{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:S6YGWZU4D7F3H6LEEIEVW4OE6Z","short_pith_number":"pith:S6YGWZU4","canonical_record":{"source":{"id":"2504.19627","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T09:39:07Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"b15837f8a1fb6b3d663b788669c9b952ff688bd6a7da38727c1e34b6318c43d0","abstract_canon_sha256":"2277f7ca6c2d74d91858991609b15db79cfbd2df66f802521b8eaed62b0a9f23"},"schema_version":"1.0"},"canonical_sha256":"97b06b669c1fcbb3f96422095b71c4f67e63599807682698d239a44dc346d270","source":{"kind":"arxiv","id":"2504.19627","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19627","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19627v2","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19627","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"S6YGWZU4D7F3","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"S6YGWZU4D7F3H6LE","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"S6YGWZU4","created_at":"2026-07-05T11:05:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:S6YGWZU4D7F3H6LEEIEVW4OE6Z","target":"record","payload":{"canonical_record":{"source":{"id":"2504.19627","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T09:39:07Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"b15837f8a1fb6b3d663b788669c9b952ff688bd6a7da38727c1e34b6318c43d0","abstract_canon_sha256":"2277f7ca6c2d74d91858991609b15db79cfbd2df66f802521b8eaed62b0a9f23"},"schema_version":"1.0"},"canonical_sha256":"97b06b669c1fcbb3f96422095b71c4f67e63599807682698d239a44dc346d270","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:24.386141Z","signature_b64":"cVsGHTq6GeuWXz8cuZCoubpCGs6ys73ChvZtOYeYZDslbMBOlVeOmfg9ebtoaypB+j7LPhZB0XagRjIDNbjIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97b06b669c1fcbb3f96422095b71c4f67e63599807682698d239a44dc346d270","last_reissued_at":"2026-07-05T11:05:24.385645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:24.385645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.19627","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":"2026-07-05T11:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1sAr9Ksv/1AEVDn1zmgW7gS23q/jCtT+gMt34IlsuLBiThcqrOiiQ64YVIUQoC/t0rCwa9D4gJ0/LIwIoWRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:36:21.298521Z"},"content_sha256":"45621e74d46842e2f4841df0ecd63533b629618fdb7ee664b1e124c872c0cbf6","schema_version":"1.0","event_id":"sha256:45621e74d46842e2f4841df0ecd63533b629618fdb7ee664b1e124c872c0cbf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:S6YGWZU4D7F3H6LEEIEVW4OE6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Longze Chen, Lu Wang, Min Yang, Renke Shan, Run Luo, Xiaobo Xia, Ziqiang Liu","submitted_at":"2025-04-28T09:39:07Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) are pivotal for real-world AI tasks like embodied intelligence due to their strong vision-language reasoning abilities. However, current LVLMs process entire images at the token level, which is inefficient compared to humans who analyze information and generate content at the conceptual level, extracting relevant visual concepts with minimal effort. This inefficiency, stemming from the lack of a visual concept model, limits LVLMs' usability in real-world applications. To address this, we propose VCM, an end-to-end self-supervised visual concept modeling fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19627","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/2504.19627/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":"2026-07-05T11:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3aQ+n/HqKkBn0+dDjSd7bW1uyZIAQmUw4nKOudkMwLpRZ8U7dsNs+OZWsLglCEHm7iCc3T6PrUV1DhpED0e3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:36:21.299547Z"},"content_sha256":"83c506180b75c9a7c586f3b377971c722fc44ed64c466fef727f1efe3930082f","schema_version":"1.0","event_id":"sha256:83c506180b75c9a7c586f3b377971c722fc44ed64c466fef727f1efe3930082f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z/bundle.json","state_url":"https://pith.science/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z/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":"2026-08-17T17:36:21Z","links":{"resolver":"https://pith.science/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z","bundle":"https://pith.science/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z/bundle.json","state":"https://pith.science/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6YGWZU4D7F3H6LEEIEVW4OE6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S6YGWZU4D7F3H6LEEIEVW4OE6Z","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":"2277f7ca6c2d74d91858991609b15db79cfbd2df66f802521b8eaed62b0a9f23","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T09:39:07Z","title_canon_sha256":"b15837f8a1fb6b3d663b788669c9b952ff688bd6a7da38727c1e34b6318c43d0"},"schema_version":"1.0","source":{"id":"2504.19627","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19627","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19627v2","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19627","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"S6YGWZU4D7F3","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"S6YGWZU4D7F3H6LE","created_at":"2026-07-05T11:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"S6YGWZU4","created_at":"2026-07-05T11:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:83c506180b75c9a7c586f3b377971c722fc44ed64c466fef727f1efe3930082f","target":"graph","created_at":"2026-07-05T11:05:24Z","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/2504.19627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) are pivotal for real-world AI tasks like embodied intelligence due to their strong vision-language reasoning abilities. However, current LVLMs process entire images at the token level, which is inefficient compared to humans who analyze information and generate content at the conceptual level, extracting relevant visual concepts with minimal effort. This inefficiency, stemming from the lack of a visual concept model, limits LVLMs' usability in real-world applications. To address this, we propose VCM, an end-to-end self-supervised visual concept modeling fra","authors_text":"Longze Chen, Lu Wang, Min Yang, Renke Shan, Run Luo, Xiaobo Xia, Ziqiang Liu","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T09:39:07Z","title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19627","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":"sha256:45621e74d46842e2f4841df0ecd63533b629618fdb7ee664b1e124c872c0cbf6","target":"record","created_at":"2026-07-05T11:05:24Z","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":"2277f7ca6c2d74d91858991609b15db79cfbd2df66f802521b8eaed62b0a9f23","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T09:39:07Z","title_canon_sha256":"b15837f8a1fb6b3d663b788669c9b952ff688bd6a7da38727c1e34b6318c43d0"},"schema_version":"1.0","source":{"id":"2504.19627","kind":"arxiv","version":2}},"canonical_sha256":"97b06b669c1fcbb3f96422095b71c4f67e63599807682698d239a44dc346d270","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97b06b669c1fcbb3f96422095b71c4f67e63599807682698d239a44dc346d270","first_computed_at":"2026-07-05T11:05:24.385645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:24.385645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cVsGHTq6GeuWXz8cuZCoubpCGs6ys73ChvZtOYeYZDslbMBOlVeOmfg9ebtoaypB+j7LPhZB0XagRjIDNbjIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:24.386141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19627","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45621e74d46842e2f4841df0ecd63533b629618fdb7ee664b1e124c872c0cbf6","sha256:83c506180b75c9a7c586f3b377971c722fc44ed64c466fef727f1efe3930082f"],"state_sha256":"ab70d357b2a0e7b0601e0b5ae69e7c9b16c0119c414b436f3555c1b3259f6944"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EwkVeU0mpX2uAqcqNlH5U8Kr5MGbARu/TSjcgCvc//nBS54X/D+QzGsfxRUqsAM2+iOXq07SCoiK8sO7LtJXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:36:21.305362Z","bundle_sha256":"75b5dfe3c753524d316aadb4ed0c9c8959bdf55eb76f8e74c35094678058c9d8"}}