"},"canonical_sha256":"5d7382eaf66b3cae297a62678347a0bb1f53d646d358cf64c64ce4a76b0ce1f6","source":{"kind":"arxiv","id":"2312.04837","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04837","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04837v2","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04837","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"pith_short_12","alias_value":"LVZYF2XWNM6K","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"pith_short_16","alias_value":"LVZYF2XWNM6K4KL2","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"pith_short_8","alias_value":"LVZYF2XW","created_at":"2026-07-05T07:23:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LVZYF2XWNM6K4KL2MJTYGR5AXM","target":"record","payload":{"canonical_record":{"source":{"id":"2312.04837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-08T05:23:50Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"b9114744e4a51af4b4d3f1282c1653552893cdbae7f1f61a67f62b786a98503a","abstract_canon_sha256":"f6fd6feb1bb3d9aa1482dcc73e26cd88e92ca53f4416111af984ccf1890f10e5"},"schema_version":"1.0"},"canonical_sha256":"5d7382eaf66b3cae297a62678347a0bb1f53d646d358cf64c64ce4a76b0ce1f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:10.466041Z","signature_b64":"RXDX49DX0GHBbgkS2vgTGfIJ32/JLLjSJGfp0If9B30O7BvIBLxcwYmd7JalIdZTS/LN4nAfBY33kUvmq1cJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d7382eaf66b3cae297a62678347a0bb1f53d646d358cf64c64ce4a76b0ce1f6","last_reissued_at":"2026-07-05T07:23:10.465578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:10.465578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.04837","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":"2026-07-05T07:23:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QYxwNd1gQzkcYwytlpajZXNT3NmOXlPhYBaxsPiUpVAiGJ5T+iSIYg1JfxeyRo0Qogce1o2AzmBBP6wHJ2Q2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:22:31.678439Z"},"content_sha256":"a84adf8dbcd57bd3c616de30fb8c7928b4b93874e79e35c226cfbe66850abe0e","schema_version":"1.0","event_id":"sha256:a84adf8dbcd57bd3c616de30fb8c7928b4b93874e79e35c226cfbe66850abe0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LVZYF2XWNM6K4KL2MJTYGR5AXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ali Farhadi, Jack Hessel, Jae Sung Park, Jianfeng Gao, Khyathi Raghavi Chandu, Paul Pu Liang, Peter West, Qiuyuan Huang, Ximing Lu, Yejin Choi, Youngjae Yu","submitted_at":"2023-12-08T05:23:50Z","abstract_excerpt":"Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to \"point to\" and access specific regions within images. This capability is important not only to support reference-grounded VL benchmarks, but also, for practical applications that require precise within-image reasoning. We build Localized Visual Commonsense models, which allow users to specify (multiple) regions as input. We train our model by sampling localized comm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04837","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/2312.04837/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":"2026-07-05T07:23:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sn4kyDGUXzQA6K1eJ3Lu1QYlXnuYYKDD3DI29B/Iv1hhfuJn82Fur3feR7jeVqfpB7ZQmbuGnIsbwqsAn7TeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:22:31.679446Z"},"content_sha256":"b19fa99da16b57a4d63e7b0ed7e1225623a4bfdff206f2a868824de5892c3242","schema_version":"1.0","event_id":"sha256:b19fa99da16b57a4d63e7b0ed7e1225623a4bfdff206f2a868824de5892c3242"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM/bundle.json","state_url":"https://pith.science/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM/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":"2026-08-08T09:22:31Z","links":{"resolver":"https://pith.science/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM","bundle":"https://pith.science/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM/bundle.json","state":"https://pith.science/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LVZYF2XWNM6K4KL2MJTYGR5AXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LVZYF2XWNM6K4KL2MJTYGR5AXM","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":"f6fd6feb1bb3d9aa1482dcc73e26cd88e92ca53f4416111af984ccf1890f10e5","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-08T05:23:50Z","title_canon_sha256":"b9114744e4a51af4b4d3f1282c1653552893cdbae7f1f61a67f62b786a98503a"},"schema_version":"1.0","source":{"id":"2312.04837","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04837","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04837v2","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04837","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"pith_short_12","alias_value":"LVZYF2XWNM6K","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"pith_short_16","alias_value":"LVZYF2XWNM6K4KL2","created_at":"2026-07-05T07:23:10Z"},{"alias_kind":"pith_short_8","alias_value":"LVZYF2XW","created_at":"2026-07-05T07:23:10Z"}],"graph_snapshots":[{"event_id":"sha256:b19fa99da16b57a4d63e7b0ed7e1225623a4bfdff206f2a868824de5892c3242","target":"graph","created_at":"2026-07-05T07:23:10Z","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/2312.04837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to \"point to\" and access specific regions within images. This capability is important not only to support reference-grounded VL benchmarks, but also, for practical applications that require precise within-image reasoning. We build Localized Visual Commonsense models, which allow users to specify (multiple) regions as input. We train our model by sampling localized comm","authors_text":"Ali Farhadi, Jack Hessel, Jae Sung Park, Jianfeng Gao, Khyathi Raghavi Chandu, Paul Pu Liang, Peter West, Qiuyuan Huang, Ximing Lu, Yejin Choi, Youngjae Yu","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-08T05:23:50Z","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04837","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:a84adf8dbcd57bd3c616de30fb8c7928b4b93874e79e35c226cfbe66850abe0e","target":"record","created_at":"2026-07-05T07:23:10Z","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":"f6fd6feb1bb3d9aa1482dcc73e26cd88e92ca53f4416111af984ccf1890f10e5","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-08T05:23:50Z","title_canon_sha256":"b9114744e4a51af4b4d3f1282c1653552893cdbae7f1f61a67f62b786a98503a"},"schema_version":"1.0","source":{"id":"2312.04837","kind":"arxiv","version":2}},"canonical_sha256":"5d7382eaf66b3cae297a62678347a0bb1f53d646d358cf64c64ce4a76b0ce1f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d7382eaf66b3cae297a62678347a0bb1f53d646d358cf64c64ce4a76b0ce1f6","first_computed_at":"2026-07-05T07:23:10.465578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:10.465578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXDX49DX0GHBbgkS2vgTGfIJ32/JLLjSJGfp0If9B30O7BvIBLxcwYmd7JalIdZTS/LN4nAfBY33kUvmq1cJDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:10.466041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04837","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a84adf8dbcd57bd3c616de30fb8c7928b4b93874e79e35c226cfbe66850abe0e","sha256:b19fa99da16b57a4d63e7b0ed7e1225623a4bfdff206f2a868824de5892c3242"],"state_sha256":"53adaf38d55ce9b4bf7e4ec2e284fff246ac0c190d9afe4640d2bb4654344591"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j88mwC9z1bwP5Pojtj++OjDsgSCu+MX95Q0rHDbeCmmd3xdBOc8rDw4ITorvJc94dXslP9Y0F9slSpoikxUmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:22:31.685252Z","bundle_sha256":"8a900575c97eb45cd0cb2314cfe15ed92625d38e657c9b59d517e72ba65ae46b"}}