{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LIYE5LFE7R4NARDPNF756JUQJ4","short_pith_number":"pith:LIYE5LFE","canonical_record":{"source":{"id":"2312.09237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:57:58Z","cross_cats_sorted":[],"title_canon_sha256":"dace7bec2505e78a018dd9915a1d57a07d7beee1d152950e3c962fe21b84d7e7","abstract_canon_sha256":"6df7540e3123e9797fec2151988150c16e1575ac7b959a778c8c4f9872b42300"},"schema_version":"1.0"},"canonical_sha256":"5a304eaca4fc78d0446f697fdf26904f01cdaf79ae50e2c2b8a617753fb152bd","source":{"kind":"arxiv","id":"2312.09237","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09237","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09237v1","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09237","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_12","alias_value":"LIYE5LFE7R4N","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_16","alias_value":"LIYE5LFE7R4NARDP","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_8","alias_value":"LIYE5LFE","created_at":"2026-07-05T07:24:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LIYE5LFE7R4NARDPNF756JUQJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2312.09237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:57:58Z","cross_cats_sorted":[],"title_canon_sha256":"dace7bec2505e78a018dd9915a1d57a07d7beee1d152950e3c962fe21b84d7e7","abstract_canon_sha256":"6df7540e3123e9797fec2151988150c16e1575ac7b959a778c8c4f9872b42300"},"schema_version":"1.0"},"canonical_sha256":"5a304eaca4fc78d0446f697fdf26904f01cdaf79ae50e2c2b8a617753fb152bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:16.327618Z","signature_b64":"AUHJG3JaUp3kE6DYqZAaOldiM3WIYjVhtS885YD1Fuf+HNauXKZbetdqjFjrQwsZvL/6SN7x8opd7/W7APoYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a304eaca4fc78d0446f697fdf26904f01cdaf79ae50e2c2b8a617753fb152bd","last_reissued_at":"2026-07-05T07:24:16.327123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:16.327123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.09237","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":"2026-07-05T07:24:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLl/7aN8br9AbCrUpkK/XZVzLjylrBN0Avv26PYOoTo9y7T6iR8MmF9Sz3TBx6lIx7E2u5V5DHqExYYMt5uEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:38:24.945964Z"},"content_sha256":"80914e3d2205fc02fe8b83da3a3ade522edc109b05327214a07e1a24f6f529b7","schema_version":"1.0","event_id":"sha256:80914e3d2205fc02fe8b83da3a3ade522edc109b05327214a07e1a24f6f529b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LIYE5LFE7R4NARDPNF756JUQJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pixel Aligned Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Chen Sun, Cordelia Schmid, Jiarui Xu, Shen Yan, Xiaolong Wang, Xingyi Zhou, Xiuye Gu","submitted_at":"2023-12-14T18:57:58Z","abstract_excerpt":"Large language models have achieved great success in recent years, so as their variants in vision. Existing vision-language models can describe images in natural languages, answer visual-related questions, or perform complex reasoning about the image. However, it is yet unclear how localization tasks, such as word grounding or referring localization, can be performed using large language models. In this work, we aim to develop a vision-language model that can take locations, for example, a set of points or boxes, as either inputs or outputs. When taking locations as inputs, the model performs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09237","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/2312.09237/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":"2026-07-05T07:24:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CvOqDmcJpylMR5YNGCip1d+VB1rRFMiX31vMs5bHRKTUddqYt50AdF1zfRMdNG8xSGV0n5wmNvayIm5gcusDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:38:24.946550Z"},"content_sha256":"fa0a101d402d8042b82a18c2680d40c94ad403ab654dd1a1529343a124511bc0","schema_version":"1.0","event_id":"sha256:fa0a101d402d8042b82a18c2680d40c94ad403ab654dd1a1529343a124511bc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIYE5LFE7R4NARDPNF756JUQJ4/bundle.json","