{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FRVIVM4OFU3YYEBD425EMZMTUF","short_pith_number":"pith:FRVIVM4O","canonical_record":{"source":{"id":"2505.08910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T19:01:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f564110db8b00fdde36f0d6079aeb52810401e6780f40c2b3c9205a48ce6376","abstract_canon_sha256":"72dc47a3931b78382567083baa135049c4159f698b446657da475156a7e7b3c7"},"schema_version":"1.0"},"canonical_sha256":"2c6a8ab38e2d378c1023e6ba466593a14afc956feb33eb02cae466bde431a789","source":{"kind":"arxiv","id":"2505.08910","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08910","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08910v2","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08910","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"FRVIVM4OFU3Y","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"FRVIVM4OFU3YYEBD","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"FRVIVM4O","created_at":"2026-07-05T11:03:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FRVIVM4OFU3YYEBD425EMZMTUF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T19:01:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f564110db8b00fdde36f0d6079aeb52810401e6780f40c2b3c9205a48ce6376","abstract_canon_sha256":"72dc47a3931b78382567083baa135049c4159f698b446657da475156a7e7b3c7"},"schema_version":"1.0"},"canonical_sha256":"2c6a8ab38e2d378c1023e6ba466593a14afc956feb33eb02cae466bde431a789","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:25.049061Z","signature_b64":"uuakjuRf8xieEujvnxGA/0DOQPRmXyyKK/dMDkx4BOhEl/jyTakE8LjONwckyHLvNHG9EJJOMD2ohl8kP3D6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6a8ab38e2d378c1023e6ba466593a14afc956feb33eb02cae466bde431a789","last_reissued_at":"2026-07-05T11:03:25.048488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:25.048488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08910","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":"2026-07-05T11:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TbK43wBNeArtSMiAwrN4A4fZzJkcT6iJ1dN6dcKXnzuAPS7EhN1oH5gGZB4iA6+3Pb2tl+5p4CDwYrGDmQ0UBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:06:11.069242Z"},"content_sha256":"bafbb874b962b009b201b4558435024e8bd623fb143474df9c3c3bd40140fb40","schema_version":"1.0","event_id":"sha256:bafbb874b962b009b201b4558435024e8bd623fb143474df9c3c3bd40140fb40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FRVIVM4OFU3YYEBD425EMZMTUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Behind Maya: Building a Multilingual Vision Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhipsha Das, Alham Fikri Aji, Anthony Susevski, Ashvanth.S, Bala Krishna S Vegesna, Chen Liu, Drishti Sharma, Genta Indra Winata, Isha Chaturvedi, Karthik Reddy Kanjula, Nahid Alam, Roshan Santhosh, Ryan Sze-Yin Chan, Shayekh Bin Islam, S M Iftekhar Uddin, Snegha A, Snehanshu Mukherjee, Surya Guthikonda, Timothy Chung","submitted_at":"2025-05-13T19:01:12Z","abstract_excerpt":"In recent times, we have seen a rapid development of large Vision-Language Models (VLMs). They have shown impressive results on academic benchmarks, primarily in widely spoken languages but lack performance on low-resource languages and varied cultural contexts. To address these limitations, we introduce Maya, an open-source Multilingual VLM. Our contributions are: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; and 2) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in visio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08910","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/2505.08910/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":"2026-07-05T11:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"juqbEo/rSYOhfFgN4awJljUNt0fVwj9fqCXoe5LYuMuhrztiAjhYsNPKkXWeyu3OHGxIUxV4ZdUd4ilvnBJvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:06:11.069634Z"},"content_sha256":"f2c73f32bb7fbbc1d44ee8dfaea4b0c7d799dd686a0a0290b4cb54e3778b8ac2","schema_version":"1.0","event_id":"sha256:f2c73f32bb7fbbc1d44ee8dfaea4b0c7d799dd686a0a0290b4cb54e3778b8ac2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRVIVM4OFU3YYEBD425EMZMTUF/bundle.json","state_url":"https://pith.science/pith/FRVIVM4OFU3YYEBD425EMZMTUