{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B3O45SHHFEPCQESVICYTUSZAKM","short_pith_number":"pith:B3O45SHH","canonical_record":{"source":{"id":"2501.03895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T16:03:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eeae5623defa9558469697e02bc356b32586b91ca0199f536ff0326104c3e498","abstract_canon_sha256":"59e5b28c08699475212126ff4b19f5eae025e8073bc1f980519ac6853339c390"},"schema_version":"1.0"},"canonical_sha256":"0eddcec8e7291e28125540b13a4b20530ce4951e287a90082f70d328012cb718","source":{"kind":"arxiv","id":"2501.03895","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03895","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03895v2","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03895","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"B3O45SHHFEPC","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"B3O45SHHFEPCQESV","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"B3O45SHH","created_at":"2026-07-05T10:22:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B3O45SHHFEPCQESVICYTUSZAKM","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T16:03:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eeae5623defa9558469697e02bc356b32586b91ca0199f536ff0326104c3e498","abstract_canon_sha256":"59e5b28c08699475212126ff4b19f5eae025e8073bc1f980519ac6853339c390"},"schema_version":"1.0"},"canonical_sha256":"0eddcec8e7291e28125540b13a4b20530ce4951e287a90082f70d328012cb718","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:11.716224Z","signature_b64":"qNPChSFwhTAOiVDWIuAlJnWbkRxFcFZl54f8f9lYt7ZmoWSLBUYBYD4RZ8fmAga1z4vA89dUFTQjQk3zxwjWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eddcec8e7291e28125540b13a4b20530ce4951e287a90082f70d328012cb718","last_reissued_at":"2026-07-05T10:22:11.715690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:11.715690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03895","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":"2026-07-05T10:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5qbT0O7skyts1rXiwyL3s/nA+7RI1DgdCmLTIL2k7CnqQXbodts5Stq7jvVDhUwrjiW4Kaw9I5/aCKOI+D2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:32:03.716469Z"},"content_sha256":"7fa21562100cdc210d2f79b969d9a19313d891e8d69ded5f9ad73809fbdc07c7","schema_version":"1.0","event_id":"sha256:7fa21562100cdc210d2f79b969d9a19313d891e8d69ded5f9ad73809fbdc07c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B3O45SHHFEPCQESVICYTUSZAKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Qingkai Fang, Shaolei Zhang, Yang Feng, Zhe Yang","submitted_at":"2025-01-07T16:03:14Z","abstract_excerpt":"The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and textual instructions into the context of large language models (LLMs), where large-scale parameters and numerous context tokens (predominantly vision tokens) result in substantial computational overhead. Previous efforts towards efficient LMMs always focus on replacing the LLM backbone with smaller models, while neglecting the crucial issue of token quantity. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03895","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/2501.03895/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":"2026-07-05T10:22:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xB6+gkqi4c+30YfAVb5neKHdnh1gnI47Itbkp1vLGaXnE629QzaXj4pG3F03hvjc8G35aVSWxnWxg1NgVPU+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:32:03.716977Z"},"content_sha256":"d52e64df812288119e3c8777b2be1ccf3ce0c3611426df31d89732d20afe8ef0","schema_version":"1.0","event_id":"sha256:d52e64df812288119e3c8777b2be1ccf3ce0c3611426df31d89732d20afe8ef0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3O45SHHFEPCQESVICYTUSZAKM/bundle.json","state_url":"https://pith.science/pith/B3O45SHHFEPCQESVICYTUSZAKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3O45SHHFEPCQESVICYTUSZAKM/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":"2026-08-11T18:32:03Z","links":{"resolver":"https://pith.science/pith/B3O45SHHFEPCQESVICYTUSZAKM","bundle":"https://pith.science/pith/B3O45SHHFEPCQESVICYTUSZAKM/bundle.json","state":"https://pith.science/pith/B3O45SHHFEPCQESVICYTUSZAKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3O45SHHFEPCQESVICYTUSZAKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B3O45SHHFEPCQESVICYTUSZAKM","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":"59e5b28c08699475212126ff4b19f5eae025e8073bc1f980519ac6853339c390","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T16:03:14Z","title_canon_sha256":"eeae5623defa9558469697e02bc356b32586b91ca0199f536ff0326104c3e498"},"schema_version":"1.0","source":{"id":"2501.03895","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03895","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03895v2","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03895","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"B3O45SHHFEPC","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"B3O45SHHFEPCQESV","created_at":"2026-07-05T10:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"B3O45SHH","created_at":"2026-07-05T10:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:d52e64df812288119e3c8777b2be1ccf3ce0c3611426df31d89732d20afe8ef0","target":"graph","created_at":"2026-07-05T10:22:11Z","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/2501.03895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and textual instructions into the context of large language models (LLMs), where large-scale parameters and numerous context tokens (predominantly vision tokens) result in substantial computational overhead. Previous efforts towards efficient LMMs always focus on replacing the LLM backbone with smaller models, while neglecting the crucial issue of token quantity. I","authors_text":"Qingkai Fang, Shaolei Zhang, Yang Feng, Zhe Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T16:03:14Z","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03895","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":"sha256:7fa21562100cdc210d2f79b969d9a19313d891e8d69ded5f9ad73809fbdc07c7","target":"record","created_at":"2026-07-05T10:22:11Z","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":"59e5b28c08699475212126ff4b19f5eae025e8073bc1f980519ac6853339c390","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T16:03:14Z","title_canon_sha256":"eeae5623defa9558469697e02bc356b32586b91ca0199f536ff0326104c3e498"},"schema_version":"1.0","source":{"id":"2501.03895","kind":"arxiv","version":2}},"canonical_sha256":"0eddcec8e7291e28125540b13a4b20530ce4951e287a90082f70d328012cb718","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0eddcec8e7291e28125540b13a4b20530ce4951e287a90082f70d328012cb718","first_computed_at":"2026-07-05T10:22:11.715690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:11.715690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNPChSFwhTAOiVDWIuAlJnWbkRxFcFZl54f8f9lYt7ZmoWSLBUYBYD4RZ8fmAga1z4vA89dUFTQjQk3zxwjWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:11.716224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03895","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fa21562100cdc210d2f79b969d9a19313d891e8d69ded5f9ad73809fbdc07c7","sha256:d52e64df812288119e3c8777b2be1ccf3ce0c3611426df31d89732d20afe8ef0"],"state_sha256":"36539798b139c920bb19ddd0cc80e21d47903448b66db58787a6bbcba5e592fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wv75+uMjPsAwnWaVXtij1JUTdzqM+NgGwYbT4WUgHwpFXuqzNnVRg4wJG/MOuNbh19Dda3DZjZhCmKOWayQjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:32:03.723610Z","bundle_sha256":"e8b1924ca83a1ef05fd7fb4d43c13ba5dea9e5a694c34720449f757f81f027ac"}}