{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J47MNN3MCJ56E36HF4TAA7YY46","short_pith_number":"pith:J47MNN3M","canonical_record":{"source":{"id":"2503.01333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T09:16:41Z","cross_cats_sorted":[],"title_canon_sha256":"51d81ca7185d1e4724287358ec801cde80914d4110f2e7ef54da16faea802a4b","abstract_canon_sha256":"9dda44f8f7410db58518982c2ccde31b9bdcc5564b8e031147496650d35eaa43"},"schema_version":"1.0"},"canonical_sha256":"4f3ec6b76c127be26fc72f26007f18e79155ce1c16c9137b7945786637a225ad","source":{"kind":"arxiv","id":"2503.01333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01333","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01333v1","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01333","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"J47MNN3MCJ56","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"J47MNN3MCJ56E36H","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"J47MNN3M","created_at":"2026-07-05T10:23:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J47MNN3MCJ56E36HF4TAA7YY46","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T09:16:41Z","cross_cats_sorted":[],"title_canon_sha256":"51d81ca7185d1e4724287358ec801cde80914d4110f2e7ef54da16faea802a4b","abstract_canon_sha256":"9dda44f8f7410db58518982c2ccde31b9bdcc5564b8e031147496650d35eaa43"},"schema_version":"1.0"},"canonical_sha256":"4f3ec6b76c127be26fc72f26007f18e79155ce1c16c9137b7945786637a225ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:04.798854Z","signature_b64":"tBbwxFqkMieea/fh+//av037lfixGCfRwYSsrYGDJmS8lCcMhNCjzCBQ3M/5/QWGbjEqSoCB3QMPsZicaWXVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f3ec6b76c127be26fc72f26007f18e79155ce1c16c9137b7945786637a225ad","last_reissued_at":"2026-07-05T10:23:04.798063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:04.798063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01333","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":"2026-07-05T10:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LoZueTBYjWCz3ZTRWg8EA05KFidwSEhlDenJ78kTzZi4GnPKHEhmDsKRNoaQ9f4eBJ8/JfSXm+D4x5wGt5QPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:41.067547Z"},"content_sha256":"88b9dc9d8c4bf396204fc8c12481e32623a7f0d01c7fee45844b98d097fd5e05","schema_version":"1.0","event_id":"sha256:88b9dc9d8c4bf396204fc8c12481e32623a7f0d01c7fee45844b98d097fd5e05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J47MNN3MCJ56E36HF4TAA7YY46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Group Relative Policy Optimization for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xu Liang","submitted_at":"2025-03-03T09:16:41Z","abstract_excerpt":"Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for reinforcement learning optimization. However, the SCST algorithm has certain defects. SCST relies only on a single greedy decoding result as a baseline. If the model itself is not stable enough, the greedy decoding result may be relatively worst, which will lead to a high variance of advantage estimation, further leading to unstable policy updates. In addition, SCST on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01333","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/2503.01333/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":"2026-07-05T10:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"faXvJk2EsAkz+fo00lhBH8A5CnXm6h30u09mMyWhzMuGBZd3pB0vQCODjW7PiOWw1mPeCOh0Kf6KLQTRpfw5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:41.068413Z"},"content_sha256":"4598f814f58c0b36619085ade49bfd93d05cef73f8c87e431e7ff31be867c9c2","schema_version":"1.0","event_id":"sha256:4598f814f58c0b36619085ade49bfd93d05cef73f8c87e431e7ff31be867c9c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J47MNN3MCJ56E36HF4TAA7YY46/bundle.json","state_url":"https://pith.science/pith/J47MNN3MCJ56E36HF4TAA7YY46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J47MNN3MCJ56E36HF4TAA7YY46/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":"2026-08-09T11:20:41Z","links":{"resolver":"https://pith.science/pith/J47MNN3MCJ56E36HF4TAA7YY46","bundle":"https://pith.science/pith/J47MNN3MCJ56E36HF4TAA7YY46/bundle.json","state":"https://pith.science/pith/J47MNN3MCJ56E36HF4TAA7YY46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J47MNN3MCJ56E36HF4TAA7YY46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J47MNN3MCJ56E36HF4TAA7YY46","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":"9dda44f8f7410db58518982c2ccde31b9bdcc5564b8e031147496650d35eaa43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T09:16:41Z","title_canon_sha256":"51d81ca7185d1e4724287358ec801cde80914d4110f2e7ef54da16faea802a4b"},"schema_version":"1.0","source":{"id":"2503.01333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01333","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01333v1","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01333","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"J47MNN3MCJ56","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"J47MNN3MCJ56E36H","created_at":"2026-07-05T10:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"J47MNN3M","created_at":"2026-07-05T10:23:04Z"}],"graph_snapshots":[{"event_id":"sha256:4598f814f58c0b36619085ade49bfd93d05cef73f8c87e431e7ff31be867c9c2","target":"graph","created_at":"2026-07-05T10:23:04Z","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/2503.01333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning tasks usually use two-stage training to complete model optimization. The first stage uses cross-entropy as the loss function for optimization, and the second stage uses self-critical sequence training (SCST) for reinforcement learning optimization. However, the SCST algorithm has certain defects. SCST relies only on a single greedy decoding result as a baseline. If the model itself is not stable enough, the greedy decoding result may be relatively worst, which will lead to a high variance of advantage estimation, further leading to unstable policy updates. In addition, SCST on","authors_text":"Xu Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T09:16:41Z","title":"Group Relative Policy Optimization for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01333","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":"sha256:88b9dc9d8c4bf396204fc8c12481e32623a7f0d01c7fee45844b98d097fd5e05","target":"record","created_at":"2026-07-05T10:23:04Z","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":"9dda44f8f7410db58518982c2ccde31b9bdcc5564b8e031147496650d35eaa43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-03T09:16:41Z","title_canon_sha256":"51d81ca7185d1e4724287358ec801cde80914d4110f2e7ef54da16faea802a4b"},"schema_version":"1.0","source":{"id":"2503.01333","kind":"arxiv","version":1}},"canonical_sha256":"4f3ec6b76c127be26fc72f26007f18e79155ce1c16c9137b7945786637a225ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f3ec6b76c127be26fc72f26007f18e79155ce1c16c9137b7945786637a225ad","first_computed_at":"2026-07-05T10:23:04.798063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:04.798063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tBbwxFqkMieea/fh+//av037lfixGCfRwYSsrYGDJmS8lCcMhNCjzCBQ3M/5/QWGbjEqSoCB3QMPsZicaWXVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:04.798854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88b9dc9d8c4bf396204fc8c12481e32623a7f0d01c7fee45844b98d097fd5e05","sha256:4598f814f58c0b36619085ade49bfd93d05cef73f8c87e431e7ff31be867c9c2"],"state_sha256":"749aba8dbe34d9729475d933d36b793bf14194c1043d17d41cea2630a4cf8052"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pu6jUq186OuoQKlK4r1B66tvXeJiV1b1v6fBdLXyQwHF05Cyd5zafrMcGRSrpVSViaO6iau8DL48AW0UrmSUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:20:41.075376Z","bundle_sha256":"4cf229fb915ff51322aeb1f5f6435ecafd01e1ce96e3ee711d7c5b4637b26d7c"}}