{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F5KIEAQKKNBAV6MHLP3SPKPTRY","short_pith_number":"pith:F5KIEAQK","canonical_record":{"source":{"id":"2501.14818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:40:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6202cc7bd0fbacb17373320233927bb4be16cacf6c6e49cf8db58f3dc8fe03e","abstract_canon_sha256":"12ace8496d7ce62f58de75050183b4d054084b71df2ea5ea6ec494b9e95bba81"},"schema_version":"1.0"},"canonical_sha256":"2f5482020a53420af9875bf727a9f38e01098757400d39a6d0ae11852b195950","source":{"kind":"arxiv","id":"2501.14818","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14818","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14818v1","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14818","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"F5KIEAQKKNBA","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"F5KIEAQKKNBAV6MH","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"F5KIEAQK","created_at":"2026-07-05T10:05:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F5KIEAQKKNBAV6MHLP3SPKPTRY","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:40:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6202cc7bd0fbacb17373320233927bb4be16cacf6c6e49cf8db58f3dc8fe03e","abstract_canon_sha256":"12ace8496d7ce62f58de75050183b4d054084b71df2ea5ea6ec494b9e95bba81"},"schema_version":"1.0"},"canonical_sha256":"2f5482020a53420af9875bf727a9f38e01098757400d39a6d0ae11852b195950","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:19.090063Z","signature_b64":"8PFM5TE3g77Vkt1TstlITPK/dsi3381NWSluapn4vYEF8IIjcyLmrDdKCEa7Ndc39Alr4wUWUzzSgZRq/RTtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5482020a53420af9875bf727a9f38e01098757400d39a6d0ae11852b195950","last_reissued_at":"2026-07-05T10:05:19.089572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:19.089572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14818","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":"2026-07-05T10:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYp4605TZ2q+UrMUu6KaXrqgBDSi2eqt4xfB4d/6vBUTTib7iw65ZFWqlAHcLUEZhOtwuvIGiz4UXkh9zVJ/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:41:47.327599Z"},"content_sha256":"e172cb8e43f63dd0381378c71100594263760405a8046a681e22ddde3a9d39db","schema_version":"1.0","event_id":"sha256:e172cb8e43f63dd0381378c71100594263760405a8046a681e22ddde3a9d39db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F5KIEAQKKNBAV6MHLP3SPKPTRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amala Sanjay Deshmukh, Andrew Tao, Bryan Catanzaro, De-An Huang, Guilin Liu, Guo Chen, Hao Zhang, Ilia Karmanov, Jan Kautz, Jose M. Alvarez, Karan Sapra, Lukas Voegtle, Matthieu Le, Nadine Chang, Philipp Fischer, Shihao Wang, Shilong Liu, Shiyi Lan, Subhashree Radhakrishnan, Timo Roman, Tong Lu, Tuomas Rintamaki, Vibashan VS, Yilin Zhao, Yishen Ji, Zhiding Yu, Zhiqi Li","submitted_at":"2025-01-20T18:40:47Z","abstract_excerpt":"Recently, promising progress has been made by open-source vision-language models (VLMs) in bringing their capabilities closer to those of proprietary frontier models. However, most open-source models only publish their final model weights, leaving the critical details of data strategies and implementation largely opaque. In this work, we address VLM post-training from a data-centric perspective, showing the key role of data strategy in developing frontier VLMs. By studying and building our post-training data strategy from scratch, we share detailed insights into the development processes, aimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14818","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/2501.14818/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":"2026-07-05T10:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQEkVhQlBe41gtT3RGmzvRYQXpKG8OZfKlu1tTwRDfZ9cvd+6Rci0WpU/awd1Xyn7TUvXN2fvYgGGtKp3AeNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:41:47.329999Z"},"content_sha256":"577a7ccf7ae81d2b777895d3002f2b8018fce71d1731624ee6ec264d51e8dad2","schema_version":"1.0","event_id":"sha256:577a7ccf7ae81d2b777895d3002f2b8018fce71d1731624ee6ec264d51e8dad2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY/bundle.json","state_url":"https://pith.science/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY/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":"2026-08-06T02:41:47Z","links":{"resolver":"https://pith.science/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY","bundle":"https://pith.science/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY/bundle.json","state":"https://pith.science/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5KIEAQKKNBAV6MHLP3SPKPTRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F5KIEAQKKNBAV6MHLP3SPKPTRY","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":"12ace8496d7ce62f58de75050183b4d054084b71df2ea5ea6ec494b9e95bba81","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:40:47Z","title_canon_sha256":"d6202cc7bd0fbacb17373320233927bb4be16cacf6c6e49cf8db58f3dc8fe03e"},"schema_version":"1.0","source":{"id":"2501.14818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14818","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14818v1","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14818","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"F5KIEAQKKNBA","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"pith_short_16","alias_value":"F5KIEAQKKNBAV6MH","created_at":"2026-07-05T10:05:19Z"},{"alias_kind":"pith_short_8","alias_value":"F5KIEAQK","created_at":"2026-07-05T10:05:19Z"}],"graph_snapshots":[{"event_id":"sha256:577a7ccf7ae81d2b777895d3002f2b8018fce71d1731624ee6ec264d51e8dad2","target":"graph","created_at":"2026-07-05T10:05:19Z","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/2501.14818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, promising progress has been made by open-source vision-language models (VLMs) in bringing their capabilities closer to those of proprietary frontier models. However, most open-source models only publish their final model weights, leaving the critical details of data strategies and implementation largely opaque. In this work, we address VLM post-training from a data-centric perspective, showing the key role of data strategy in developing frontier VLMs. By studying and building our post-training data strategy from scratch, we share detailed insights into the development processes, aimi","authors_text":"Amala Sanjay Deshmukh, Andrew Tao, Bryan Catanzaro, De-An Huang, Guilin Liu, Guo Chen, Hao Zhang, Ilia Karmanov, Jan Kautz, Jose M. Alvarez, Karan Sapra, Lukas Voegtle, Matthieu Le, Nadine Chang, Philipp Fischer, Shihao Wang, Shilong Liu, Shiyi Lan, Subhashree Radhakrishnan, Timo Roman, Tong Lu, Tuomas Rintamaki, Vibashan VS, Yilin Zhao, Yishen Ji, Zhiding Yu, Zhiqi Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:40:47Z","title":"Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14818","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:e172cb8e43f63dd0381378c71100594263760405a8046a681e22ddde3a9d39db","target":"record","created_at":"2026-07-05T10:05:19Z","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":"12ace8496d7ce62f58de75050183b4d054084b71df2ea5ea6ec494b9e95bba81","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:40:47Z","title_canon_sha256":"d6202cc7bd0fbacb17373320233927bb4be16cacf6c6e49cf8db58f3dc8fe03e"},"schema_version":"1.0","source":{"id":"2501.14818","kind":"arxiv","version":1}},"canonical_sha256":"2f5482020a53420af9875bf727a9f38e01098757400d39a6d0ae11852b195950","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f5482020a53420af9875bf727a9f38e01098757400d39a6d0ae11852b195950","first_computed_at":"2026-07-05T10:05:19.089572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:19.089572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8PFM5TE3g77Vkt1TstlITPK/dsi3381NWSluapn4vYEF8IIjcyLmrDdKCEa7Ndc39Alr4wUWUzzSgZRq/RTtAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:19.090063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e172cb8e43f63dd0381378c71100594263760405a8046a681e22ddde3a9d39db","sha256:577a7ccf7ae81d2b777895d3002f2b8018fce71d1731624ee6ec264d51e8dad2"],"state_sha256":"853654ae0b7509413a5a2113b21f6be38b7714f22f68121363476bcf23dd91ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X6A0eDg6DUiTamPt/1Sjto4aZW2dpFRw/4JCQd/BWg2Kbb7TBIf8bwdUQ//7SHN1JY2eQf8Ge597cpPpXhGzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:41:47.336263Z","bundle_sha256":"d793516beb3a031862dd9220636248b21fd6abb85f2d767465d790733d8df69b"}}