{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3PIRTQXMSRYAJUPWCR3C3GRX7X","short_pith_number":"pith:3PIRTQXM","canonical_record":{"source":{"id":"2502.18512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-22T16:05:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b82f28db7992f0266e28af6a8628c44c6791c4f9efbc8f504590c9e6557b8060","abstract_canon_sha256":"6978b5fa71ca6347e91158761ac013330be07621b93248bf1df22ee13d5e1fa8"},"schema_version":"1.0"},"canonical_sha256":"dbd119c2ec947004d1f614762d9a37fdddb3f643888d1caba2a0dc3b6e813765","source":{"kind":"arxiv","id":"2502.18512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18512","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18512v1","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18512","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"3PIRTQXMSRYA","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"3PIRTQXMSRYAJUPW","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"3PIRTQXM","created_at":"2026-07-05T10:19:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3PIRTQXMSRYAJUPWCR3C3GRX7X","target":"record","payload":{"canonical_record":{"source":{"id":"2502.18512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-22T16:05:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b82f28db7992f0266e28af6a8628c44c6791c4f9efbc8f504590c9e6557b8060","abstract_canon_sha256":"6978b5fa71ca6347e91158761ac013330be07621b93248bf1df22ee13d5e1fa8"},"schema_version":"1.0"},"canonical_sha256":"dbd119c2ec947004d1f614762d9a37fdddb3f643888d1caba2a0dc3b6e813765","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:59.204200Z","signature_b64":"obifrDOak2VHdG24roS6MfRaYT5jAN7tYO1i5/7gXh5cwLp5p/bGXO22SSD11v8QfiiGTDt8CaQ/exL5pEUgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbd119c2ec947004d1f614762d9a37fdddb3f643888d1caba2a0dc3b6e813765","last_reissued_at":"2026-07-05T10:19:59.203626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:59.203626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.18512","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":"2026-07-05T10:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p16W4SR/qUi9Z9sBQviByW3aELLpZLKdckXgwwMIOUZLbE5TcbhyODhbtZUSAfjOTb6TWN6nsHfIy8JQhFPeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:36:59.750294Z"},"content_sha256":"6a4a17b459969beed8dccb942d737e4a3f3f49d9289f808b25e6d6f46fbd5b25","schema_version":"1.0","event_id":"sha256:6a4a17b459969beed8dccb942d737e4a3f3f49d9289f808b25e6d6f46fbd5b25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3PIRTQXMSRYAJUPWCR3C3GRX7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Tang, Gang Huang, Jianjian Li, Junquan Fan, Nian Xie, Shitao Zhu, Songlin Liu, Wulong Liu, Yong Liao","submitted_at":"2025-02-22T16:05:33Z","abstract_excerpt":"The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods exhibit serious performance degradation in tasks involving high-resolution, text-oriented image understanding and reasoning. In this paper, we propose an efficient visual token compression framework for text-oriented VLLMs in high-resolution scenarios. In particular, we employ a light-weight self-distillation pre-training stage to compress the visual tokens, req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18512","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/2502.18512/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":"2026-07-05T10:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SO78BsnZBYcDh/ImATzNXpPqMUHEABwdiVfAXbAy5pNIKE5g9mSTk+Wh0sFE96tWL6vQ5wQw6QeKysMui8wAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:36:59.750975Z"},"content_sha256":"b5ef77623797ed4f49e71030ec82132aa62da8408ca3a7922ab41c2894f4a7e1","schema_version":"1.0","event_id":"sha256:b5ef77623797ed4f49e71030ec82132aa62da8408ca3a7922ab41c2894f4a7e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X/bundle.json","state_url":"https://pith.science/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X/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":"2026-07-05T14:36:59Z","links":{"resolver":"https://pith.science/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X","bundle":"https://pith.science/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X/bundle.json","state":"https://pith.science/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3PIRTQXMSRYAJUPWCR3C3GRX7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3PIRTQXMSRYAJUPWCR3C3GRX7X","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":"6978b5fa71ca6347e91158761ac013330be07621b93248bf1df22ee13d5e1fa8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-22T16:05:33Z","title_canon_sha256":"b82f28db7992f0266e28af6a8628c44c6791c4f9efbc8f504590c9e6557b8060"},"schema_version":"1.0","source":{"id":"2502.18512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18512","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18512v1","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18512","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"3PIRTQXMSRYA","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"3PIRTQXMSRYAJUPW","created_at":"2026-07-05T10:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"3PIRTQXM","created_at":"2026-07-05T10:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:b5ef77623797ed4f49e71030ec82132aa62da8408ca3a7922ab41c2894f4a7e1","target":"graph","created_at":"2026-07-05T10:19:59Z","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/2502.18512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods exhibit serious performance degradation in tasks involving high-resolution, text-oriented image understanding and reasoning. In this paper, we propose an efficient visual token compression framework for text-oriented VLLMs in high-resolution scenarios. In particular, we employ a light-weight self-distillation pre-training stage to compress the visual tokens, req","authors_text":"Feng Tang, Gang Huang, Jianjian Li, Junquan Fan, Nian Xie, Shitao Zhu, Songlin Liu, Wulong Liu, Yong Liao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-22T16:05:33Z","title":"FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18512","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":"sha256:6a4a17b459969beed8dccb942d737e4a3f3f49d9289f808b25e6d6f46fbd5b25","target":"record","created_at":"2026-07-05T10:19:59Z","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":"6978b5fa71ca6347e91158761ac013330be07621b93248bf1df22ee13d5e1fa8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-22T16:05:33Z","title_canon_sha256":"b82f28db7992f0266e28af6a8628c44c6791c4f9efbc8f504590c9e6557b8060"},"schema_version":"1.0","source":{"id":"2502.18512","kind":"arxiv","version":1}},"canonical_sha256":"dbd119c2ec947004d1f614762d9a37fdddb3f643888d1caba2a0dc3b6e813765","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbd119c2ec947004d1f614762d9a37fdddb3f643888d1caba2a0dc3b6e813765","first_computed_at":"2026-07-05T10:19:59.203626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:59.203626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"obifrDOak2VHdG24roS6MfRaYT5jAN7tYO1i5/7gXh5cwLp5p/bGXO22SSD11v8QfiiGTDt8CaQ/exL5pEUgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:59.204200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a4a17b459969beed8dccb942d737e4a3f3f49d9289f808b25e6d6f46fbd5b25","sha256:b5ef77623797ed4f49e71030ec82132aa62da8408ca3a7922ab41c2894f4a7e1"],"state_sha256":"28c7ed05be049d3cf4e404623f8c1e577e515deb804faddcc782e691a15a3e81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ytkxTt46lYi3NzNDNcEufCnoC/JF1SgP3vM2JC9UiRicLP4sNeDiiytqhqU9tGg2z29iXDg4l15yHOBrD3XoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:36:59.755533Z","bundle_sha256":"46b38d3eb2f0052e2689012875390c67df0e16b463479b5803ee46496c4f5e38"}}