state_url":"https://pith.science/pith/LIYE5LFE7R4NARDPNF756JUQJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIYE5LFE7R4NARDPNF756JUQJ4/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":"2026-08-09T17:38:24Z","links":{"resolver":"https://pith.science/pith/LIYE5LFE7R4NARDPNF756JUQJ4","bundle":"https://pith.science/pith/LIYE5LFE7R4NARDPNF756JUQJ4/bundle.json","state":"https://pith.science/pith/LIYE5LFE7R4NARDPNF756JUQJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIYE5LFE7R4NARDPNF756JUQJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LIYE5LFE7R4NARDPNF756JUQJ4","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":"6df7540e3123e9797fec2151988150c16e1575ac7b959a778c8c4f9872b42300","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:57:58Z","title_canon_sha256":"dace7bec2505e78a018dd9915a1d57a07d7beee1d152950e3c962fe21b84d7e7"},"schema_version":"1.0","source":{"id":"2312.09237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09237","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09237v1","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09237","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_12","alias_value":"LIYE5LFE7R4N","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_16","alias_value":"LIYE5LFE7R4NARDP","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_8","alias_value":"LIYE5LFE","created_at":"2026-07-05T07:24:16Z"}],"graph_snapshots":[{"event_id":"sha256:fa0a101d402d8042b82a18c2680d40c94ad403ab654dd1a1529343a124511bc0","target":"graph","created_at":"2026-07-05T07:24:16Z","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/2312.09237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have achieved great success in recent years, so as their variants in vision. Existing vision-language models can describe images in natural languages, answer visual-related questions, or perform complex reasoning about the image. However, it is yet unclear how localization tasks, such as word grounding or referring localization, can be performed using large language models. In this work, we aim to develop a vision-language model that can take locations, for example, a set of points or boxes, as either inputs or outputs. When taking locations as inputs, the model performs ","authors_text":"Anurag Arnab, Chen Sun, Cordelia Schmid, Jiarui Xu, Shen Yan, Xiaolong Wang, Xingyi Zhou, Xiuye Gu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:57:58Z","title":"Pixel Aligned Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09237","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":"sha256:80914e3d2205fc02fe8b83da3a3ade522edc109b05327214a07e1a24f6f529b7","target":"record","created_at":"2026-07-05T07:24:16Z","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":"6df7540e3123e9797fec2151988150c16e1575ac7b959a778c8c4f9872b42300","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:57:58Z","title_canon_sha256":"dace7bec2505e78a018dd9915a1d57a07d7beee1d152950e3c962fe21b84d7e7"},"schema_version":"1.0","source":{"id":"2312.09237","kind":"arxiv","version":1}},"canonical_sha256":"5a304eaca4fc78d0446f697fdf26904f01cdaf79ae50e2c2b8a617753fb152bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a304eaca4fc78d0446f697fdf26904f01cdaf79ae50e2c2b8a617753fb152bd","first_computed_at":"2026-07-05T07:24:16.327123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:16.327123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AUHJG3JaUp3kE6DYqZAaOldiM3WIYjVhtS885YD1Fuf+HNauXKZbetdqjFjrQwsZvL/6SN7x8opd7/W7APoYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:16.327618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80914e3d2205fc02fe8b83da3a3ade522edc109b05327214a07e1a24f6f529b7","sha256:fa0a101d402d8042b82a18c2680d40c94ad403ab654dd1a1529343a124511bc0"],"state_sha256":"d4193c0d6abd75771136ad79ac7c86142b3d504241c4435afb451ac0535d8dd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XvPRKOJqTHpH5WpG7oTVx9LGanoXL9IwJBhaa23vdNHmfmOmoHOXjlwNKMMgbj6ft7vxSywQbG5T2BOVXIV/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:38:24.950793Z","bundle_sha256":"3a508fbabd2bc1b270741860d617267456762587f3a8ea55e09e51643476200f"}}