{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NDEFTV343FK2LA7WBRYF4JPOB5","short_pith_number":"pith:NDEFTV34","canonical_record":{"source":{"id":"2401.12503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T05:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"e718fe1f07ca3e3a9d1d0d8a86769dcbf576e512d75ebe47e88ac244b8193dbd","abstract_canon_sha256":"935e4143a886cd09757caea3303d25a845a68eacef294c38b98e7278c7f6f994"},"schema_version":"1.0"},"canonical_sha256":"68c859d77cd955a583f60c705e25ee0f556057a8ec26bbd4eea1128389a67995","source":{"kind":"arxiv","id":"2401.12503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12503","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12503v1","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12503","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"NDEFTV343FK2","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"NDEFTV343FK2LA7W","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"NDEFTV34","created_at":"2026-07-05T07:36:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NDEFTV343FK2LA7WBRYF4JPOB5","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T05:55:26Z","cross_cats_sorted":[],"title_canon_sha256":"e718fe1f07ca3e3a9d1d0d8a86769dcbf576e512d75ebe47e88ac244b8193dbd","abstract_canon_sha256":"935e4143a886cd09757caea3303d25a845a68eacef294c38b98e7278c7f6f994"},"schema_version":"1.0"},"canonical_sha256":"68c859d77cd955a583f60c705e25ee0f556057a8ec26bbd4eea1128389a67995","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:31.666030Z","signature_b64":"OCCwWZt7O+v1rUk8s4treqyX51/n11RCaeJsR+i/FsS9Icz0TP9mjjbu+eqwuPc8YH2O2ErYWEiZpeAeKv49Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68c859d77cd955a583f60c705e25ee0f556057a8ec26bbd4eea1128389a67995","last_reissued_at":"2026-07-05T07:36:31.665589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:31.665589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12503","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":"2026-07-05T07:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0cu24+UMNTrRfoYTxRB+TDLVWuMCpK4KoiRCIVPDpHaNJknA+uCYBQBkG21MCAGILwCEKkJ5W7gx0WvIUKRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:20:23.405340Z"},"content_sha256":"8e778538592ed900567b9e0291166f52b881d94aa3efe0f26072289a69ca85f4","schema_version":"1.0","event_id":"sha256:8e778538592ed900567b9e0291166f52b881d94aa3efe0f26072289a69ca85f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NDEFTV343FK2LA7WBRYF4JPOB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Small Language Model Meets with Reinforced Vision Vocabulary","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunrui Han, En Yu, Haoran Wei, Jianjian Sun, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge","submitted_at":"2024-01-23T05:55:26Z","abstract_excerpt":"Playing Large Vision Language Models (LVLMs) in 2023 is trendy among the AI community. However, the relatively large number of parameters (more than 7B) of popular LVLMs makes it difficult to train and deploy on consumer GPUs, discouraging many researchers with limited resources. Imagine how cool it would be to experience all the features of current LVLMs on an old GTX1080ti (our only game card). Accordingly, we present Vary-toy in this report, a small-size Vary along with Qwen-1.8B as the base ``large'' language model. In Vary-toy, we introduce an improved vision vocabulary, allowing the mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12503","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/2401.12503/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":"2026-07-05T07:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WNiA7oItmLB6ZkiGBx6z38fqxhlDbgesgtsEkCu82TkhSzpOmmY+lULVm7sq7Y5ZmF3E5Fs1eFKH5h3jCeonCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:20:23.405860Z"},"content_sha256":"24a71aee983d3161021de1f8799d58419188f892aa25e374b1d6773ff31e11da","schema_version":"1.0","event_id":"sha256:24a71aee983d3161021de1f8799d58419188f892aa25e374b1d6773ff31e11da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDEFTV343FK2LA7WBRYF4JPOB5/bundle.json","state_url":"https://pith.science/pith/NDEFTV343FK2LA7WBRYF4JPOB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDEFTV343FK2LA7WBRYF4JPOB5/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":"2026-08-06T07:20:23Z","links":{"resolver":"https://pith.science/pith/NDEFTV343FK2LA7WBRYF4JPOB5","bundle":"https://pith.science/pith/NDEFTV343FK2LA7WBRYF4JPOB5/bundle.json","state":"https://pith.science/pith/NDEFTV343FK2LA7WBRYF4JPOB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDEFTV343FK2LA7WBRYF4JPOB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDEFTV343FK2LA7WBRYF4JPOB5","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":"935e4143a886cd09757caea3303d25a845a68eacef294c38b98e7278c7f6f994","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T05:55:26Z","title_canon_sha256":"e718fe1f07ca3e3a9d1d0d8a86769dcbf576e512d75ebe47e88ac244b8193dbd"},"schema_version":"1.0","source":{"id":"2401.12503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12503","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12503v1","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12503","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"NDEFTV343FK2","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"NDEFTV343FK2LA7W","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"NDEFTV34","created_at":"2026-07-05T07:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:24a71aee983d3161021de1f8799d58419188f892aa25e374b1d6773ff31e11da","target":"graph","created_at":"2026-07-05T07:36:31Z","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/2401.12503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Playing Large Vision Language Models (LVLMs) in 2023 is trendy among the AI community. However, the relatively large number of parameters (more than 7B) of popular LVLMs makes it difficult to train and deploy on consumer GPUs, discouraging many researchers with limited resources. Imagine how cool it would be to experience all the features of current LVLMs on an old GTX1080ti (our only game card). Accordingly, we present Vary-toy in this report, a small-size Vary along with Qwen-1.8B as the base ``large'' language model. In Vary-toy, we introduce an improved vision vocabulary, allowing the mode","authors_text":"Chunrui Han, En Yu, Haoran Wei, Jianjian Sun, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T05:55:26Z","title":"Small Language Model Meets with Reinforced Vision Vocabulary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12503","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":"sha256:8e778538592ed900567b9e0291166f52b881d94aa3efe0f26072289a69ca85f4","target":"record","created_at":"2026-07-05T07:36:31Z","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":"935e4143a886cd09757caea3303d25a845a68eacef294c38b98e7278c7f6f994","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T05:55:26Z","title_canon_sha256":"e718fe1f07ca3e3a9d1d0d8a86769dcbf576e512d75ebe47e88ac244b8193dbd"},"schema_version":"1.0","source":{"id":"2401.12503","kind":"arxiv","version":1}},"canonical_sha256":"68c859d77cd955a583f60c705e25ee0f556057a8ec26bbd4eea1128389a67995","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68c859d77cd955a583f60c705e25ee0f556057a8ec26bbd4eea1128389a67995","first_computed_at":"2026-07-05T07:36:31.665589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:31.665589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OCCwWZt7O+v1rUk8s4treqyX51/n11RCaeJsR+i/FsS9Icz0TP9mjjbu+eqwuPc8YH2O2ErYWEiZpeAeKv49Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:31.666030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e778538592ed900567b9e0291166f52b881d94aa3efe0f26072289a69ca85f4","sha256:24a71aee983d3161021de1f8799d58419188f892aa25e374b1d6773ff31e11da"],"state_sha256":"c04eb50c525767030a31fb30e35ea3c9fea720e52aebc8389ec5b1473f8a89d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7St8fsrPcrVmJs8vUqGMqvDFxOTp6ltyzfTDotjplfA+dS5lvD4c/SaetgLWejd6Mr7l3fg0Kn2uwJE1Iw43CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:20:23.412547Z","bundle_sha256":"835cff7f59e2ed5c1b246a5482af41ef433e5b7a0bf879fe4e4708730a48c32c"}}