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRVIVM4OFU3YYEBD425EMZMTUF/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":"2026-07-07T14:06:11Z","links":{"resolver":"https://pith.science/pith/FRVIVM4OFU3YYEBD425EMZMTUF","bundle":"https://pith.science/pith/FRVIVM4OFU3YYEBD425EMZMTUF/bundle.json","state":"https://pith.science/pith/FRVIVM4OFU3YYEBD425EMZMTUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRVIVM4OFU3YYEBD425EMZMTUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FRVIVM4OFU3YYEBD425EMZMTUF","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":"72dc47a3931b78382567083baa135049c4159f698b446657da475156a7e7b3c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T19:01:12Z","title_canon_sha256":"4f564110db8b00fdde36f0d6079aeb52810401e6780f40c2b3c9205a48ce6376"},"schema_version":"1.0","source":{"id":"2505.08910","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08910","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08910v2","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08910","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"FRVIVM4OFU3Y","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"FRVIVM4OFU3YYEBD","created_at":"2026-07-05T11:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"FRVIVM4O","created_at":"2026-07-05T11:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:f2c73f32bb7fbbc1d44ee8dfaea4b0c7d799dd686a0a0290b4cb54e3778b8ac2","target":"graph","created_at":"2026-07-05T11:03:25Z","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/2505.08910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent times, we have seen a rapid development of large Vision-Language Models (VLMs). They have shown impressive results on academic benchmarks, primarily in widely spoken languages but lack performance on low-resource languages and varied cultural contexts. To address these limitations, we introduce Maya, an open-source Multilingual VLM. Our contributions are: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; and 2) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in visio","authors_text":"Abhipsha Das, Alham Fikri Aji, Anthony Susevski, Ashvanth.S, Bala Krishna S Vegesna, Chen Liu, Drishti Sharma, Genta Indra Winata, Isha Chaturvedi, Karthik Reddy Kanjula, Nahid Alam, Roshan Santhosh, Ryan Sze-Yin Chan, Shayekh Bin Islam, S M Iftekhar Uddin, Snegha A, Snehanshu Mukherjee, Surya Guthikonda, Timothy Chung","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T19:01:12Z","title":"Behind Maya: Building a Multilingual Vision Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08910","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:bafbb874b962b009b201b4558435024e8bd623fb143474df9c3c3bd40140fb40","target":"record","created_at":"2026-07-05T11:03:25Z","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":"72dc47a3931b78382567083baa135049c4159f698b446657da475156a7e7b3c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-13T19:01:12Z","title_canon_sha256":"4f564110db8b00fdde36f0d6079aeb52810401e6780f40c2b3c9205a48ce6376"},"schema_version":"1.0","source":{"id":"2505.08910","kind":"arxiv","version":2}},"canonical_sha256":"2c6a8ab38e2d378c1023e6ba466593a14afc956feb33eb02cae466bde431a789","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c6a8ab38e2d378c1023e6ba466593a14afc956feb33eb02cae466bde431a789","first_computed_at":"2026-07-05T11:03:25.048488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:25.048488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uuakjuRf8xieEujvnxGA/0DOQPRmXyyKK/dMDkx4BOhEl/jyTakE8LjONwckyHLvNHG9EJJOMD2ohl8kP3D6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:25.049061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08910","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bafbb874b962b009b201b4558435024e8bd623fb143474df9c3c3bd40140fb40","sha256:f2c73f32bb7fbbc1d44ee8dfaea4b0c7d799dd686a0a0290b4cb54e3778b8ac2"],"state_sha256":"f31549a07fff0b208bcbe6a096977d59911841ba1e63ea3bdb56139165ab7d17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBTdtkeaXd8CJVXJrw4IpB0oY6xmnYdFiVCXdr7KnfSuDZ59VE/FBU7Fu2E0w/w6tFL/sJX2jvwBM7D35vmEBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:06:11.071551Z","bundle_sha256":"3c3dcdf233265397697025ce99475c30c40ce9542c884481b0b35110bc15566f"}}