{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M6RRDG2TUVVIYRUH25Q5AWL2TU","short_pith_number":"pith:M6RRDG2T","canonical_record":{"source":{"id":"2607.28509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"ecd29fd2e58218d953c5722883221424693d976af7d3f5bdede5f4650329e49b","abstract_canon_sha256":"1a967fad418d132b09b21fa4f4960f1e97eb233f2ec87b9087b7ca5bbd4280a8"},"schema_version":"1.0"},"canonical_sha256":"67a3119b53a56a8c4687d761d0597a9d171cd31838dd6a0a52416deb39c31dc2","source":{"kind":"arxiv","id":"2607.28509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28509","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28509v1","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28509","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"pith_short_12","alias_value":"M6RRDG2TUVVI","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"pith_short_16","alias_value":"M6RRDG2TUVVIYRUH","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"pith_short_8","alias_value":"M6RRDG2T","created_at":"2026-07-31T01:38:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M6RRDG2TUVVIYRUH25Q5AWL2TU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"ecd29fd2e58218d953c5722883221424693d976af7d3f5bdede5f4650329e49b","abstract_canon_sha256":"1a967fad418d132b09b21fa4f4960f1e97eb233f2ec87b9087b7ca5bbd4280a8"},"schema_version":"1.0"},"canonical_sha256":"67a3119b53a56a8c4687d761d0597a9d171cd31838dd6a0a52416deb39c31dc2","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67a3119b53a56a8c4687d761d0597a9d171cd31838dd6a0a52416deb39c31dc2","last_reissued_at":"2026-07-31T01:38:18.184275Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:38:18.184275Z"},"source_kind":"arxiv","source_id":"2607.28509","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":"2026-07-31T01:38:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cszZ4gD2Rk1WnV3pIzWgNnS6IWRG6KY3pr28hkEVEN2E4mA186wn6tNPZpxwvddzhBjBFJOW8BvsJbDTlQg3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:20:59.484018Z"},"content_sha256":"930e052f57cecfe03e7d956397dc87678a28c0f3bd027c81d856a8be1201d706","schema_version":"1.0","event_id":"sha256:930e052f57cecfe03e7d956397dc87678a28c0f3bd027c81d856a8be1201d706"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M6RRDG2TUVVIYRUH25Q5AWL2TU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RefCaptioner: Multi-Reference Image-Grounded Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengxiang Wang, Haotian Wang, Jialu Chen, Qixun Wang, Tengfei Liu, Weihong Lin, Xiaohan Zhang, Xinlei Yu, Xinlong Chen, Xinwei Long, Xuanyu Zhu, Yang Shi, Yuanxing Zhang, Yue Ding, Yujie Wei, Yuqing Wen, Yuqi Tang, Yuran Wang, Zhuoran Zhang","submitted_at":"2026-07-30T16:48:28Z","abstract_excerpt":"Existing video captioning models generate natural descriptions of video content but cannot explicitly ground local visual elements to multiple reference images. We introduce multi-reference image-grounded video captioning, a new task requiring factual video descriptions with phrase-level reference grounding, and propose RefCaptioner, a two-stage post-training framework for this task. RefCaptioner combines mixed-data SFT with Hierarchical Coverage-Discounted GRPO to jointly improve reference selection, phrase-level binding, distractor rejection, and cross-reference consistency while preserving "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28509","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/2607.28509/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":"2026-07-31T01:38:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Of46wF/Of3w1SjXiAi3xAIrxXcq/a2t5gEtCnYs1EuahXkVy3uY1iD5hH2vx+Xr242tAXWjxhuNnphJBZGpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:20:59.484408Z"},"content_sha256":"ac79ce0053ba060b1b43c268170c62c90eb5365a22dcabcd7119433b91440fd1","schema_version":"1.0","event_id":"sha256:ac79ce0053ba060b1b43c268170c62c90eb5365a22dcabcd7119433b91440fd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU/bundle.json","state_url":"https://pith.science/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU/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":"2026-08-04T05:20:59Z","links":{"resolver":"https://pith.science/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU","bundle":"https://pith.science/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU/bundle.json","state":"https://pith.science/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6RRDG2TUVVIYRUH25Q5AWL2TU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M6RRDG2TUVVIYRUH25Q5AWL2TU","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":"1a967fad418d132b09b21fa4f4960f1e97eb233f2ec87b9087b7ca5bbd4280a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:48:28Z","title_canon_sha256":"ecd29fd2e58218d953c5722883221424693d976af7d3f5bdede5f4650329e49b"},"schema_version":"1.0","source":{"id":"2607.28509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28509","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28509v1","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28509","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"pith_short_12","alias_value":"M6RRDG2TUVVI","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"pith_short_16","alias_value":"M6RRDG2TUVVIYRUH","created_at":"2026-07-31T01:38:18Z"},{"alias_kind":"pith_short_8","alias_value":"M6RRDG2T","created_at":"2026-07-31T01:38:18Z"}],"graph_snapshots":[{"event_id":"sha256:ac79ce0053ba060b1b43c268170c62c90eb5365a22dcabcd7119433b91440fd1","target":"graph","created_at":"2026-07-31T01:38:18Z","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/2607.28509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing video captioning models generate natural descriptions of video content but cannot explicitly ground local visual elements to multiple reference images. We introduce multi-reference image-grounded video captioning, a new task requiring factual video descriptions with phrase-level reference grounding, and propose RefCaptioner, a two-stage post-training framework for this task. RefCaptioner combines mixed-data SFT with Hierarchical Coverage-Discounted GRPO to jointly improve reference selection, phrase-level binding, distractor rejection, and cross-reference consistency while preserving ","authors_text":"Fengxiang Wang, Haotian Wang, Jialu Chen, Qixun Wang, Tengfei Liu, Weihong Lin, Xiaohan Zhang, Xinlei Yu, Xinlong Chen, Xinwei Long, Xuanyu Zhu, Yang Shi, Yuanxing Zhang, Yue Ding, Yujie Wei, Yuqing Wen, Yuqi Tang, Yuran Wang, Zhuoran Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:48:28Z","title":"RefCaptioner: Multi-Reference Image-Grounded Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28509","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":"sha256:930e052f57cecfe03e7d956397dc87678a28c0f3bd027c81d856a8be1201d706","target":"record","created_at":"2026-07-31T01:38:18Z","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":"1a967fad418d132b09b21fa4f4960f1e97eb233f2ec87b9087b7ca5bbd4280a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:48:28Z","title_canon_sha256":"ecd29fd2e58218d953c5722883221424693d976af7d3f5bdede5f4650329e49b"},"schema_version":"1.0","source":{"id":"2607.28509","kind":"arxiv","version":1}},"canonical_sha256":"67a3119b53a56a8c4687d761d0597a9d171cd31838dd6a0a52416deb39c31dc2","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67a3119b53a56a8c4687d761d0597a9d171cd31838dd6a0a52416deb39c31dc2","first_computed_at":"2026-07-31T01:38:18.184275Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:38:18.184275Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:930e052f57cecfe03e7d956397dc87678a28c0f3bd027c81d856a8be1201d706","sha256:ac79ce0053ba060b1b43c268170c62c90eb5365a22dcabcd7119433b91440fd1"],"state_sha256":"754b1530bb72cb393cbf0d4dbfeab5580521f0a823acecab132ffe472a7c6bff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6V5aieKmWOVbC2TWBLA0ok0PT2OgWg7B9KUvxdKvd9EsTBx07nQOaurx2npOsJcJURIQMKEpVKxd2Hi9aRILDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:20:59.486740Z","bundle_sha256":"95f53ed7a9d5956ef68e791b3fb700d443613b38230494a2908616a90e6496d4"}}